Merge branch 'dev' into patch-1

.eslintignore

@@ -0,0 +1,4 @@
+extensions
+extensions-disabled
+repositories
+venv

.eslintrc.js

@@ -0,0 +1,91 @@
+/* global module */
+module.exports = {
+    env: {
+        browser: true,
+        es2021: true,
+    },
+    extends: "eslint:recommended",
+    parserOptions: {
+        ecmaVersion: "latest",
+    },
+    rules: {
+        "arrow-spacing": "error",
+        "block-spacing": "error",
+        "brace-style": "error",
+        "comma-dangle": ["error", "only-multiline"],
+        "comma-spacing": "error",
+        "comma-style": ["error", "last"],
+        "curly": ["error", "multi-line", "consistent"],
+        "eol-last": "error",
+        "func-call-spacing": "error",
+        "function-call-argument-newline": ["error", "consistent"],
+        "function-paren-newline": ["error", "consistent"],
+        "indent": ["error", 4],
+        "key-spacing": "error",
+        "keyword-spacing": "error",
+        "linebreak-style": ["error", "unix"],
+        "no-extra-semi": "error",
+        "no-mixed-spaces-and-tabs": "error",
+        "no-multi-spaces": "error",
+        "no-redeclare": ["error", {builtinGlobals: false}],
+        "no-trailing-spaces": "error",
+        "no-unused-vars": "off",
+        "no-whitespace-before-property": "error",
+        "object-curly-newline": ["error", {consistent: true, multiline: true}],
+        "object-curly-spacing": ["error", "never"],
+        "operator-linebreak": ["error", "after"],
+        "quote-props": ["error", "consistent-as-needed"],
+        "semi": ["error", "always"],
+        "semi-spacing": "error",
+        "semi-style": ["error", "last"],
+        "space-before-blocks": "error",
+        "space-before-function-paren": ["error", "never"],
+        "space-in-parens": ["error", "never"],
+        "space-infix-ops": "error",
+        "space-unary-ops": "error",
+        "switch-colon-spacing": "error",
+        "template-curly-spacing": ["error", "never"],
+        "unicode-bom": "error",
+    },
+    globals: {
+        //script.js
+        gradioApp: "readonly",
+        executeCallbacks: "readonly",
+        onAfterUiUpdate: "readonly",
+        onOptionsChanged: "readonly",
+        onUiLoaded: "readonly",
+        onUiUpdate: "readonly",
+        uiCurrentTab: "writable",
+        uiElementInSight: "readonly",
+        uiElementIsVisible: "readonly",
+        //ui.js
+        opts: "writable",
+        all_gallery_buttons: "readonly",
+        selected_gallery_button: "readonly",
+        selected_gallery_index: "readonly",
+        switch_to_txt2img: "readonly",
+        switch_to_img2img_tab: "readonly",
+        switch_to_img2img: "readonly",
+        switch_to_sketch: "readonly",
+        switch_to_inpaint: "readonly",
+        switch_to_inpaint_sketch: "readonly",
+        switch_to_extras: "readonly",
+        get_tab_index: "readonly",
+        create_submit_args: "readonly",
+        restart_reload: "readonly",
+        updateInput: "readonly",
+        //extraNetworks.js
+        requestGet: "readonly",
+        popup: "readonly",
+        // from python
+        localization: "readonly",
+        // progrssbar.js
+        randomId: "readonly",
+        requestProgress: "readonly",
+        // imageviewer.js
+        modalPrevImage: "readonly",
+        modalNextImage: "readonly",
+        // token-counters.js
+        setupTokenCounters: "readonly",
+    }
+};

.git-blame-ignore-revs

@@ -0,0 +1,2 @@
+# Apply ESlint
+9c54b78d9dde5601e916f308d9a9d6953ec39430

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -43,10 +43,19 @@ body:
   - type: input
     id: commit
     attributes:
-      label: Commit where the problem happens
+      label: Version or Commit where the problem happens
-      description: Which commit are you running ? (Do not write *Latest version/repo/commit*, as this means nothing and will have changed by the time we read your issue. Rather, copy the **Commit** link at the bottom of the UI, or from the cmd/terminal if you can't launch it.)
+      description: "Which webui version or commit are you running ? (Do not write *Latest Version/repo/commit*, as this means nothing and will have changed by the time we read your issue. Rather, copy the **Version: v1.2.3** link at the bottom of the UI, or from the cmd/terminal if you can't launch it.)"
     validations:
       required: true
+  - type: dropdown
+    id: py-version
+    attributes:
+      label: What Python version are you running on ?
+      multiple: false
+      options:
+        - Python 3.10.x
+        - Python 3.11.x (above, no supported yet)
+        - Python 3.9.x (below, no recommended)
   - type: dropdown
     id: platforms
     attributes:
@@ -59,6 +68,35 @@ body:
         - iOS
         - Android
         - Other/Cloud
+  - type: dropdown
+    id: device
+    attributes:
+        label: What device are you running WebUI on?
+        multiple: true
+        options:
+        - Nvidia GPUs (RTX 20 above)
+        - Nvidia GPUs (GTX 16 below)
+        - AMD GPUs (RX 6000 above)
+        - AMD GPUs (RX 5000 below)
+        - CPU
+        - Other GPUs
+  - type: dropdown
+    id: cross_attention_opt
+    attributes:
+      label: Cross attention optimization
+      description: What cross attention optimization are you using, Settings -> Optimizations -> Cross attention optimization
+      multiple: false
+      options:
+        - Automatic
+        - xformers
+        - sdp-no-mem
+        - sdp
+        - Doggettx
+        - V1 
+        - InvokeAI
+        - "None "
+    validations:
+      required: true
   - type: dropdown
     id: browsers
     attributes:

.github/pull_request_template.md

@@ -1,28 +1,15 @@
-# Please read the [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing) before submitting a pull request!
+## Description
 
-If you have a large change, pay special attention to this paragraph:
+* a simple description of what you're trying to accomplish
+* a summary of changes in code
+* which issues it fixes, if any
 
-> Before making changes, if you think that your feature will result in more than 100 lines changing, find me and talk to me about the feature you are proposing. It pains me to reject the hard work someone else did, but I won't add everything to the repo, and it's better if the rejection happens before you have to waste time working on the feature.
+## Screenshots/videos:
 
-Otherwise, after making sure you're following the rules described in wiki page, remove this section and continue on.
 
-**Describe what this pull request is trying to achieve.**
+## Checklist:
 
-A clear and concise description of what you're trying to accomplish with this, so your intent doesn't have to be extracted from your code.
+- [ ] I have read [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
-
+- [ ] I have performed a self-review of my own code
-**Additional notes and description of your changes**
+- [ ] My code follows the [style guidelines](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing#code-style)
-
+- [ ] My code passes [tests](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Tests)
-More technical discussion about your changes go here, plus anything that a maintainer might have to specifically take a look at, or be wary of.
-
-**Environment this was tested in**
-
-List the environment you have developed / tested this on. As per the contributing page, changes should be able to work on Windows out of the box.
- - OS: [e.g. Windows, Linux]
- - Browser: [e.g. chrome, safari]
- - Graphics card: [e.g. NVIDIA RTX 2080 8GB, AMD RX 6600 8GB]
-
-**Screenshots or videos of your changes**
-
-If applicable, screenshots or a video showing off your changes. If it edits an existing UI, it should ideally contain a comparison of what used to be there, before your changes were made.
-
-This is **required** for anything that touches the user interface.

.github/workflows/on_pull_request.yaml

@@ -1,39 +1,34 @@
-# See https://github.com/actions/starter-workflows/blob/1067f16ad8a1eac328834e4b0ae24f7d206f810d/ci/pylint.yml for original reference file
 name: Run Linting/Formatting on Pull Requests
 
 on:
   - push
   - pull_request
-  # See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#onpull_requestpull_request_targetbranchesbranches-ignore for syntax docs
-  # if you want to filter out branches, delete the `- pull_request` and uncomment these lines :
-  # pull_request:  
-  #  branches:
-  #    - master
-  #  branches-ignore:
-  #    - development
 
 jobs:
-  lint:
+  lint-python:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout Code
         uses: actions/checkout@v3
-      - name: Set up Python 3.10
+      - uses: actions/setup-python@v4
-        uses: actions/setup-python@v4
         with:
-          python-version: 3.10.6
+          python-version: 3.11
-          cache: pip
+          # NB: there's no cache: pip here since we're not installing anything
-          cache-dependency-path: |
+          #     from the requirements.txt file(s) in the repository; it's faster
-            **/requirements*txt
+          #     not to have GHA download an (at the time of writing) 4 GB cache
-      - name: Install PyLint
+          #     of PyTorch and other dependencies.
-        run: | 
+      - name: Install Ruff
-          python -m pip install --upgrade pip
+        run: pip install ruff==0.0.272
-          pip install pylint
+      - name: Run Ruff
-      # This lets PyLint check to see if it can resolve imports
+        run: ruff .
-      - name: Install dependencies
+  lint-js:
-        run: |
+    runs-on: ubuntu-latest
-          export COMMANDLINE_ARGS="--skip-torch-cuda-test --exit"
+    steps:
-          python launch.py
+      - name: Checkout Code
-      - name: Analysing the code with pylint
+        uses: actions/checkout@v3
-        run: |
+      - name: Install Node.js
-          pylint $(git ls-files '*.py')
+        uses: actions/setup-node@v3
+        with:
+          node-version: 18
+      - run: npm i --ci
+      - run: npm run lint

.github/workflows/run_tests.yaml

@@ -17,13 +17,54 @@ jobs:
           cache: pip
           cache-dependency-path: |
             **/requirements*txt
+            launch.py
+      - name: Install test dependencies
+        run: pip install wait-for-it -r requirements-test.txt
+        env:
+          PIP_DISABLE_PIP_VERSION_CHECK: "1"
+          PIP_PROGRESS_BAR: "off"
+      - name: Setup environment
+        run: python launch.py --skip-torch-cuda-test --exit
+        env:
+          PIP_DISABLE_PIP_VERSION_CHECK: "1"
+          PIP_PROGRESS_BAR: "off"
+          TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu
+          WEBUI_LAUNCH_LIVE_OUTPUT: "1"
+          PYTHONUNBUFFERED: "1"
+      - name: Start test server
+        run: >
+          python -m coverage run
+          --data-file=.coverage.server
+          launch.py
+          --skip-prepare-environment
+          --skip-torch-cuda-test
+          --test-server
+          --no-half
+          --disable-opt-split-attention
+          --use-cpu all
+          --api-server-stop
+          2>&1 | tee output.txt &
       - name: Run tests
-        run: python launch.py --tests test --no-half --disable-opt-split-attention --use-cpu all --skip-torch-cuda-test
+        run: |
-      - name: Upload main app stdout-stderr
+          wait-for-it --service 127.0.0.1:7860 -t 600
+          python -m pytest -vv --junitxml=test/results.xml --cov . --cov-report=xml --verify-base-url test
+      - name: Kill test server
+        if: always()
+        run: curl -vv -XPOST http://127.0.0.1:7860/sdapi/v1/server-stop && sleep 10
+      - name: Show coverage
+        run: |
+          python -m coverage combine .coverage*
+          python -m coverage report -i
+          python -m coverage html -i
+      - name: Upload main app output
         uses: actions/upload-artifact@v3
         if: always()
         with:
-          name: stdout-stderr
+          name: output
-          path: |
+          path: output.txt
-            test/stdout.txt
+      - name: Upload coverage HTML
-            test/stderr.txt
+        uses: actions/upload-artifact@v3
+        if: always()
+        with:
+          name: htmlcov
+          path: htmlcov

.gitignore

@@ -34,3 +34,6 @@ notification.mp3
 /test/stderr.txt
 /cache.json*
 /config_states/
+/node_modules
+/package-lock.json
+/.coverage*

CHANGELOG.md

@@ -1,56 +1,193 @@
+## 1.4.0
+
+### Features:
+ * zoom controls for inpainting
+ * run basic torch calculation at startup in parallel to reduce the performance impact of first generation
+ * option to pad prompt/neg prompt to be same length
+ * remove taming_transformers dependency
+ * custom k-diffusion scheduler settings
+ * add an option to show selected settings in main txt2img/img2img UI
+ * sysinfo tab in settings
+ * infer styles from prompts when pasting params into the UI
+ * an option to control the behavior of the above
+
+### Minor:
+ * bump Gradio to 3.32.0
+ * bump xformers to 0.0.20
+ * Add option to disable token counters
+ * tooltip fixes & optimizations
+ * make it possible to configure filename for the zip download
+ * `[vae_filename]` pattern for filenames
+ * Revert discarding penultimate sigma for DPM-Solver++(2M) SDE
+ * change UI reorder setting to multiselect
+ * read version info form CHANGELOG.md if git version info is not available
+ * link footer API to Wiki when API is not active
+ * persistent conds cache (opt-in optimization)
+ 
+### Extensions:
+ * After installing extensions, webui properly restarts the process rather than reloads the UI 
+ * Added VAE listing to web API. Via: /sdapi/v1/sd-vae
+ * custom unet support
+ * Add onAfterUiUpdate callback
+ * refactor EmbeddingDatabase.register_embedding() to allow unregistering
+ * add before_process callback for scripts
+ * add ability for alwayson scripts to specify section and let user reorder those sections
+ 
+### Bug Fixes:
+ * Fix dragging text to prompt
+ * fix incorrect quoting for infotext values with colon in them
+ * fix "hires. fix" prompt sharing same labels with txt2img_prompt
+ * Fix s_min_uncond default type int
+ * Fix for #10643 (Inpainting mask sometimes not working)
+ * fix bad styling for thumbs view in extra networks #10639
+ * fix for empty list of optimizations #10605
+ * small fixes to prepare_tcmalloc for Debian/Ubuntu compatibility
+ * fix --ui-debug-mode exit
+ * patch GitPython to not use leaky persistent processes
+ * fix duplicate Cross attention optimization after UI reload
+ * torch.cuda.is_available() check for SdOptimizationXformers
+ * fix hires fix using wrong conds in second pass if using Loras.
+ * handle exception when parsing generation parameters from png info
+ * fix upcast attention dtype error
+ * forcing Torch Version to 1.13.1 for RX 5000 series GPUs
+ * split mask blur into X and Y components, patch Outpainting MK2 accordingly
+ * don't die when a LoRA is a broken symlink
+ * allow activation of Generate Forever during generation
+
+
+## 1.3.2
+
+### Bug Fixes:
+ * fix files served out of tmp directory even if they are saved to disk
+ * fix postprocessing overwriting parameters
+
+## 1.3.1
+
+### Features:
+ * revert default cross attention optimization to Doggettx
+
+### Bug Fixes:
+ * fix bug: LoRA don't apply on dropdown list sd_lora
+ * fix png info always added even if setting is not enabled
+ * fix some fields not applying in xyz plot
+ * fix "hires. fix" prompt sharing same labels with txt2img_prompt
+ * fix lora hashes not being added properly to infotex if there is only one lora
+ * fix --use-cpu failing to work properly at startup
+ * make --disable-opt-split-attention command line option work again
+
+## 1.3.0
+
+### Features:
+ * add UI to edit defaults
+ * token merging (via dbolya/tomesd)
+ * settings tab rework: add a lot of additional explanations and links
+ * load extensions' Git metadata in parallel to loading the main program to save a ton of time during startup
+ * update extensions table: show branch, show date in separate column, and show version from tags if available
+ * TAESD - another option for cheap live previews
+ * allow choosing sampler and prompts for second pass of hires fix - hidden by default, enabled in settings
+ * calculate hashes for Lora
+ * add lora hashes to infotext
+ * when pasting infotext, use infotext's lora hashes to find local loras for `<lora:xxx:1>` entries whose hashes match loras the user has
+ * select cross attention optimization from UI
+
+### Minor:
+ * bump Gradio to 3.31.0
+ * bump PyTorch to 2.0.1 for macOS and Linux AMD
+ * allow setting defaults for elements in extensions' tabs
+ * allow selecting file type for live previews
+ * show "Loading..." for extra networks when displaying for the first time
+ * suppress ENSD infotext for samplers that don't use it
+ * clientside optimizations
+ * add options to show/hide hidden files and dirs in extra networks, and to not list models/files in hidden directories
+ * allow whitespace in styles.csv
+ * add option to reorder tabs
+ * move some functionality (swap resolution and set seed to -1) to client
+ * option to specify editor height for img2img
+ * button to copy image resolution into img2img width/height sliders
+ * switch from pyngrok to ngrok-py
+ * lazy-load images in extra networks UI
+ * set "Navigate image viewer with gamepad" option to false by default, by request
+ * change upscalers to download models into user-specified directory (from commandline args) rather than the default models/<...>
+ * allow hiding buttons in ui-config.json
+
+### Extensions:
+ * add /sdapi/v1/script-info api
+ * use Ruff to lint Python code
+ * use ESlint to lint Javascript code
+ * add/modify CFG callbacks for Self-Attention Guidance extension
+ * add command and endpoint for graceful server stopping
+ * add some locals (prompts/seeds/etc) from processing function into the Processing class as fields
+ * rework quoting for infotext items that have commas in them to use JSON (should be backwards compatible except for cases where it didn't work previously)
+ * add /sdapi/v1/refresh-loras api checkpoint post request
+ * tests overhaul
+
+### Bug Fixes:
+ * fix an issue preventing the program from starting if the user specifies a bad Gradio theme
+ * fix broken prompts from file script
+ * fix symlink scanning for extra networks
+ * fix --data-dir ignored when launching via webui-user.bat COMMANDLINE_ARGS
+ * allow web UI to be ran fully offline
+ * fix inability to run with --freeze-settings
+ * fix inability to merge checkpoint without adding metadata
+ * fix extra networks' save preview image not adding infotext for jpeg/webm
+ * remove blinking effect from text in hires fix and scale resolution preview
+ * make links to `http://<...>.git` extensions work in the extension tab
+ * fix bug with webui hanging at startup due to hanging git process
+
+
 ## 1.2.1
 
 ### Features:
- * add an option to always refer to lora by filenames
+ * add an option to always refer to LoRA by filenames
 
 ### Bug Fixes:
- * never refer to lora by an alias if multiple loras have same alias or the alias is called none
+ * never refer to LoRA by an alias if multiple LoRAs have same alias or the alias is called none
  * fix upscalers disappearing after the user reloads UI
- * allow bf16 in safe unpickler (resolves problems with loading some loras)
+ * allow bf16 in safe unpickler (resolves problems with loading some LoRAs)
  * allow web UI to be ran fully offline
  * fix localizations not working
- * fix error for loras: 'LatentDiffusion' object has no attribute 'lora_layer_mapping'
+ * fix error for LoRAs: `'LatentDiffusion' object has no attribute 'lora_layer_mapping'`
 
 ## 1.2.0
 
 ### Features:
- * do not wait for stable diffusion model to load at startup
+ * do not wait for Stable Diffusion model to load at startup
- * add filename patterns: [denoising]
+ * add filename patterns: `[denoising]`
- * directory hiding for extra networks: dirs starting with . will hide their cards on extra network tabs unless specifically searched for
+ * directory hiding for extra networks: dirs starting with `.` will hide their cards on extra network tabs unless specifically searched for
- * Lora: for the `<...>` text in prompt, use name of Lora that is in the metdata of the file, if present, instead of filename (both can be used to activate lora)
+ * LoRA: for the `<...>` text in prompt, use name of LoRA that is in the metdata of the file, if present, instead of filename (both can be used to activate LoRA)
- * Lora: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active
+ * LoRA: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active
- * Lora: Fix some Loras not working (ones that have 3x3 convolution layer)
+ * LoRA: fix some LoRAs not working (ones that have 3x3 convolution layer)
- * Lora: add an option to use old method of applying loras (producing same results as with kohya-ss)
+ * LoRA: add an option to use old method of applying LoRAs (producing same results as with kohya-ss)
  * add version to infotext, footer and console output when starting
  * add links to wiki for filename pattern settings
  * add extended info for quicksettings setting and use multiselect input instead of a text field
 
 ### Minor:
- * gradio bumped to 3.29.0
+ * bump Gradio to 3.29.0
- * torch bumped to 2.0.1
+ * bump PyTorch to 2.0.1
- * --subpath option for gradio for use with reverse proxy
+ * `--subpath` option for gradio for use with reverse proxy
- * linux/OSX: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)
+ * Linux/macOS: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)
- * possible frontend optimization: do not apply localizations if there are none
+ * do not apply localizations if there are none (possible frontend optimization)
- * Add extra `None` option for VAE in XYZ plot
+ * add extra `None` option for VAE in XYZ plot
  * print error to console when batch processing in img2img fails
  * create HTML for extra network pages only on demand
- * allow directories starting with . to still list their models for lora, checkpoints, etc
+ * allow directories starting with `.` to still list their models for LoRA, checkpoints, etc
  * put infotext options into their own category in settings tab
  * do not show licenses page when user selects Show all pages in settings
 
 ### Extensions:
- * Tooltip localization support
+ * tooltip localization support
- * Add api method to get LoRA models with prompt
+ * add API method to get LoRA models with prompt
 
 ### Bug Fixes:
- * re-add /docs endpoint
+ * re-add `/docs` endpoint
  * fix gamepad navigation
  * make the lightbox fullscreen image function properly
  * fix squished thumbnails in extras tab
  * keep "search" filter for extra networks when user refreshes the tab (previously it showed everthing after you refreshed)
  * fix webui showing the same image if you configure the generation to always save results into same file
  * fix bug with upscalers not working properly
- * Fix MPS on PyTorch 2.0.1, Intel Macs
+ * fix MPS on PyTorch 2.0.1, Intel Macs
  * make it so that custom context menu from contextMenu.js only disappears after user's click, ignoring non-user click events
  * prevent Reload UI button/link from reloading the page when it's not yet ready
  * fix prompts from file script failing to read contents from a drag/drop file
@@ -58,20 +195,20 @@
 
 ## 1.1.1
 ### Bug Fixes:
- * fix an error that prevents running webui on torch<2.0 without --disable-safe-unpickle
+ * fix an error that prevents running webui on PyTorch<2.0 without --disable-safe-unpickle
 
 ## 1.1.0
 ### Features:
- * switch to torch 2.0.0 (except for AMD GPUs)
+ * switch to PyTorch 2.0.0 (except for AMD GPUs)
  * visual improvements to custom code scripts
- * add filename patterns: [clip_skip], [hasprompt<>], [batch_number], [generation_number]
+ * add filename patterns: `[clip_skip]`, `[hasprompt<>]`, `[batch_number]`, `[generation_number]`
  * add support for saving init images in img2img, and record their hashes in infotext for reproducability
  * automatically select current word when adjusting weight with ctrl+up/down
  * add dropdowns for X/Y/Z plot
- * setting: Stable Diffusion/Random number generator source: makes it possible to make images generated from a given manual seed consistent across different GPUs
+ * add setting: Stable Diffusion/Random number generator source: makes it possible to make images generated from a given manual seed consistent across different GPUs
  * support Gradio's theme API
  * use TCMalloc on Linux by default; possible fix for memory leaks
- * (optimization) option to remove negative conditioning at low sigma values #9177
+ * add optimization option to remove negative conditioning at low sigma values #9177
  * embed model merge metadata in .safetensors file
  * extension settings backup/restore feature #9169
  * add "resize by" and "resize to" tabs to img2img
@@ -80,22 +217,22 @@
  * button to restore the progress from session lost / tab reload
 
 ### Minor:
- * gradio bumped to 3.28.1
+ * bump Gradio to 3.28.1
- * in extra tab, change extras "scale to" to sliders
+ * change "scale to" to sliders in Extras tab
  * add labels to tool buttons to make it possible to hide them
  * add tiled inference support for ScuNET
  * add branch support for extension installation
- * change linux installation script to insall into current directory rather than /home/username
+ * change Linux installation script to install into current directory rather than `/home/username`
- * sort textual inversion embeddings by name (case insensitive)
+ * sort textual inversion embeddings by name (case-insensitive)
  * allow styles.csv to be symlinked or mounted in docker
  * remove the "do not add watermark to images" option
  * make selected tab configurable with UI config
- * extra networks UI in now fixed height and scrollable
+ * make the extra networks UI fixed height and scrollable
- * add disable_tls_verify arg for use with self-signed certs
+ * add `disable_tls_verify` arg for use with self-signed certs
 
 ### Extensions:
- * Add reload callback
+ * add reload callback
- * add is_hr_pass field for processing
+ * add `is_hr_pass` field for processing
 
 ### Bug Fixes:
  * fix broken batch image processing on 'Extras/Batch Process' tab
@@ -111,10 +248,10 @@
  * one broken image in img2img batch won't stop all processing
  * fix image orientation bug in train/preprocess
  * fix Ngrok recreating tunnels every reload
- * fix --realesrgan-models-path and --ldsr-models-path not working
+ * fix `--realesrgan-models-path` and `--ldsr-models-path` not working
- * fix --skip-install not working
+ * fix `--skip-install` not working
- * outpainting Mk2 & Poorman should use the SAMPLE file format to save images, not GRID file format
+ * use SAMPLE file format in Outpainting Mk2 & Poorman
- * do not fail all Loras if some have failed to load when making a picture
+ * do not fail all LoRAs if some have failed to load when making a picture
 
 ## 1.0.0
   * everything

README.md

@@ -15,7 +15,7 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Attention, specify parts of text that the model should pay more attention to
     - a man in a `((tuxedo))` - will pay more attention to tuxedo
     - a man in a `(tuxedo:1.21)` - alternative syntax
-    - select text and press `Ctrl+Up` or `Ctrl+Down` to automatically adjust attention to selected text (code contributed by anonymous user)
+    - select text and press `Ctrl+Up` or `Ctrl+Down` (or `Command+Up` or `Command+Down` if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)
 - Loopback, run img2img processing multiple times
 - X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
 - Textual Inversion
@@ -99,6 +99,12 @@ Alternatively, use online services (like Google Colab):
 
 - [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
 
+### Installation on Windows 10/11 with NVidia-GPUs using release package
+1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.0.0-pre) and extract it's contents.
+2. Run `update.bat`.
+3. Run `run.bat`.
+> For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs)
+
 ### Automatic Installation on Windows
 1. Install [Python 3.10.6](https://www.python.org/downloads/release/python-3106/) (Newer version of Python does not support torch), checking "Add Python to PATH".
 2. Install [git](https://git-scm.com/download/win).
@@ -158,5 +164,6 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al
 - Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
 - Security advice - RyotaK
 - UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
+- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
 - (You)

extensions-builtin/LDSR/ldsr_model_arch.py

@@ -88,7 +88,7 @@ class LDSR:
 
         x_t = None
         logs = None
-        for n in range(n_runs):
+        for _ in range(n_runs):
             if custom_shape is not None:
                 x_t = torch.randn(1, custom_shape[1], custom_shape[2], custom_shape[3]).to(model.device)
                 x_t = repeat(x_t, '1 c h w -> b c h w', b=custom_shape[0])
@@ -110,7 +110,6 @@ class LDSR:
         diffusion_steps = int(steps)
         eta = 1.0
 
-        down_sample_method = 'Lanczos'
 
         gc.collect()
         if torch.cuda.is_available:
@@ -158,7 +157,7 @@ class LDSR:
 
 
 def get_cond(selected_path):
-    example = dict()
+    example = {}
     up_f = 4
     c = selected_path.convert('RGB')
     c = torch.unsqueeze(torchvision.transforms.ToTensor()(c), 0)
@@ -196,7 +195,7 @@ def convsample_ddim(model, cond, steps, shape, eta=1.0, callback=None, normals_s
 @torch.no_grad()
 def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize_x0=False, custom_shape=None, temperature=1., noise_dropout=0., corrector=None,
                               corrector_kwargs=None, x_T=None, ddim_use_x0_pred=False):
-    log = dict()
+    log = {}
 
     z, c, x, xrec, xc = model.get_input(batch, model.first_stage_key,
                                         return_first_stage_outputs=True,
@@ -244,7 +243,7 @@ def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize
         x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True)
         log["sample_noquant"] = x_sample_noquant
         log["sample_diff"] = torch.abs(x_sample_noquant - x_sample)
-    except:
+    except Exception:
         pass
 
     log["sample"] = x_sample

extensions-builtin/LDSR/scripts/ldsr_model.py

@@ -1,13 +1,11 @@
 import os
-import sys
-import traceback
-
-from basicsr.utils.download_util import load_file_from_url
 
+from modules.modelloader import load_file_from_url
 from modules.upscaler import Upscaler, UpscalerData
 from ldsr_model_arch import LDSR
-from modules import shared, script_callbacks
+from modules import shared, script_callbacks, errors
-import sd_hijack_autoencoder, sd_hijack_ddpm_v1
+import sd_hijack_autoencoder  # noqa: F401
+import sd_hijack_ddpm_v1  # noqa: F401
 
 
 class UpscalerLDSR(Upscaler):
@@ -44,22 +42,17 @@ class UpscalerLDSR(Upscaler):
         if local_safetensors_path is not None and os.path.exists(local_safetensors_path):
             model = local_safetensors_path
         else:
-            model = local_ckpt_path if local_ckpt_path is not None else load_file_from_url(url=self.model_url, model_dir=self.model_path, file_name="model.ckpt", progress=True)
+            model = local_ckpt_path or load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name="model.ckpt")
 
-        yaml = local_yaml_path if local_yaml_path is not None else load_file_from_url(url=self.yaml_url, model_dir=self.model_path, file_name="project.yaml", progress=True)
+        yaml = local_yaml_path or load_file_from_url(self.yaml_url, model_dir=self.model_download_path, file_name="project.yaml")
 
-        try:
         return LDSR(model, yaml)
 
-        except Exception:
-            print("Error importing LDSR:", file=sys.stderr)
-            print(traceback.format_exc(), file=sys.stderr)
-        return None
-
     def do_upscale(self, img, path):
+        try:
             ldsr = self.load_model(path)
-        if ldsr is None:
+        except Exception:
-            print("NO LDSR!")
+            errors.report(f"Failed loading LDSR model {path}", exc_info=True)
             return img
         ddim_steps = shared.opts.ldsr_steps
         return ldsr.super_resolution(img, ddim_steps, self.scale)

extensions-builtin/LDSR/sd_hijack_autoencoder.py

@@ -1,16 +1,21 @@
 # The content of this file comes from the ldm/models/autoencoder.py file of the compvis/stable-diffusion repo
 # The VQModel & VQModelInterface were subsequently removed from ldm/models/autoencoder.py when we moved to the stability-ai/stablediffusion repo
 # As the LDSR upscaler relies on VQModel & VQModelInterface, the hijack aims to put them back into the ldm.models.autoencoder
-
+import numpy as np
 import torch
 import pytorch_lightning as pl
 import torch.nn.functional as F
 from contextlib import contextmanager
-from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer
+
+from torch.optim.lr_scheduler import LambdaLR
+
+from ldm.modules.ema import LitEma
+from vqvae_quantize import VectorQuantizer2 as VectorQuantizer
 from ldm.modules.diffusionmodules.model import Encoder, Decoder
 from ldm.util import instantiate_from_config
 
 import ldm.models.autoencoder
+from packaging import version
 
 class VQModel(pl.LightningModule):
     def __init__(self,
@@ -19,7 +24,7 @@ class VQModel(pl.LightningModule):
                  n_embed,
                  embed_dim,
                  ckpt_path=None,
-                 ignore_keys=[],
+                 ignore_keys=None,
                  image_key="image",
                  colorize_nlabels=None,
                  monitor=None,
@@ -57,7 +62,7 @@ class VQModel(pl.LightningModule):
             print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
 
         if ckpt_path is not None:
-            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys)
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [])
         self.scheduler_config = scheduler_config
         self.lr_g_factor = lr_g_factor
 
@@ -76,18 +81,19 @@ class VQModel(pl.LightningModule):
                 if context is not None:
                     print(f"{context}: Restored training weights")
 
-    def init_from_ckpt(self, path, ignore_keys=list()):
+    def init_from_ckpt(self, path, ignore_keys=None):
         sd = torch.load(path, map_location="cpu")["state_dict"]
         keys = list(sd.keys())
         for k in keys:
-            for ik in ignore_keys:
+            for ik in ignore_keys or []:
                 if k.startswith(ik):
                     print("Deleting key {} from state_dict.".format(k))
                     del sd[k]
         missing, unexpected = self.load_state_dict(sd, strict=False)
         print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
-        if len(missing) > 0:
+        if missing:
             print(f"Missing Keys: {missing}")
+        if unexpected:
             print(f"Unexpected Keys: {unexpected}")
 
     def on_train_batch_end(self, *args, **kwargs):
@@ -165,7 +171,7 @@ class VQModel(pl.LightningModule):
     def validation_step(self, batch, batch_idx):
         log_dict = self._validation_step(batch, batch_idx)
         with self.ema_scope():
-            log_dict_ema = self._validation_step(batch, batch_idx, suffix="_ema")
+            self._validation_step(batch, batch_idx, suffix="_ema")
         return log_dict
 
     def _validation_step(self, batch, batch_idx, suffix=""):
@@ -232,7 +238,7 @@ class VQModel(pl.LightningModule):
         return self.decoder.conv_out.weight
 
     def log_images(self, batch, only_inputs=False, plot_ema=False, **kwargs):
-        log = dict()
+        log = {}
         x = self.get_input(batch, self.image_key)
         x = x.to(self.device)
         if only_inputs:
@@ -249,7 +255,8 @@ class VQModel(pl.LightningModule):
         if plot_ema:
             with self.ema_scope():
                 xrec_ema, _ = self(x)
-                if x.shape[1] > 3: xrec_ema = self.to_rgb(xrec_ema)
+                if x.shape[1] > 3:
+                    xrec_ema = self.to_rgb(xrec_ema)
                 log["reconstructions_ema"] = xrec_ema
         return log
 
@@ -264,7 +271,7 @@ class VQModel(pl.LightningModule):
 
 class VQModelInterface(VQModel):
     def __init__(self, embed_dim, *args, **kwargs):
-        super().__init__(embed_dim=embed_dim, *args, **kwargs)
+        super().__init__(*args, embed_dim=embed_dim, **kwargs)
         self.embed_dim = embed_dim
 
     def encode(self, x):
@@ -282,5 +289,5 @@ class VQModelInterface(VQModel):
         dec = self.decoder(quant)
         return dec
 
-setattr(ldm.models.autoencoder, "VQModel", VQModel)
+ldm.models.autoencoder.VQModel = VQModel
-setattr(ldm.models.autoencoder, "VQModelInterface", VQModelInterface)
+ldm.models.autoencoder.VQModelInterface = VQModelInterface

extensions-builtin/LDSR/sd_hijack_ddpm_v1.py

@@ -48,7 +48,7 @@ class DDPMV1(pl.LightningModule):
                  beta_schedule="linear",
                  loss_type="l2",
                  ckpt_path=None,
-                 ignore_keys=[],
+                 ignore_keys=None,
                  load_only_unet=False,
                  monitor="val/loss",
                  use_ema=True,
@@ -100,7 +100,7 @@ class DDPMV1(pl.LightningModule):
         if monitor is not None:
             self.monitor = monitor
         if ckpt_path is not None:
-            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [], only_model=load_only_unet)
 
         self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
                                linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
@@ -182,22 +182,22 @@ class DDPMV1(pl.LightningModule):
                 if context is not None:
                     print(f"{context}: Restored training weights")
 
-    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+    def init_from_ckpt(self, path, ignore_keys=None, only_model=False):
         sd = torch.load(path, map_location="cpu")
         if "state_dict" in list(sd.keys()):
             sd = sd["state_dict"]
         keys = list(sd.keys())
         for k in keys:
-            for ik in ignore_keys:
+            for ik in ignore_keys or []:
                 if k.startswith(ik):
                     print("Deleting key {} from state_dict.".format(k))
                     del sd[k]
         missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
             sd, strict=False)
         print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
-        if len(missing) > 0:
+        if missing:
             print(f"Missing Keys: {missing}")
-        if len(unexpected) > 0:
+        if unexpected:
             print(f"Unexpected Keys: {unexpected}")
 
     def q_mean_variance(self, x_start, t):
@@ -375,7 +375,7 @@ class DDPMV1(pl.LightningModule):
 
     @torch.no_grad()
     def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
-        log = dict()
+        log = {}
         x = self.get_input(batch, self.first_stage_key)
         N = min(x.shape[0], N)
         n_row = min(x.shape[0], n_row)
@@ -383,7 +383,7 @@ class DDPMV1(pl.LightningModule):
         log["inputs"] = x
 
         # get diffusion row
-        diffusion_row = list()
+        diffusion_row = []
         x_start = x[:n_row]
 
         for t in range(self.num_timesteps):
@@ -444,13 +444,13 @@ class LatentDiffusionV1(DDPMV1):
             conditioning_key = None
         ckpt_path = kwargs.pop("ckpt_path", None)
         ignore_keys = kwargs.pop("ignore_keys", [])
-        super().__init__(conditioning_key=conditioning_key, *args, **kwargs)
+        super().__init__(*args, conditioning_key=conditioning_key, **kwargs)
         self.concat_mode = concat_mode
         self.cond_stage_trainable = cond_stage_trainable
         self.cond_stage_key = cond_stage_key
         try:
             self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
-        except:
+        except Exception:
             self.num_downs = 0
         if not scale_by_std:
             self.scale_factor = scale_factor
@@ -877,16 +877,6 @@ class LatentDiffusionV1(DDPMV1):
                 c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
         return self.p_losses(x, c, t, *args, **kwargs)
 
-    def _rescale_annotations(self, bboxes, crop_coordinates):  # TODO: move to dataset
-        def rescale_bbox(bbox):
-            x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
-            y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
-            w = min(bbox[2] / crop_coordinates[2], 1 - x0)
-            h = min(bbox[3] / crop_coordinates[3], 1 - y0)
-            return x0, y0, w, h
-
-        return [rescale_bbox(b) for b in bboxes]
-
     def apply_model(self, x_noisy, t, cond, return_ids=False):
 
         if isinstance(cond, dict):
@@ -1126,7 +1116,7 @@ class LatentDiffusionV1(DDPMV1):
         if cond is not None:
             if isinstance(cond, dict):
                 cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
-                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+                [x[:batch_size] for x in cond[key]] for key in cond}
             else:
                 cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
 
@@ -1157,8 +1147,10 @@ class LatentDiffusionV1(DDPMV1):
 
             if i % log_every_t == 0 or i == timesteps - 1:
                 intermediates.append(x0_partial)
-            if callback: callback(i)
+            if callback:
-            if img_callback: img_callback(img, i)
+                callback(i)
+            if img_callback:
+                img_callback(img, i)
         return img, intermediates
 
     @torch.no_grad()
@@ -1205,8 +1197,10 @@ class LatentDiffusionV1(DDPMV1):
 
             if i % log_every_t == 0 or i == timesteps - 1:
                 intermediates.append(img)
-            if callback: callback(i)
+            if callback:
-            if img_callback: img_callback(img, i)
+                callback(i)
+            if img_callback:
+                img_callback(img, i)
 
         if return_intermediates:
             return img, intermediates
@@ -1221,7 +1215,7 @@ class LatentDiffusionV1(DDPMV1):
         if cond is not None:
             if isinstance(cond, dict):
                 cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
-                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+                [x[:batch_size] for x in cond[key]] for key in cond}
             else:
                 cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
         return self.p_sample_loop(cond,
@@ -1253,7 +1247,7 @@ class LatentDiffusionV1(DDPMV1):
 
         use_ddim = ddim_steps is not None
 
-        log = dict()
+        log = {}
         z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
                                            return_first_stage_outputs=True,
                                            force_c_encode=True,
@@ -1280,7 +1274,7 @@ class LatentDiffusionV1(DDPMV1):
 
         if plot_diffusion_rows:
             # get diffusion row
-            diffusion_row = list()
+            diffusion_row = []
             z_start = z[:n_row]
             for t in range(self.num_timesteps):
                 if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
@@ -1322,7 +1316,7 @@ class LatentDiffusionV1(DDPMV1):
 
             if inpaint:
                 # make a simple center square
-                b, h, w = z.shape[0], z.shape[2], z.shape[3]
+                h, w = z.shape[2], z.shape[3]
                 mask = torch.ones(N, h, w).to(self.device)
                 # zeros will be filled in
                 mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
@@ -1424,10 +1418,10 @@ class Layout2ImgDiffusionV1(LatentDiffusionV1):
     # TODO: move all layout-specific hacks to this class
     def __init__(self, cond_stage_key, *args, **kwargs):
         assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
-        super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+        super().__init__(*args, cond_stage_key=cond_stage_key, **kwargs)
 
     def log_images(self, batch, N=8, *args, **kwargs):
-        logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+        logs = super().log_images(*args, batch=batch, N=N, **kwargs)
 
         key = 'train' if self.training else 'validation'
         dset = self.trainer.datamodule.datasets[key]
@@ -1443,7 +1437,7 @@ class Layout2ImgDiffusionV1(LatentDiffusionV1):
         logs['bbox_image'] = cond_img
         return logs
 
-setattr(ldm.models.diffusion.ddpm, "DDPMV1", DDPMV1)
+ldm.models.diffusion.ddpm.DDPMV1 = DDPMV1
-setattr(ldm.models.diffusion.ddpm, "LatentDiffusionV1", LatentDiffusionV1)
+ldm.models.diffusion.ddpm.LatentDiffusionV1 = LatentDiffusionV1
-setattr(ldm.models.diffusion.ddpm, "DiffusionWrapperV1", DiffusionWrapperV1)
+ldm.models.diffusion.ddpm.DiffusionWrapperV1 = DiffusionWrapperV1
-setattr(ldm.models.diffusion.ddpm, "Layout2ImgDiffusionV1", Layout2ImgDiffusionV1)
+ldm.models.diffusion.ddpm.Layout2ImgDiffusionV1 = Layout2ImgDiffusionV1

extensions-builtin/LDSR/vqvae_quantize.py

@@ -0,0 +1,147 @@
+# Vendored from https://raw.githubusercontent.com/CompVis/taming-transformers/24268930bf1dce879235a7fddd0b2355b84d7ea6/taming/modules/vqvae/quantize.py,
+# where the license is as follows:
+#
+# Copyright (c) 2020 Patrick Esser and Robin Rombach and Björn Ommer
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE
+# OR OTHER DEALINGS IN THE SOFTWARE./
+
+import torch
+import torch.nn as nn
+import numpy as np
+from einops import rearrange
+
+
+class VectorQuantizer2(nn.Module):
+    """
+    Improved version over VectorQuantizer, can be used as a drop-in replacement. Mostly
+    avoids costly matrix multiplications and allows for post-hoc remapping of indices.
+    """
+
+    # NOTE: due to a bug the beta term was applied to the wrong term. for
+    # backwards compatibility we use the buggy version by default, but you can
+    # specify legacy=False to fix it.
+    def __init__(self, n_e, e_dim, beta, remap=None, unknown_index="random",
+                 sane_index_shape=False, legacy=True):
+        super().__init__()
+        self.n_e = n_e
+        self.e_dim = e_dim
+        self.beta = beta
+        self.legacy = legacy
+
+        self.embedding = nn.Embedding(self.n_e, self.e_dim)
+        self.embedding.weight.data.uniform_(-1.0 / self.n_e, 1.0 / self.n_e)
+
+        self.remap = remap
+        if self.remap is not None:
+            self.register_buffer("used", torch.tensor(np.load(self.remap)))
+            self.re_embed = self.used.shape[0]
+            self.unknown_index = unknown_index  # "random" or "extra" or integer
+            if self.unknown_index == "extra":
+                self.unknown_index = self.re_embed
+                self.re_embed = self.re_embed + 1
+            print(f"Remapping {self.n_e} indices to {self.re_embed} indices. "
+                  f"Using {self.unknown_index} for unknown indices.")
+        else:
+            self.re_embed = n_e
+
+        self.sane_index_shape = sane_index_shape
+
+    def remap_to_used(self, inds):
+        ishape = inds.shape
+        assert len(ishape) > 1
+        inds = inds.reshape(ishape[0], -1)
+        used = self.used.to(inds)
+        match = (inds[:, :, None] == used[None, None, ...]).long()
+        new = match.argmax(-1)
+        unknown = match.sum(2) < 1
+        if self.unknown_index == "random":
+            new[unknown] = torch.randint(0, self.re_embed, size=new[unknown].shape).to(device=new.device)
+        else:
+            new[unknown] = self.unknown_index
+        return new.reshape(ishape)
+
+    def unmap_to_all(self, inds):
+        ishape = inds.shape
+        assert len(ishape) > 1
+        inds = inds.reshape(ishape[0], -1)
+        used = self.used.to(inds)
+        if self.re_embed > self.used.shape[0]:  # extra token
+            inds[inds >= self.used.shape[0]] = 0  # simply set to zero
+        back = torch.gather(used[None, :][inds.shape[0] * [0], :], 1, inds)
+        return back.reshape(ishape)
+
+    def forward(self, z, temp=None, rescale_logits=False, return_logits=False):
+        assert temp is None or temp == 1.0, "Only for interface compatible with Gumbel"
+        assert rescale_logits is False, "Only for interface compatible with Gumbel"
+        assert return_logits is False, "Only for interface compatible with Gumbel"
+        # reshape z -> (batch, height, width, channel) and flatten
+        z = rearrange(z, 'b c h w -> b h w c').contiguous()
+        z_flattened = z.view(-1, self.e_dim)
+        # distances from z to embeddings e_j (z - e)^2 = z^2 + e^2 - 2 e * z
+
+        d = torch.sum(z_flattened ** 2, dim=1, keepdim=True) + \
+            torch.sum(self.embedding.weight ** 2, dim=1) - 2 * \
+            torch.einsum('bd,dn->bn', z_flattened, rearrange(self.embedding.weight, 'n d -> d n'))
+
+        min_encoding_indices = torch.argmin(d, dim=1)
+        z_q = self.embedding(min_encoding_indices).view(z.shape)
+        perplexity = None
+        min_encodings = None
+
+        # compute loss for embedding
+        if not self.legacy:
+            loss = self.beta * torch.mean((z_q.detach() - z) ** 2) + \
+                   torch.mean((z_q - z.detach()) ** 2)
+        else:
+            loss = torch.mean((z_q.detach() - z) ** 2) + self.beta * \
+                   torch.mean((z_q - z.detach()) ** 2)
+
+        # preserve gradients
+        z_q = z + (z_q - z).detach()
+
+        # reshape back to match original input shape
+        z_q = rearrange(z_q, 'b h w c -> b c h w').contiguous()
+
+        if self.remap is not None:
+            min_encoding_indices = min_encoding_indices.reshape(z.shape[0], -1)  # add batch axis
+            min_encoding_indices = self.remap_to_used(min_encoding_indices)
+            min_encoding_indices = min_encoding_indices.reshape(-1, 1)  # flatten
+
+        if self.sane_index_shape:
+            min_encoding_indices = min_encoding_indices.reshape(
+                z_q.shape[0], z_q.shape[2], z_q.shape[3])
+
+        return z_q, loss, (perplexity, min_encodings, min_encoding_indices)
+
+    def get_codebook_entry(self, indices, shape):
+        # shape specifying (batch, height, width, channel)
+        if self.remap is not None:
+            indices = indices.reshape(shape[0], -1)  # add batch axis
+            indices = self.unmap_to_all(indices)
+            indices = indices.reshape(-1)  # flatten again
+
+        # get quantized latent vectors
+        z_q = self.embedding(indices)
+
+        if shape is not None:
+            z_q = z_q.view(shape)
+            # reshape back to match original input shape
+            z_q = z_q.permute(0, 3, 1, 2).contiguous()
+
+        return z_q

extensions-builtin/Lora/extra_networks_lora.py

@@ -9,19 +9,37 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
     def activate(self, p, params_list):
         additional = shared.opts.sd_lora
 
-        if additional != "None" and additional in lora.available_loras and len([x for x in params_list if x.items[0] == additional]) == 0:
+        if additional != "None" and additional in lora.available_loras and not any(x for x in params_list if x.items[0] == additional):
             p.all_prompts = [x + f"<lora:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
             params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
 
         names = []
         multipliers = []
         for params in params_list:
-            assert len(params.items) > 0
+            assert params.items
 
             names.append(params.items[0])
             multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)
 
         lora.load_loras(names, multipliers)
 
+        if shared.opts.lora_add_hashes_to_infotext:
+            lora_hashes = []
+            for item in lora.loaded_loras:
+                shorthash = item.lora_on_disk.shorthash
+                if not shorthash:
+                    continue
+
+                alias = item.mentioned_name
+                if not alias:
+                    continue
+
+                alias = alias.replace(":", "").replace(",", "")
+
+                lora_hashes.append(f"{alias}: {shorthash}")
+
+            if lora_hashes:
+                p.extra_generation_params["Lora hashes"] = ", ".join(lora_hashes)
+
     def deactivate(self, p):
         pass

extensions-builtin/Lora/lora.py

@@ -1,10 +1,9 @@
-import glob
 import os
 import re
 import torch
 from typing import Union
 
-from modules import shared, devices, sd_models, errors, scripts
+from modules import shared, devices, sd_models, errors, scripts, sd_hijack, hashes
 
 metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
 
@@ -77,9 +76,9 @@ class LoraOnDisk:
         self.name = name
         self.filename = filename
         self.metadata = {}
+        self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
 
-        _, ext = os.path.splitext(filename)
+        if self.is_safetensors:
-        if ext.lower() == ".safetensors":
             try:
                 self.metadata = sd_models.read_metadata_from_safetensors(filename)
             except Exception as e:
@@ -95,14 +94,43 @@ class LoraOnDisk:
         self.ssmd_cover_images = self.metadata.pop('ssmd_cover_images', None)  # those are cover images and they are too big to display in UI as text
         self.alias = self.metadata.get('ss_output_name', self.name)
 
+        self.hash = None
+        self.shorthash = None
+        self.set_hash(
+            self.metadata.get('sshs_model_hash') or
+            hashes.sha256_from_cache(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or
+            ''
+        )
+
+    def set_hash(self, v):
+        self.hash = v
+        self.shorthash = self.hash[0:12]
+
+        if self.shorthash:
+            available_lora_hash_lookup[self.shorthash] = self
+
+    def read_hash(self):
+        if not self.hash:
+            self.set_hash(hashes.sha256(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or '')
+
+    def get_alias(self):
+        if shared.opts.lora_preferred_name == "Filename" or self.alias.lower() in forbidden_lora_aliases:
+            return self.name
+        else:
+            return self.alias
+
 
 class LoraModule:
-    def __init__(self, name):
+    def __init__(self, name, lora_on_disk: LoraOnDisk):
         self.name = name
+        self.lora_on_disk = lora_on_disk
         self.multiplier = 1.0
         self.modules = {}
         self.mtime = None
 
+        self.mentioned_name = None
+        """the text that was used to add lora to prompt - can be either name or an alias"""
+
 
 class LoraUpDownModule:
     def __init__(self):
@@ -127,11 +155,11 @@ def assign_lora_names_to_compvis_modules(sd_model):
     sd_model.lora_layer_mapping = lora_layer_mapping
 
 
-def load_lora(name, filename):
+def load_lora(name, lora_on_disk):
-    lora = LoraModule(name)
+    lora = LoraModule(name, lora_on_disk)
-    lora.mtime = os.path.getmtime(filename)
+    lora.mtime = os.path.getmtime(lora_on_disk.filename)
 
-    sd = sd_models.read_state_dict(filename)
+    sd = sd_models.read_state_dict(lora_on_disk.filename)
 
     # this should not be needed but is here as an emergency fix for an unknown error people are experiencing in 1.2.0
     if not hasattr(shared.sd_model, 'lora_layer_mapping'):
@@ -177,7 +205,7 @@ def load_lora(name, filename):
         else:
             print(f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}')
             continue
-            assert False, f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}'
+            raise AssertionError(f"Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}")
 
         with torch.no_grad():
             module.weight.copy_(weight)
@@ -189,10 +217,10 @@ def load_lora(name, filename):
         elif lora_key == "lora_down.weight":
             lora_module.down = module
         else:
-            assert False, f'Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha'
+            raise AssertionError(f"Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha")
 
-    if len(keys_failed_to_match) > 0:
+    if keys_failed_to_match:
-        print(f"Failed to match keys when loading Lora {filename}: {keys_failed_to_match}")
+        print(f"Failed to match keys when loading Lora {lora_on_disk.filename}: {keys_failed_to_match}")
 
     return lora
 
@@ -207,30 +235,41 @@ def load_loras(names, multipliers=None):
     loaded_loras.clear()
 
     loras_on_disk = [available_lora_aliases.get(name, None) for name in names]
-    if any([x is None for x in loras_on_disk]):
+    if any(x is None for x in loras_on_disk):
         list_available_loras()
 
         loras_on_disk = [available_lora_aliases.get(name, None) for name in names]
 
+    failed_to_load_loras = []
+
     for i, name in enumerate(names):
         lora = already_loaded.get(name, None)
 
         lora_on_disk = loras_on_disk[i]
+
         if lora_on_disk is not None:
             if lora is None or os.path.getmtime(lora_on_disk.filename) > lora.mtime:
                 try:
-                    lora = load_lora(name, lora_on_disk.filename)
+                    lora = load_lora(name, lora_on_disk)
                 except Exception as e:
                     errors.display(e, f"loading Lora {lora_on_disk.filename}")
                     continue
 
+            lora.mentioned_name = name
+
+            lora_on_disk.read_hash()
+
         if lora is None:
+            failed_to_load_loras.append(name)
             print(f"Couldn't find Lora with name {name}")
             continue
 
         lora.multiplier = multipliers[i] if multipliers else 1.0
         loaded_loras.append(lora)
 
+    if failed_to_load_loras:
+        sd_hijack.model_hijack.comments.append("Failed to find Loras: " + ", ".join(failed_to_load_loras))
+
 
 def lora_calc_updown(lora, module, target):
     with torch.no_grad():
@@ -314,7 +353,7 @@ def lora_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.Mu
 
             print(f'failed to calculate lora weights for layer {lora_layer_name}')
 
-        setattr(self, "lora_current_names", wanted_names)
+        self.lora_current_names = wanted_names
 
 
 def lora_forward(module, input, original_forward):
@@ -348,8 +387,8 @@ def lora_forward(module, input, original_forward):
 
 
 def lora_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]):
-    setattr(self, "lora_current_names", ())
+    self.lora_current_names = ()
-    setattr(self, "lora_weights_backup", None)
+    self.lora_weights_backup = None
 
 
 def lora_Linear_forward(self, input):
@@ -398,17 +437,22 @@ def list_available_loras():
     available_loras.clear()
     available_lora_aliases.clear()
     forbidden_lora_aliases.clear()
-    forbidden_lora_aliases.update({"none": 1})
+    available_lora_hash_lookup.clear()
+    forbidden_lora_aliases.update({"none": 1, "Addams": 1})
 
     os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
 
     candidates = list(shared.walk_files(shared.cmd_opts.lora_dir, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
-    for filename in sorted(candidates, key=str.lower):
+    for filename in candidates:
         if os.path.isdir(filename):
             continue
 
         name = os.path.splitext(os.path.basename(filename))[0]
+        try:
             entry = LoraOnDisk(name, filename)
+        except OSError:  # should catch FileNotFoundError and PermissionError etc.
+            errors.report(f"Failed to load LoRA {name} from {filename}", exc_info=True)
+            continue
 
         available_loras[name] = entry
 
@@ -428,7 +472,7 @@ def infotext_pasted(infotext, params):
 
     added = []
 
-    for k, v in params.items():
+    for k in params:
         if not k.startswith("AddNet Model "):
             continue
 
@@ -452,8 +496,10 @@ def infotext_pasted(infotext, params):
     if added:
         params["Prompt"] += "\n" + "".join(added)
 
+
 available_loras = {}
 available_lora_aliases = {}
+available_lora_hash_lookup = {}
 forbidden_lora_aliases = {}
 loaded_loras = []
 

extensions-builtin/Lora/scripts/lora_script.py

@@ -1,3 +1,5 @@
+import re
+
 import torch
 import gradio as gr
 from fastapi import FastAPI
@@ -53,8 +55,9 @@ script_callbacks.on_infotext_pasted(lora.infotext_pasted)
 
 
 shared.options_templates.update(shared.options_section(('extra_networks', "Extra Networks"), {
-    "sd_lora": shared.OptionInfo("None", "Add Lora to prompt", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in lora.available_loras]}, refresh=lora.list_available_loras),
+    "sd_lora": shared.OptionInfo("None", "Add Lora to prompt", gr.Dropdown, lambda: {"choices": ["None", *lora.available_loras]}, refresh=lora.list_available_loras),
-    "lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}),
+    "lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to Lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}),
+    "lora_add_hashes_to_infotext": shared.OptionInfo(True, "Add Lora hashes to infotext"),
 }))
 
 
@@ -77,6 +80,37 @@ def api_loras(_: gr.Blocks, app: FastAPI):
     async def get_loras():
         return [create_lora_json(obj) for obj in lora.available_loras.values()]
 
+    @app.post("/sdapi/v1/refresh-loras")
+    async def refresh_loras():
+        return lora.list_available_loras()
+
 
 script_callbacks.on_app_started(api_loras)
 
+re_lora = re.compile("<lora:([^:]+):")
+
+
+def infotext_pasted(infotext, d):
+    hashes = d.get("Lora hashes")
+    if not hashes:
+        return
+
+    hashes = [x.strip().split(':', 1) for x in hashes.split(",")]
+    hashes = {x[0].strip().replace(",", ""): x[1].strip() for x in hashes}
+
+    def lora_replacement(m):
+        alias = m.group(1)
+        shorthash = hashes.get(alias)
+        if shorthash is None:
+            return m.group(0)
+
+        lora_on_disk = lora.available_lora_hash_lookup.get(shorthash)
+        if lora_on_disk is None:
+            return m.group(0)
+
+        return f'<lora:{lora_on_disk.get_alias()}:'
+
+    d["Prompt"] = re.sub(re_lora, lora_replacement, d["Prompt"])
+
+
+script_callbacks.on_infotext_pasted(infotext_pasted)

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -13,13 +13,10 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         lora.list_available_loras()
 
     def list_items(self):
-        for name, lora_on_disk in lora.available_loras.items():
+        for index, (name, lora_on_disk) in enumerate(lora.available_loras.items()):
             path, ext = os.path.splitext(lora_on_disk.filename)
 
-            if shared.opts.lora_preferred_name == "Filename" or lora_on_disk.alias.lower() in lora.forbidden_lora_aliases:
+            alias = lora_on_disk.get_alias()
-                alias = name
-            else:
-                alias = lora_on_disk.alias
 
             yield {
                 "name": name,
@@ -30,6 +27,8 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
                 "prompt": json.dumps(f"<lora:{alias}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
                 "local_preview": f"{path}.{shared.opts.samples_format}",
                 "metadata": json.dumps(lora_on_disk.metadata, indent=4) if lora_on_disk.metadata else None,
+                "sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
+
             }
 
     def allowed_directories_for_previews(self):

extensions-builtin/ScuNET/scripts/scunet_model.py

@@ -1,19 +1,16 @@
-import os.path
 import sys
-import traceback
 
 import PIL.Image
 import numpy as np
 import torch
 from tqdm import tqdm
 
-from basicsr.utils.download_util import load_file_from_url
-
 import modules.upscaler
-from modules import devices, modelloader
+from modules import devices, modelloader, script_callbacks, errors
-from scunet_model_arch import SCUNet as net
+from scunet_model_arch import SCUNet
+
+from modules.modelloader import load_file_from_url
 from modules.shared import opts
-from modules import images
 
 
 class UpscalerScuNET(modules.upscaler.Upscaler):
@@ -29,7 +26,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         scalers = []
         add_model2 = True
         for file in model_paths:
-            if "http" in file:
+            if file.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(file)
@@ -39,8 +36,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
                 scaler_data = modules.upscaler.UpscalerData(name, file, self, 4)
                 scalers.append(scaler_data)
             except Exception:
-                print(f"Error loading ScuNET model: {file}", file=sys.stderr)
+                errors.report(f"Error loading ScuNET model: {file}", exc_info=True)
-                print(traceback.format_exc(), file=sys.stderr)
         if add_model2:
             scaler_data2 = modules.upscaler.UpscalerData(self.model_name2, self.model_url2, self)
             scalers.append(scaler_data2)
@@ -91,9 +87,10 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
 
         torch.cuda.empty_cache()
 
+        try:
             model = self.load_model(selected_file)
-        if model is None:
+        except Exception as e:
-            print(f"ScuNET: Unable to load model from {selected_file}", file=sys.stderr)
+            print(f"ScuNET: Unable to load model from {selected_file}: {e}", file=sys.stderr)
             return img
 
         device = devices.get_device_for('scunet')
@@ -121,20 +118,27 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
 
     def load_model(self, path: str):
         device = devices.get_device_for('scunet')
-        if "http" in path:
+        if path.startswith("http"):
-            filename = load_file_from_url(url=self.model_url, model_dir=self.model_path, file_name="%s.pth" % self.name,
+            # TODO: this doesn't use `path` at all?
-                                          progress=True)
+            filename = load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name=f"{self.name}.pth")
         else:
             filename = path
-        if not os.path.exists(os.path.join(self.model_path, filename)) or filename is None:
+        model = SCUNet(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
-            print(f"ScuNET: Unable to load model from {filename}", file=sys.stderr)
-            return None
-
-        model = net(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
         model.load_state_dict(torch.load(filename), strict=True)
         model.eval()
-        for k, v in model.named_parameters():
+        for _, v in model.named_parameters():
             v.requires_grad = False
         model = model.to(device)
 
         return model
+
+
+def on_ui_settings():
+    import gradio as gr
+    from modules import shared
+
+    shared.opts.add_option("SCUNET_tile", shared.OptionInfo(256, "Tile size for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")).info("0 = no tiling"))
+    shared.opts.add_option("SCUNET_tile_overlap", shared.OptionInfo(8, "Tile overlap for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, section=('upscaling', "Upscaling")).info("Low values = visible seam"))
+
+
+script_callbacks.on_ui_settings(on_ui_settings)

extensions-builtin/ScuNET/scunet_model_arch.py

@@ -61,7 +61,9 @@ class WMSA(nn.Module):
         Returns:
             output: tensor shape [b h w c]
         """
-        if self.type != 'W': x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2))
+        if self.type != 'W':
+            x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2))
+
         x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size)
         h_windows = x.size(1)
         w_windows = x.size(2)
@@ -85,8 +87,9 @@ class WMSA(nn.Module):
         output = self.linear(output)
         output = rearrange(output, 'b (w1 w2) (p1 p2) c -> b (w1 p1) (w2 p2) c', w1=h_windows, p1=self.window_size)
 
-        if self.type != 'W': output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2),
+        if self.type != 'W':
-                                                 dims=(1, 2))
+            output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), dims=(1, 2))
+
         return output
 
     def relative_embedding(self):

extensions-builtin/SwinIR/scripts/swinir_model.py

@@ -1,18 +1,17 @@
-import contextlib
+import sys
-import os
 
 import numpy as np
 import torch
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 from tqdm import tqdm
 
 from modules import modelloader, devices, script_callbacks, shared
-from modules.shared import cmd_opts, opts, state
+from modules.shared import opts, state
-from swinir_model_arch import SwinIR as net
+from swinir_model_arch import SwinIR
-from swinir_model_arch_v2 import Swin2SR as net2
+from swinir_model_arch_v2 import Swin2SR
 from modules.upscaler import Upscaler, UpscalerData
 
+SWINIR_MODEL_URL = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth"
 
 device_swinir = devices.get_device_for('swinir')
 
@@ -20,16 +19,14 @@ device_swinir = devices.get_device_for('swinir')
 class UpscalerSwinIR(Upscaler):
     def __init__(self, dirname):
         self.name = "SwinIR"
-        self.model_url = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0" \
+        self.model_url = SWINIR_MODEL_URL
-                         "/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR" \
-                         "-L_x4_GAN.pth "
         self.model_name = "SwinIR 4x"
         self.user_path = dirname
         super().__init__()
         scalers = []
         model_files = self.find_models(ext_filter=[".pt", ".pth"])
         for model in model_files:
-            if "http" in model:
+            if model.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(model)
@@ -38,27 +35,30 @@ class UpscalerSwinIR(Upscaler):
         self.scalers = scalers
 
     def do_upscale(self, img, model_file):
+        try:
             model = self.load_model(model_file)
-        if model is None:
+        except Exception as e:
+            print(f"Failed loading SwinIR model {model_file}: {e}", file=sys.stderr)
             return img
         model = model.to(device_swinir, dtype=devices.dtype)
         img = upscale(img, model)
         try:
             torch.cuda.empty_cache()
-        except:
+        except Exception:
             pass
         return img
 
     def load_model(self, path, scale=4):
-        if "http" in path:
+        if path.startswith("http"):
-            dl_name = "%s%s" % (self.model_name.replace(" ", "_"), ".pth")
+            filename = modelloader.load_file_from_url(
-            filename = load_file_from_url(url=path, model_dir=self.model_path, file_name=dl_name, progress=True)
+                url=path,
+                model_dir=self.model_download_path,
+                file_name=f"{self.model_name.replace(' ', '_')}.pth",
+            )
         else:
             filename = path
-        if filename is None or not os.path.exists(filename):
-            return None
         if filename.endswith(".v2.pth"):
-            model = net2(
+            model = Swin2SR(
                 upscale=scale,
                 in_chans=3,
                 img_size=64,
@@ -73,7 +73,7 @@ class UpscalerSwinIR(Upscaler):
             )
             params = None
         else:
-            model = net(
+            model = SwinIR(
                 upscale=scale,
                 in_chans=3,
                 img_size=64,

extensions-builtin/SwinIR/swinir_model_arch.py

@@ -644,7 +644,7 @@ class SwinIR(nn.Module):
     """
 
     def __init__(self, img_size=64, patch_size=1, in_chans=3,
-                 embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6],
+                 embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6),
                  window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None,
                  drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
                  norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
@@ -844,7 +844,7 @@ class SwinIR(nn.Module):
         H, W = self.patches_resolution
         flops += H * W * 3 * self.embed_dim * 9
         flops += self.patch_embed.flops()
-        for i, layer in enumerate(self.layers):
+        for layer in self.layers:
             flops += layer.flops()
         flops += H * W * 3 * self.embed_dim * self.embed_dim
         flops += self.upsample.flops()

extensions-builtin/SwinIR/swinir_model_arch_v2.py

@@ -74,7 +74,7 @@ class WindowAttention(nn.Module):
     """
 
     def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.,
-                 pretrained_window_size=[0, 0]):
+                 pretrained_window_size=(0, 0)):
 
         super().__init__()
         self.dim = dim
@@ -698,7 +698,7 @@ class Swin2SR(nn.Module):
     """
 
     def __init__(self, img_size=64, patch_size=1, in_chans=3,
-                 embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6],
+                 embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6),
                  window_size=7, mlp_ratio=4., qkv_bias=True,
                  drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
                  norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
@@ -994,7 +994,7 @@ class Swin2SR(nn.Module):
         H, W = self.patches_resolution
         flops += H * W * 3 * self.embed_dim * 9
         flops += self.patch_embed.flops()
-        for i, layer in enumerate(self.layers):
+        for layer in self.layers:
             flops += layer.flops()
         flops += H * W * 3 * self.embed_dim * self.embed_dim
         flops += self.upsample.flops()

extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js

@@ -0,0 +1,776 @@
+onUiLoaded(async() => {
+    const elementIDs = {
+        img2imgTabs: "#mode_img2img .tab-nav",
+        inpaint: "#img2maskimg",
+        inpaintSketch: "#inpaint_sketch",
+        rangeGroup: "#img2img_column_size",
+        sketch: "#img2img_sketch"
+    };
+    const tabNameToElementId = {
+        "Inpaint sketch": elementIDs.inpaintSketch,
+        "Inpaint": elementIDs.inpaint,
+        "Sketch": elementIDs.sketch
+    };
+
+    // Helper functions
+    // Get active tab
+    function getActiveTab(elements, all = false) {
+        const tabs = elements.img2imgTabs.querySelectorAll("button");
+
+        if (all) return tabs;
+
+        for (let tab of tabs) {
+            if (tab.classList.contains("selected")) {
+                return tab;
+            }
+        }
+    }
+
+    // Get tab ID
+    function getTabId(elements) {
+        const activeTab = getActiveTab(elements);
+        return tabNameToElementId[activeTab.innerText];
+    }
+
+    // Wait until opts loaded
+    async function waitForOpts() {
+        for (;;) {
+            if (window.opts && Object.keys(window.opts).length) {
+                return window.opts;
+            }
+            await new Promise(resolve => setTimeout(resolve, 100));
+        }
+    }
+
+    // Function for defining the "Ctrl", "Shift" and "Alt" keys
+    function isModifierKey(event, key) {
+        switch (key) {
+        case "Ctrl":
+            return event.ctrlKey;
+        case "Shift":
+            return event.shiftKey;
+        case "Alt":
+            return event.altKey;
+        default:
+            return false;
+        }
+    }
+
+    // Check if hotkey is valid
+    function isValidHotkey(value) {
+        const specialKeys = ["Ctrl", "Alt", "Shift", "Disable"];
+        return (
+            (typeof value === "string" &&
+                value.length === 1 &&
+                /[a-z]/i.test(value)) ||
+            specialKeys.includes(value)
+        );
+    }
+
+    // Normalize hotkey
+    function normalizeHotkey(hotkey) {
+        return hotkey.length === 1 ? "Key" + hotkey.toUpperCase() : hotkey;
+    }
+
+    // Format hotkey for display
+    function formatHotkeyForDisplay(hotkey) {
+        return hotkey.startsWith("Key") ? hotkey.slice(3) : hotkey;
+    }
+
+    // Create hotkey configuration with the provided options
+    function createHotkeyConfig(defaultHotkeysConfig, hotkeysConfigOpts) {
+        const result = {}; // Resulting hotkey configuration
+        const usedKeys = new Set(); // Set of used hotkeys
+
+        // Iterate through defaultHotkeysConfig keys
+        for (const key in defaultHotkeysConfig) {
+            const userValue = hotkeysConfigOpts[key]; // User-provided hotkey value
+            const defaultValue = defaultHotkeysConfig[key]; // Default hotkey value
+
+            // Apply appropriate value for undefined, boolean, or object userValue
+            if (
+                userValue === undefined ||
+                typeof userValue === "boolean" ||
+                typeof userValue === "object" ||
+                userValue === "disable"
+            ) {
+                result[key] =
+                    userValue === undefined ? defaultValue : userValue;
+            } else if (isValidHotkey(userValue)) {
+                const normalizedUserValue = normalizeHotkey(userValue);
+
+                // Check for conflicting hotkeys
+                if (!usedKeys.has(normalizedUserValue)) {
+                    usedKeys.add(normalizedUserValue);
+                    result[key] = normalizedUserValue;
+                } else {
+                    console.error(
+                        `Hotkey: ${formatHotkeyForDisplay(
+                            userValue
+                        )} for ${key} is repeated and conflicts with another hotkey. The default hotkey is used: ${formatHotkeyForDisplay(
+                            defaultValue
+                        )}`
+                    );
+                    result[key] = defaultValue;
+                }
+            } else {
+                console.error(
+                    `Hotkey: ${formatHotkeyForDisplay(
+                        userValue
+                    )} for ${key} is not valid. The default hotkey is used: ${formatHotkeyForDisplay(
+                        defaultValue
+                    )}`
+                );
+                result[key] = defaultValue;
+            }
+        }
+
+        return result;
+    }
+
+    // Disables functions in the config object based on the provided list of function names
+    function disableFunctions(config, disabledFunctions) {
+        // Bind the hasOwnProperty method to the functionMap object to avoid errors
+        const hasOwnProperty =
+            Object.prototype.hasOwnProperty.bind(functionMap);
+
+        // Loop through the disabledFunctions array and disable the corresponding functions in the config object
+        disabledFunctions.forEach(funcName => {
+            if (hasOwnProperty(funcName)) {
+                const key = functionMap[funcName];
+                config[key] = "disable";
+            }
+        });
+
+        // Return the updated config object
+        return config;
+    }
+
+    /**
+     * The restoreImgRedMask function displays a red mask around an image to indicate the aspect ratio.
+     * If the image display property is set to 'none', the mask breaks. To fix this, the function
+     * temporarily sets the display property to 'block' and then hides the mask again after 300 milliseconds
+     * to avoid breaking the canvas. Additionally, the function adjusts the mask to work correctly on
+     * very long images.
+     */
+    function restoreImgRedMask(elements) {
+        const mainTabId = getTabId(elements);
+
+        if (!mainTabId) return;
+
+        const mainTab = gradioApp().querySelector(mainTabId);
+        const img = mainTab.querySelector("img");
+        const imageARPreview = gradioApp().querySelector("#imageARPreview");
+
+        if (!img || !imageARPreview) return;
+
+        imageARPreview.style.transform = "";
+        if (parseFloat(mainTab.style.width) > 865) {
+            const transformString = mainTab.style.transform;
+            const scaleMatch = transformString.match(
+                /scale\(([-+]?[0-9]*\.?[0-9]+)\)/
+            );
+            let zoom = 1; // default zoom
+
+            if (scaleMatch && scaleMatch[1]) {
+                zoom = Number(scaleMatch[1]);
+            }
+
+            imageARPreview.style.transformOrigin = "0 0";
+            imageARPreview.style.transform = `scale(${zoom})`;
+        }
+
+        if (img.style.display !== "none") return;
+
+        img.style.display = "block";
+
+        setTimeout(() => {
+            img.style.display = "none";
+        }, 400);
+    }
+
+    const hotkeysConfigOpts = await waitForOpts();
+
+    // Default config
+    const defaultHotkeysConfig = {
+        canvas_hotkey_zoom: "Alt",
+        canvas_hotkey_adjust: "Ctrl",
+        canvas_hotkey_reset: "KeyR",
+        canvas_hotkey_fullscreen: "KeyS",
+        canvas_hotkey_move: "KeyF",
+        canvas_hotkey_overlap: "KeyO",
+        canvas_disabled_functions: [],
+        canvas_show_tooltip: true,
+        canvas_blur_prompt: false
+    };
+
+    const functionMap = {
+        "Zoom": "canvas_hotkey_zoom",
+        "Adjust brush size": "canvas_hotkey_adjust",
+        "Moving canvas": "canvas_hotkey_move",
+        "Fullscreen": "canvas_hotkey_fullscreen",
+        "Reset Zoom": "canvas_hotkey_reset",
+        "Overlap": "canvas_hotkey_overlap"
+    };
+
+    // Loading the configuration from opts
+    const preHotkeysConfig = createHotkeyConfig(
+        defaultHotkeysConfig,
+        hotkeysConfigOpts
+    );
+
+    // Disable functions that are not needed by the user
+    const hotkeysConfig = disableFunctions(
+        preHotkeysConfig,
+        preHotkeysConfig.canvas_disabled_functions
+    );
+
+    let isMoving = false;
+    let mouseX, mouseY;
+    let activeElement;
+
+    const elements = Object.fromEntries(
+        Object.keys(elementIDs).map(id => [
+            id,
+            gradioApp().querySelector(elementIDs[id])
+        ])
+    );
+    const elemData = {};
+
+    // Apply functionality to the range inputs. Restore redmask and correct for long images.
+    const rangeInputs = elements.rangeGroup ?
+        Array.from(elements.rangeGroup.querySelectorAll("input")) :
+        [
+            gradioApp().querySelector("#img2img_width input[type='range']"),
+            gradioApp().querySelector("#img2img_height input[type='range']")
+        ];
+
+    for (const input of rangeInputs) {
+        input?.addEventListener("input", () => restoreImgRedMask(elements));
+    }
+
+    function applyZoomAndPan(elemId) {
+        const targetElement = gradioApp().querySelector(elemId);
+
+        if (!targetElement) {
+            console.log("Element not found");
+            return;
+        }
+
+        targetElement.style.transformOrigin = "0 0";
+
+        elemData[elemId] = {
+            zoom: 1,
+            panX: 0,
+            panY: 0
+        };
+        let fullScreenMode = false;
+
+        // Create tooltip
+        function createTooltip() {
+            const toolTipElemnt =
+                targetElement.querySelector(".image-container");
+            const tooltip = document.createElement("div");
+            tooltip.className = "canvas-tooltip";
+
+            // Creating an item of information
+            const info = document.createElement("i");
+            info.className = "canvas-tooltip-info";
+            info.textContent = "";
+
+            // Create a container for the contents of the tooltip
+            const tooltipContent = document.createElement("div");
+            tooltipContent.className = "canvas-tooltip-content";
+
+            // Define an array with hotkey information and their actions
+            const hotkeysInfo = [
+                {
+                    configKey: "canvas_hotkey_zoom",
+                    action: "Zoom canvas",
+                    keySuffix: " + wheel"
+                },
+                {
+                    configKey: "canvas_hotkey_adjust",
+                    action: "Adjust brush size",
+                    keySuffix: " + wheel"
+                },
+                {configKey: "canvas_hotkey_reset", action: "Reset zoom"},
+                {
+                    configKey: "canvas_hotkey_fullscreen",
+                    action: "Fullscreen mode"
+                },
+                {configKey: "canvas_hotkey_move", action: "Move canvas"},
+                {configKey: "canvas_hotkey_overlap", action: "Overlap"}
+            ];
+
+            // Create hotkeys array with disabled property based on the config values
+            const hotkeys = hotkeysInfo.map(info => {
+                const configValue = hotkeysConfig[info.configKey];
+                const key = info.keySuffix ?
+                    `${configValue}${info.keySuffix}` :
+                    configValue.charAt(configValue.length - 1);
+                return {
+                    key,
+                    action: info.action,
+                    disabled: configValue === "disable"
+                };
+            });
+
+            for (const hotkey of hotkeys) {
+                if (hotkey.disabled) {
+                    continue;
+                }
+
+                const p = document.createElement("p");
+                p.innerHTML = `<b>${hotkey.key}</b> - ${hotkey.action}`;
+                tooltipContent.appendChild(p);
+            }
+
+            // Add information and content elements to the tooltip element
+            tooltip.appendChild(info);
+            tooltip.appendChild(tooltipContent);
+
+            // Add a hint element to the target element
+            toolTipElemnt.appendChild(tooltip);
+        }
+
+        //Show tool tip if setting enable
+        if (hotkeysConfig.canvas_show_tooltip) {
+            createTooltip();
+        }
+
+        // In the course of research, it was found that the tag img is very harmful when zooming and creates white canvases. This hack allows you to almost never think about this problem, it has no effect on webui.
+        function fixCanvas() {
+            const activeTab = getActiveTab(elements).textContent.trim();
+
+            if (activeTab !== "img2img") {
+                const img = targetElement.querySelector(`${elemId} img`);
+
+                if (img && img.style.display !== "none") {
+                    img.style.display = "none";
+                    img.style.visibility = "hidden";
+                }
+            }
+        }
+
+        // Reset the zoom level and pan position of the target element to their initial values
+        function resetZoom() {
+            elemData[elemId] = {
+                zoomLevel: 1,
+                panX: 0,
+                panY: 0
+            };
+
+            fixCanvas();
+            targetElement.style.transform = `scale(${elemData[elemId].zoomLevel}) translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px)`;
+
+            const canvas = gradioApp().querySelector(
+                `${elemId} canvas[key="interface"]`
+            );
+
+            toggleOverlap("off");
+            fullScreenMode = false;
+
+            if (
+                canvas &&
+                parseFloat(canvas.style.width) > 865 &&
+                parseFloat(targetElement.style.width) > 865
+            ) {
+                fitToElement();
+                return;
+            }
+
+            targetElement.style.width = "";
+            if (canvas) {
+                targetElement.style.height = canvas.style.height;
+            }
+        }
+
+        // Toggle the zIndex of the target element between two values, allowing it to overlap or be overlapped by other elements
+        function toggleOverlap(forced = "") {
+            const zIndex1 = "0";
+            const zIndex2 = "998";
+
+            targetElement.style.zIndex =
+                targetElement.style.zIndex !== zIndex2 ? zIndex2 : zIndex1;
+
+            if (forced === "off") {
+                targetElement.style.zIndex = zIndex1;
+            } else if (forced === "on") {
+                targetElement.style.zIndex = zIndex2;
+            }
+        }
+
+        // Adjust the brush size based on the deltaY value from a mouse wheel event
+        function adjustBrushSize(
+            elemId,
+            deltaY,
+            withoutValue = false,
+            percentage = 5
+        ) {
+            const input =
+                gradioApp().querySelector(
+                    `${elemId} input[aria-label='Brush radius']`
+                ) ||
+                gradioApp().querySelector(
+                    `${elemId} button[aria-label="Use brush"]`
+                );
+
+            if (input) {
+                input.click();
+                if (!withoutValue) {
+                    const maxValue =
+                        parseFloat(input.getAttribute("max")) || 100;
+                    const changeAmount = maxValue * (percentage / 100);
+                    const newValue =
+                        parseFloat(input.value) +
+                        (deltaY > 0 ? -changeAmount : changeAmount);
+                    input.value = Math.min(Math.max(newValue, 0), maxValue);
+                    input.dispatchEvent(new Event("change"));
+                }
+            }
+        }
+
+        // Reset zoom when uploading a new image
+        const fileInput = gradioApp().querySelector(
+            `${elemId} input[type="file"][accept="image/*"].svelte-116rqfv`
+        );
+        fileInput.addEventListener("click", resetZoom);
+
+        // Update the zoom level and pan position of the target element based on the values of the zoomLevel, panX and panY variables
+        function updateZoom(newZoomLevel, mouseX, mouseY) {
+            newZoomLevel = Math.max(0.5, Math.min(newZoomLevel, 15));
+
+            elemData[elemId].panX +=
+                mouseX - (mouseX * newZoomLevel) / elemData[elemId].zoomLevel;
+            elemData[elemId].panY +=
+                mouseY - (mouseY * newZoomLevel) / elemData[elemId].zoomLevel;
+
+            targetElement.style.transformOrigin = "0 0";
+            targetElement.style.transform = `translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px) scale(${newZoomLevel})`;
+
+            toggleOverlap("on");
+            return newZoomLevel;
+        }
+
+        // Change the zoom level based on user interaction
+        function changeZoomLevel(operation, e) {
+            if (isModifierKey(e, hotkeysConfig.canvas_hotkey_zoom)) {
+                e.preventDefault();
+
+                let zoomPosX, zoomPosY;
+                let delta = 0.2;
+                if (elemData[elemId].zoomLevel > 7) {
+                    delta = 0.9;
+                } else if (elemData[elemId].zoomLevel > 2) {
+                    delta = 0.6;
+                }
+
+                zoomPosX = e.clientX;
+                zoomPosY = e.clientY;
+
+                fullScreenMode = false;
+                elemData[elemId].zoomLevel = updateZoom(
+                    elemData[elemId].zoomLevel +
+                        (operation === "+" ? delta : -delta),
+                    zoomPosX - targetElement.getBoundingClientRect().left,
+                    zoomPosY - targetElement.getBoundingClientRect().top
+                );
+            }
+        }
+
+        /**
+         * This function fits the target element to the screen by calculating
+         * the required scale and offsets. It also updates the global variables
+         * zoomLevel, panX, and panY to reflect the new state.
+         */
+
+        function fitToElement() {
+            //Reset Zoom
+            targetElement.style.transform = `translate(${0}px, ${0}px) scale(${1})`;
+
+            // Get element and screen dimensions
+            const elementWidth = targetElement.offsetWidth;
+            const elementHeight = targetElement.offsetHeight;
+            const parentElement = targetElement.parentElement;
+            const screenWidth = parentElement.clientWidth;
+            const screenHeight = parentElement.clientHeight;
+
+            // Get element's coordinates relative to the parent element
+            const elementRect = targetElement.getBoundingClientRect();
+            const parentRect = parentElement.getBoundingClientRect();
+            const elementX = elementRect.x - parentRect.x;
+
+            // Calculate scale and offsets
+            const scaleX = screenWidth / elementWidth;
+            const scaleY = screenHeight / elementHeight;
+            const scale = Math.min(scaleX, scaleY);
+
+            const transformOrigin =
+                window.getComputedStyle(targetElement).transformOrigin;
+            const [originX, originY] = transformOrigin.split(" ");
+            const originXValue = parseFloat(originX);
+            const originYValue = parseFloat(originY);
+
+            const offsetX =
+                (screenWidth - elementWidth * scale) / 2 -
+                originXValue * (1 - scale);
+            const offsetY =
+                (screenHeight - elementHeight * scale) / 2.5 -
+                originYValue * (1 - scale);
+
+            // Apply scale and offsets to the element
+            targetElement.style.transform = `translate(${offsetX}px, ${offsetY}px) scale(${scale})`;
+
+            // Update global variables
+            elemData[elemId].zoomLevel = scale;
+            elemData[elemId].panX = offsetX;
+            elemData[elemId].panY = offsetY;
+
+            fullScreenMode = false;
+            toggleOverlap("off");
+        }
+
+        /**
+         * This function fits the target element to the screen by calculating
+         * the required scale and offsets. It also updates the global variables
+         * zoomLevel, panX, and panY to reflect the new state.
+         */
+
+        // Fullscreen mode
+        function fitToScreen() {
+            const canvas = gradioApp().querySelector(
+                `${elemId} canvas[key="interface"]`
+            );
+
+            if (!canvas) return;
+
+            if (canvas.offsetWidth > 862) {
+                targetElement.style.width = canvas.offsetWidth + "px";
+            }
+
+            if (fullScreenMode) {
+                resetZoom();
+                fullScreenMode = false;
+                return;
+            }
+
+            //Reset Zoom
+            targetElement.style.transform = `translate(${0}px, ${0}px) scale(${1})`;
+
+            // Get scrollbar width to right-align the image
+            const scrollbarWidth =
+                window.innerWidth - document.documentElement.clientWidth;
+
+            // Get element and screen dimensions
+            const elementWidth = targetElement.offsetWidth;
+            const elementHeight = targetElement.offsetHeight;
+            const screenWidth = window.innerWidth - scrollbarWidth;
+            const screenHeight = window.innerHeight;
+
+            // Get element's coordinates relative to the page
+            const elementRect = targetElement.getBoundingClientRect();
+            const elementY = elementRect.y;
+            const elementX = elementRect.x;
+
+            // Calculate scale and offsets
+            const scaleX = screenWidth / elementWidth;
+            const scaleY = screenHeight / elementHeight;
+            const scale = Math.min(scaleX, scaleY);
+
+            // Get the current transformOrigin
+            const computedStyle = window.getComputedStyle(targetElement);
+            const transformOrigin = computedStyle.transformOrigin;
+            const [originX, originY] = transformOrigin.split(" ");
+            const originXValue = parseFloat(originX);
+            const originYValue = parseFloat(originY);
+
+            // Calculate offsets with respect to the transformOrigin
+            const offsetX =
+                (screenWidth - elementWidth * scale) / 2 -
+                elementX -
+                originXValue * (1 - scale);
+            const offsetY =
+                (screenHeight - elementHeight * scale) / 2 -
+                elementY -
+                originYValue * (1 - scale);
+
+            // Apply scale and offsets to the element
+            targetElement.style.transform = `translate(${offsetX}px, ${offsetY}px) scale(${scale})`;
+
+            // Update global variables
+            elemData[elemId].zoomLevel = scale;
+            elemData[elemId].panX = offsetX;
+            elemData[elemId].panY = offsetY;
+
+            fullScreenMode = true;
+            toggleOverlap("on");
+        }
+
+        // Handle keydown events
+        function handleKeyDown(event) {
+            // Disable key locks to make pasting from the buffer work correctly
+            if ((event.ctrlKey && event.code === 'KeyV') || (event.ctrlKey && event.code === 'KeyC') || event.code === "F5") {
+                return;
+            }
+
+            // before activating shortcut, ensure user is not actively typing in an input field
+            if (!hotkeysConfig.canvas_blur_prompt) {
+                if (event.target.nodeName === 'TEXTAREA' || event.target.nodeName === 'INPUT') {
+                    return;
+                }
+            }
+
+
+            const hotkeyActions = {
+                [hotkeysConfig.canvas_hotkey_reset]: resetZoom,
+                [hotkeysConfig.canvas_hotkey_overlap]: toggleOverlap,
+                [hotkeysConfig.canvas_hotkey_fullscreen]: fitToScreen
+            };
+
+            const action = hotkeyActions[event.code];
+            if (action) {
+                event.preventDefault();
+                action(event);
+            }
+
+            if (
+                isModifierKey(event, hotkeysConfig.canvas_hotkey_zoom) ||
+                isModifierKey(event, hotkeysConfig.canvas_hotkey_adjust)
+            ) {
+                event.preventDefault();
+            }
+        }
+
+        // Get Mouse position
+        function getMousePosition(e) {
+            mouseX = e.offsetX;
+            mouseY = e.offsetY;
+        }
+
+        targetElement.addEventListener("mousemove", getMousePosition);
+
+        // Handle events only inside the targetElement
+        let isKeyDownHandlerAttached = false;
+
+        function handleMouseMove() {
+            if (!isKeyDownHandlerAttached) {
+                document.addEventListener("keydown", handleKeyDown);
+                isKeyDownHandlerAttached = true;
+
+                activeElement = elemId;
+            }
+        }
+
+        function handleMouseLeave() {
+            if (isKeyDownHandlerAttached) {
+                document.removeEventListener("keydown", handleKeyDown);
+                isKeyDownHandlerAttached = false;
+
+                activeElement = null;
+            }
+        }
+
+        // Add mouse event handlers
+        targetElement.addEventListener("mousemove", handleMouseMove);
+        targetElement.addEventListener("mouseleave", handleMouseLeave);
+
+        // Reset zoom when click on another tab
+        elements.img2imgTabs.addEventListener("click", resetZoom);
+        elements.img2imgTabs.addEventListener("click", () => {
+            // targetElement.style.width = "";
+            if (parseInt(targetElement.style.width) > 865) {
+                setTimeout(fitToElement, 0);
+            }
+        });
+
+        targetElement.addEventListener("wheel", e => {
+            // change zoom level
+            const operation = e.deltaY > 0 ? "-" : "+";
+            changeZoomLevel(operation, e);
+
+            // Handle brush size adjustment with ctrl key pressed
+            if (isModifierKey(e, hotkeysConfig.canvas_hotkey_adjust)) {
+                e.preventDefault();
+
+                // Increase or decrease brush size based on scroll direction
+                adjustBrushSize(elemId, e.deltaY);
+            }
+        });
+
+        // Handle the move event for pan functionality. Updates the panX and panY variables and applies the new transform to the target element.
+        function handleMoveKeyDown(e) {
+
+            // Disable key locks to make pasting from the buffer work correctly
+            if ((e.ctrlKey && e.code === 'KeyV') || (e.ctrlKey && event.code === 'KeyC') || e.code === "F5") {
+                return;
+            }
+
+            // before activating shortcut, ensure user is not actively typing in an input field
+            if (!hotkeysConfig.canvas_blur_prompt) {
+                if (e.target.nodeName === 'TEXTAREA' || e.target.nodeName === 'INPUT') {
+                    return;
+                }
+            }
+
+
+            if (e.code === hotkeysConfig.canvas_hotkey_move) {
+                if (!e.ctrlKey && !e.metaKey && isKeyDownHandlerAttached) {
+                    e.preventDefault();
+                    document.activeElement.blur();
+                    isMoving = true;
+                }
+            }
+        }
+
+        function handleMoveKeyUp(e) {
+            if (e.code === hotkeysConfig.canvas_hotkey_move) {
+                isMoving = false;
+            }
+        }
+
+        document.addEventListener("keydown", handleMoveKeyDown);
+        document.addEventListener("keyup", handleMoveKeyUp);
+
+        // Detect zoom level and update the pan speed.
+        function updatePanPosition(movementX, movementY) {
+            let panSpeed = 2;
+
+            if (elemData[elemId].zoomLevel > 8) {
+                panSpeed = 3.5;
+            }
+
+            elemData[elemId].panX += movementX * panSpeed;
+            elemData[elemId].panY += movementY * panSpeed;
+
+            // Delayed redraw of an element
+            requestAnimationFrame(() => {
+                targetElement.style.transform = `translate(${elemData[elemId].panX}px, ${elemData[elemId].panY}px) scale(${elemData[elemId].zoomLevel})`;
+                toggleOverlap("on");
+            });
+        }
+
+        function handleMoveByKey(e) {
+            if (isMoving && elemId === activeElement) {
+                updatePanPosition(e.movementX, e.movementY);
+                targetElement.style.pointerEvents = "none";
+            } else {
+                targetElement.style.pointerEvents = "auto";
+            }
+        }
+
+        // Prevents sticking to the mouse
+        window.onblur = function() {
+            isMoving = false;
+        };
+
+        gradioApp().addEventListener("mousemove", handleMoveByKey);
+    }
+
+    applyZoomAndPan(elementIDs.sketch);
+    applyZoomAndPan(elementIDs.inpaint);
+    applyZoomAndPan(elementIDs.inpaintSketch);
+
+    // Make the function global so that other extensions can take advantage of this solution
+    window.applyZoomAndPan = applyZoomAndPan;
+});

extensions-builtin/canvas-zoom-and-pan/scripts/hotkey_config.py

@@ -0,0 +1,14 @@
+import gradio as gr
+from modules import shared
+
+shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas Hotkeys"), {
+    "canvas_hotkey_zoom": shared.OptionInfo("Alt", "Zoom canvas", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
+    "canvas_hotkey_adjust": shared.OptionInfo("Ctrl", "Adjust brush size", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
+    "canvas_hotkey_move": shared.OptionInfo("F", "Moving the canvas").info("To work correctly in firefox, turn off 'Automatically search the page text when typing' in the browser settings"),
+    "canvas_hotkey_fullscreen": shared.OptionInfo("S", "Fullscreen Mode, maximizes the picture so that it fits into the screen and stretches it to its full width "),
+    "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas positon"),
+    "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, neededs for testing"),
+    "canvas_show_tooltip": shared.OptionInfo(True, "Enable tooltip on the canvas"),
+    "canvas_blur_prompt": shared.OptionInfo(False, "Take the focus off the prompt when working with a canvas"),
+    "canvas_disabled_functions": shared.OptionInfo(["Overlap"], "Disable function that you don't use", gr.CheckboxGroup, {"choices": ["Zoom","Adjust brush size", "Moving canvas","Fullscreen","Reset Zoom","Overlap"]}),
+}))

extensions-builtin/canvas-zoom-and-pan/style.css

@@ -0,0 +1,63 @@
+.canvas-tooltip-info {
+  position: absolute;
+  top: 10px;
+  left: 10px;
+  cursor: help;
+  background-color: rgba(0, 0, 0, 0.3);
+  width: 20px;
+  height: 20px;
+  border-radius: 50%;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  flex-direction: column; 
+
+  z-index: 100;
+}
+
+.canvas-tooltip-info::after {
+  content: '';
+  display: block;
+  width: 2px;
+  height: 7px;
+  background-color: white;
+  margin-top: 2px; 
+}
+
+.canvas-tooltip-info::before {
+  content: '';
+  display: block;
+  width: 2px;
+  height: 2px;
+  background-color: white;
+}
+
+.canvas-tooltip-content {
+  display: none;
+  background-color: #f9f9f9; 
+  color: #333; 
+  border: 1px solid #ddd;
+  padding: 15px; 
+  position: absolute;
+  top: 40px;
+  left: 10px;
+  width: 250px;
+  font-size: 16px;
+  opacity: 0;
+  border-radius: 8px;
+  box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2); 
+
+  z-index: 100;
+}
+
+.canvas-tooltip:hover .canvas-tooltip-content {
+  display: block;
+  animation: fadeIn 0.5s; 
+  opacity: 1;
+}
+
+@keyframes fadeIn {
+  from {opacity: 0;}
+  to {opacity: 1;}
+}
+

extensions-builtin/extra-options-section/scripts/extra_options_section.py

@@ -0,0 +1,48 @@
+import gradio as gr
+from modules import scripts, shared, ui_components, ui_settings
+from modules.ui_components import FormColumn
+
+
+class ExtraOptionsSection(scripts.Script):
+    section = "extra_options"
+
+    def __init__(self):
+        self.comps = None
+        self.setting_names = None
+
+    def title(self):
+        return "Extra options"
+
+    def show(self, is_img2img):
+        return scripts.AlwaysVisible
+
+    def ui(self, is_img2img):
+        self.comps = []
+        self.setting_names = []
+
+        with gr.Blocks() as interface:
+            with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and shared.opts.extra_options else gr.Group(), gr.Row():
+                for setting_name in shared.opts.extra_options:
+                    with FormColumn():
+                        comp = ui_settings.create_setting_component(setting_name)
+
+                    self.comps.append(comp)
+                    self.setting_names.append(setting_name)
+
+        def get_settings_values():
+            return [ui_settings.get_value_for_setting(key) for key in self.setting_names]
+
+        interface.load(fn=get_settings_values, inputs=[], outputs=self.comps, queue=False, show_progress=False)
+
+        return self.comps
+
+    def before_process(self, p, *args):
+        for name, value in zip(self.setting_names, args):
+            if name not in p.override_settings:
+                p.override_settings[name] = value
+
+
+shared.options_templates.update(shared.options_section(('ui', "User interface"), {
+    "extra_options": shared.OptionInfo([], "Options in main UI", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img/img2img interfaces").needs_restart(),
+    "extra_options_accordion": shared.OptionInfo(False, "Place options in main UI into an accordion")
+}))

extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js

@@ -5,7 +5,7 @@
 
 function checkBrackets(textArea, counterElt) {
     var counts = {};
-  (textArea.value.match(/[(){}\[\]]/g) || []).forEach(bracket => {
+    (textArea.value.match(/[(){}[\]]/g) || []).forEach(bracket => {
         counts[bracket] = (counts[bracket] || 0) + 1;
     });
     var errors = [];
@@ -27,14 +27,14 @@ function checkBrackets(textArea, counterElt) {
 
 function setupBracketChecking(id_prompt, id_counter) {
     var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea");
-  var counter = gradioApp().getElementById(id_counter)
+    var counter = gradioApp().getElementById(id_counter);
 
     if (textarea && counter) {
         textarea.addEventListener("input", () => checkBrackets(textarea, counter));
     }
 }
 
-onUiLoaded(function () {
+onUiLoaded(function() {
     setupBracketChecking('txt2img_prompt', 'txt2img_token_counter');
     setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter');
     setupBracketChecking('img2img_prompt', 'img2img_token_counter');

html/extra-networks-card.html

@@ -1,15 +1,14 @@
-<div class='card' style={style} onclick={card_clicked}>
+<div class='card' style={style} onclick={card_clicked} {sort_keys}>
+	{background_image}
 	{metadata_button}
-
 	<div class='actions'>
 		<div class='additional'>
 			<ul>
 				<a href="#" title="replace preview image with currently selected in gallery" onclick={save_card_preview}>replace preview</a>
 			</ul>
-			<span style="display:none" class='search_term{serach_only}'>{search_term}</span>
+			<span style="display:none" class='search_term{search_only}'>{search_term}</span>
 		</div>
 		<span class='name'>{name}</span>
 		<span class='description'>{description}</span>
 	</div>
 </div>
-

html/footer.html

@@ -1,10 +1,12 @@
 <div>
-        <a href="/docs">API</a>
+        <a href="{api_docs}">API</a>
          • 
         <a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">Github</a>
          • 
         <a href="https://gradio.app">Gradio</a>
          • 
+        <a href="#" onclick="showProfile('./internal/profile-startup'); return false;">Startup profile</a>
+         • 
         <a href="/" onclick="javascript:gradioApp().getElementById('settings_restart_gradio').click(); return false">Reload UI</a>
 </div>
 <br />

html/licenses.html

@@ -662,3 +662,29 @@ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 THE SOFTWARE.
 </pre>
+
+<h2><a href="https://github.com/madebyollin/taesd/blob/main/LICENSE">TAESD</a></h2>
+<small>Tiny AutoEncoder for Stable Diffusion option for live previews</small>
+<pre>
+MIT License
+
+Copyright (c) 2023 Ollin Boer Bohan
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+</pre>

javascript/aspectRatioOverlay.js

@@ -1,78 +1,78 @@
 
 let currentWidth = null;
 let currentHeight = null;
-let arFrameTimeout = setTimeout(function(){},0);
+let arFrameTimeout = setTimeout(function() {}, 0);
 
-function dimensionChange(e, is_width, is_height){
+function dimensionChange(e, is_width, is_height) {
 
-	if(is_width){
+    if (is_width) {
-		currentWidth = e.target.value*1.0
+        currentWidth = e.target.value * 1.0;
     }
-	if(is_height){
+    if (is_height) {
-		currentHeight = e.target.value*1.0
+        currentHeight = e.target.value * 1.0;
     }
 
     var inImg2img = gradioApp().querySelector("#tab_img2img").style.display == "block";
 
-	if(!inImg2img){
+    if (!inImg2img) {
         return;
     }
 
     var targetElement = null;
 
-    var tabIndex = get_tab_index('mode_img2img')
+    var tabIndex = get_tab_index('mode_img2img');
-	if(tabIndex == 0){ // img2img
+    if (tabIndex == 0) { // img2img
         targetElement = gradioApp().querySelector('#img2img_image div[data-testid=image] img');
-	} else if(tabIndex == 1){ //Sketch
+    } else if (tabIndex == 1) { //Sketch
         targetElement = gradioApp().querySelector('#img2img_sketch div[data-testid=image] img');
-	} else if(tabIndex == 2){ // Inpaint
+    } else if (tabIndex == 2) { // Inpaint
         targetElement = gradioApp().querySelector('#img2maskimg div[data-testid=image] img');
-	} else if(tabIndex == 3){ // Inpaint sketch
+    } else if (tabIndex == 3) { // Inpaint sketch
         targetElement = gradioApp().querySelector('#inpaint_sketch div[data-testid=image] img');
     }
 
 
-	if(targetElement){
+    if (targetElement) {
 
         var arPreviewRect = gradioApp().querySelector('#imageARPreview');
-		if(!arPreviewRect){
+        if (!arPreviewRect) {
-		    arPreviewRect = document.createElement('div')
+            arPreviewRect = document.createElement('div');
             arPreviewRect.id = "imageARPreview";
-		    gradioApp().appendChild(arPreviewRect)
+            gradioApp().appendChild(arPreviewRect);
         }
 
 
 
         var viewportOffset = targetElement.getBoundingClientRect();
 
-		var viewportscale = Math.min(  targetElement.clientWidth/targetElement.naturalWidth, targetElement.clientHeight/targetElement.naturalHeight )
+        var viewportscale = Math.min(targetElement.clientWidth / targetElement.naturalWidth, targetElement.clientHeight / targetElement.naturalHeight);
 
-		var scaledx = targetElement.naturalWidth*viewportscale
+        var scaledx = targetElement.naturalWidth * viewportscale;
-		var scaledy = targetElement.naturalHeight*viewportscale
+        var scaledy = targetElement.naturalHeight * viewportscale;
 
-		var cleintRectTop    = (viewportOffset.top+window.scrollY)
+        var cleintRectTop = (viewportOffset.top + window.scrollY);
-		var cleintRectLeft   = (viewportOffset.left+window.scrollX)
+        var cleintRectLeft = (viewportOffset.left + window.scrollX);
-		var cleintRectCentreY = cleintRectTop  + (targetElement.clientHeight/2)
+        var cleintRectCentreY = cleintRectTop + (targetElement.clientHeight / 2);
-		var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth/2)
+        var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth / 2);
 
-		var arscale = Math.min(  scaledx/currentWidth, scaledy/currentHeight )
+        var arscale = Math.min(scaledx / currentWidth, scaledy / currentHeight);
-		var arscaledx = currentWidth*arscale
+        var arscaledx = currentWidth * arscale;
-		var arscaledy = currentHeight*arscale
+        var arscaledy = currentHeight * arscale;
 
-		var arRectTop    = cleintRectCentreY-(arscaledy/2)
+        var arRectTop = cleintRectCentreY - (arscaledy / 2);
-		var arRectLeft   = cleintRectCentreX-(arscaledx/2)
+        var arRectLeft = cleintRectCentreX - (arscaledx / 2);
-		var arRectWidth  = arscaledx
+        var arRectWidth = arscaledx;
-		var arRectHeight = arscaledy
+        var arRectHeight = arscaledy;
 
-	    arPreviewRect.style.top  = arRectTop+'px';
+        arPreviewRect.style.top = arRectTop + 'px';
-	    arPreviewRect.style.left = arRectLeft+'px';
+        arPreviewRect.style.left = arRectLeft + 'px';
-	    arPreviewRect.style.width = arRectWidth+'px';
+        arPreviewRect.style.width = arRectWidth + 'px';
-	    arPreviewRect.style.height = arRectHeight+'px';
+        arPreviewRect.style.height = arRectHeight + 'px';
 
         clearTimeout(arFrameTimeout);
-	    arFrameTimeout = setTimeout(function(){
+        arFrameTimeout = setTimeout(function() {
             arPreviewRect.style.display = 'none';
-	    },2000);
+        }, 2000);
 
         arPreviewRect.style.display = 'block';
 
@@ -81,31 +81,33 @@ function dimensionChange(e, is_width, is_height){
 }
 
 
-onUiUpdate(function(){
+onAfterUiUpdate(function() {
     var arPreviewRect = gradioApp().querySelector('#imageARPreview');
-	if(arPreviewRect){
+    if (arPreviewRect) {
         arPreviewRect.style.display = 'none';
     }
     var tabImg2img = gradioApp().querySelector("#tab_img2img");
     if (tabImg2img) {
         var inImg2img = tabImg2img.style.display == "block";
-        if(inImg2img){
+        if (inImg2img) {
             let inputs = gradioApp().querySelectorAll('input');
-            inputs.forEach(function(e){
+            inputs.forEach(function(e) {
-                var is_width = e.parentElement.id == "img2img_width"
+                var is_width = e.parentElement.id == "img2img_width";
-                var is_height = e.parentElement.id == "img2img_height"
+                var is_height = e.parentElement.id == "img2img_height";
 
-                if((is_width || is_height) && !e.classList.contains('scrollwatch')){
+                if ((is_width || is_height) && !e.classList.contains('scrollwatch')) {
-                    e.addEventListener('input', function(e){dimensionChange(e, is_width, is_height)} )
+                    e.addEventListener('input', function(e) {
-                    e.classList.add('scrollwatch')
+                        dimensionChange(e, is_width, is_height);
+                    });
+                    e.classList.add('scrollwatch');
                 }
-                if(is_width){
+                if (is_width) {
-                    currentWidth = e.value*1.0
+                    currentWidth = e.value * 1.0;
                 }
-                if(is_height){
+                if (is_height) {
-                    currentHeight = e.value*1.0
+                    currentHeight = e.value * 1.0;
                 }
-            })
+            });
         }
     }
 });

javascript/contextMenus.js

@@ -1,48 +1,48 @@
 
-contextMenuInit = function(){
+var contextMenuInit = function() {
-  let eventListenerApplied=false;
+    let eventListenerApplied = false;
     let menuSpecs = new Map();
 
-  const uid = function(){
+    const uid = function() {
         return Date.now().toString(36) + Math.random().toString(36).substring(2);
-  }
+    };
 
-  function showContextMenu(event,element,menuEntries){
+    function showContextMenu(event, element, menuEntries) {
         let posx = event.clientX + document.body.scrollLeft + document.documentElement.scrollLeft;
         let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop;
 
-    let oldMenu = gradioApp().querySelector('#context-menu')
+        let oldMenu = gradioApp().querySelector('#context-menu');
-    if(oldMenu){
+        if (oldMenu) {
-      oldMenu.remove()
+            oldMenu.remove();
         }
 
-    let baseStyle = window.getComputedStyle(uiCurrentTab)
+        let baseStyle = window.getComputedStyle(uiCurrentTab);
 
-    const contextMenu = document.createElement('nav')
+        const contextMenu = document.createElement('nav');
-    contextMenu.id = "context-menu"
+        contextMenu.id = "context-menu";
-    contextMenu.style.background = baseStyle.background
+        contextMenu.style.background = baseStyle.background;
-    contextMenu.style.color = baseStyle.color
+        contextMenu.style.color = baseStyle.color;
-    contextMenu.style.fontFamily = baseStyle.fontFamily
+        contextMenu.style.fontFamily = baseStyle.fontFamily;
-    contextMenu.style.top = posy+'px'
+        contextMenu.style.top = posy + 'px';
-    contextMenu.style.left = posx+'px'
+        contextMenu.style.left = posx + 'px';
 
 
 
-    const contextMenuList = document.createElement('ul')
+        const contextMenuList = document.createElement('ul');
         contextMenuList.className = 'context-menu-items';
         contextMenu.append(contextMenuList);
 
-    menuEntries.forEach(function(entry){
+        menuEntries.forEach(function(entry) {
-      let contextMenuEntry = document.createElement('a')
+            let contextMenuEntry = document.createElement('a');
-      contextMenuEntry.innerHTML = entry['name']
+            contextMenuEntry.innerHTML = entry['name'];
             contextMenuEntry.addEventListener("click", function() {
                 entry['func']();
-      })
+            });
             contextMenuList.append(contextMenuEntry);
 
-    })
+        });
 
-    gradioApp().appendChild(contextMenu)
+        gradioApp().appendChild(contextMenu);
 
         let menuWidth = contextMenu.offsetWidth + 4;
         let menuHeight = contextMenu.offsetHeight + 4;
@@ -50,117 +50,127 @@ contextMenuInit = function(){
         let windowWidth = window.innerWidth;
         let windowHeight = window.innerHeight;
 
-    if ( (windowWidth - posx) < menuWidth ) {
+        if ((windowWidth - posx) < menuWidth) {
             contextMenu.style.left = windowWidth - menuWidth + "px";
         }
 
-    if ( (windowHeight - posy) < menuHeight ) {
+        if ((windowHeight - posy) < menuHeight) {
             contextMenu.style.top = windowHeight - menuHeight + "px";
         }
 
     }
 
-  function appendContextMenuOption(targetElementSelector,entryName,entryFunction){
+    function appendContextMenuOption(targetElementSelector, entryName, entryFunction) {
 
-    var currentItems = menuSpecs.get(targetElementSelector)
+        var currentItems = menuSpecs.get(targetElementSelector);
 
-    if(!currentItems){
+        if (!currentItems) {
-      currentItems = []
+            currentItems = [];
-      menuSpecs.set(targetElementSelector,currentItems);
+            menuSpecs.set(targetElementSelector, currentItems);
         }
-    let newItem = {'id':targetElementSelector+'_'+uid(),
+        let newItem = {
-                   'name':entryName,
+            id: targetElementSelector + '_' + uid(),
-                   'func':entryFunction,
+            name: entryName,
-                   'isNew':true}
+            func: entryFunction,
+            isNew: true
+        };
 
-    currentItems.push(newItem)
+        currentItems.push(newItem);
-    return newItem['id']
+        return newItem['id'];
     }
 
-  function removeContextMenuOption(uid){
+    function removeContextMenuOption(uid) {
         menuSpecs.forEach(function(v) {
-      let index = -1
+            let index = -1;
-      v.forEach(function(e,ei){if(e['id']==uid){index=ei}})
+            v.forEach(function(e, ei) {
-      if(index>=0){
+                if (e['id'] == uid) {
+                    index = ei;
+                }
+            });
+            if (index >= 0) {
                 v.splice(index, 1);
             }
-    })
+        });
     }
 
-  function addContextMenuEventListener(){
+    function addContextMenuEventListener() {
-    if(eventListenerApplied){
+        if (eventListenerApplied) {
             return;
         }
         gradioApp().addEventListener("click", function(e) {
-      if(! e.isTrusted){
+            if (!e.isTrusted) {
-        return
+                return;
             }
 
-      let oldMenu = gradioApp().querySelector('#context-menu')
+            let oldMenu = gradioApp().querySelector('#context-menu');
-      if(oldMenu){
+            if (oldMenu) {
-        oldMenu.remove()
+                oldMenu.remove();
             }
         });
         gradioApp().addEventListener("contextmenu", function(e) {
-      let oldMenu = gradioApp().querySelector('#context-menu')
+            let oldMenu = gradioApp().querySelector('#context-menu');
-      if(oldMenu){
+            if (oldMenu) {
-        oldMenu.remove()
+                oldMenu.remove();
             }
-      menuSpecs.forEach(function(v,k) {
+            menuSpecs.forEach(function(v, k) {
-        if(e.composedPath()[0].matches(k)){
+                if (e.composedPath()[0].matches(k)) {
-          showContextMenu(e,e.composedPath()[0],v)
+                    showContextMenu(e, e.composedPath()[0], v);
-          e.preventDefault()
+                    e.preventDefault();
                 }
-      })
             });
-    eventListenerApplied=true
+        });
+        eventListenerApplied = true;
 
     }
 
-  return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener]
+    return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener];
-}
+};
 
-initResponse = contextMenuInit();
+var initResponse = contextMenuInit();
-appendContextMenuOption     = initResponse[0];
+var appendContextMenuOption = initResponse[0];
-removeContextMenuOption     = initResponse[1];
+var removeContextMenuOption = initResponse[1];
-addContextMenuEventListener = initResponse[2];
+var addContextMenuEventListener = initResponse[2];
 
-(function(){
+(function() {
     //Start example Context Menu Items
-  let generateOnRepeat = function(genbuttonid,interruptbuttonid){
+    let generateOnRepeat = function(genbuttonid, interruptbuttonid) {
         let genbutton = gradioApp().querySelector(genbuttonid);
         let interruptbutton = gradioApp().querySelector(interruptbuttonid);
-    if(!interruptbutton.offsetParent){
+        if (!interruptbutton.offsetParent) {
             genbutton.click();
         }
-    clearInterval(window.generateOnRepeatInterval)
+        clearInterval(window.generateOnRepeatInterval);
-    window.generateOnRepeatInterval = setInterval(function(){
+        window.generateOnRepeatInterval = setInterval(function() {
-      if(!interruptbutton.offsetParent){
+            if (!interruptbutton.offsetParent) {
                 genbutton.click();
             }
         },
-    500)
+        500);
-  }
+    };
 
-  appendContextMenuOption('#txt2img_generate','Generate forever',function(){
+    let generateOnRepeat_txt2img = function() {
-    generateOnRepeat('#txt2img_generate','#txt2img_interrupt');
+        generateOnRepeat('#txt2img_generate', '#txt2img_interrupt');
-  })
+    };
-  appendContextMenuOption('#img2img_generate','Generate forever',function(){
-    generateOnRepeat('#img2img_generate','#img2img_interrupt');
-  })
 
-  let cancelGenerateForever = function(){
+    let generateOnRepeat_img2img = function() {
-    clearInterval(window.generateOnRepeatInterval)
+        generateOnRepeat('#img2img_generate', '#img2img_interrupt');
-  }
+    };
 
-  appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever)
+    appendContextMenuOption('#txt2img_generate', 'Generate forever', generateOnRepeat_txt2img);
-  appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever)
+    appendContextMenuOption('#txt2img_interrupt', 'Generate forever', generateOnRepeat_txt2img);
-  appendContextMenuOption('#img2img_interrupt','Cancel generate forever',cancelGenerateForever)
+    appendContextMenuOption('#img2img_generate', 'Generate forever', generateOnRepeat_img2img);
-  appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever)
+    appendContextMenuOption('#img2img_interrupt', 'Generate forever', generateOnRepeat_img2img);
+
+    let cancelGenerateForever = function() {
+        clearInterval(window.generateOnRepeatInterval);
+    };
+
+    appendContextMenuOption('#txt2img_interrupt', 'Cancel generate forever', cancelGenerateForever);
+    appendContextMenuOption('#txt2img_generate', 'Cancel generate forever', cancelGenerateForever);
+    appendContextMenuOption('#img2img_interrupt', 'Cancel generate forever', cancelGenerateForever);
+    appendContextMenuOption('#img2img_generate', 'Cancel generate forever', cancelGenerateForever);
 
 })();
 //End example Context Menu Items
 
-onUiUpdate(function(){
+onAfterUiUpdate(addContextMenuEventListener);
-  addContextMenuEventListener()
-});

javascript/dragdrop.js

@@ -1,11 +1,11 @@
 // allows drag-dropping files into gradio image elements, and also pasting images from clipboard
 
-function isValidImageList( files ) {
+function isValidImageList(files) {
     return files && files?.length === 1 && ['image/png', 'image/gif', 'image/jpeg'].includes(files[0].type);
 }
 
-function dropReplaceImage( imgWrap, files ) {
+function dropReplaceImage(imgWrap, files) {
-    if ( ! isValidImageList( files ) ) {
+    if (!isValidImageList(files)) {
         return;
     }
 
@@ -14,8 +14,8 @@ function dropReplaceImage( imgWrap, files ) {
     imgWrap.querySelector('.modify-upload button + button, .touch-none + div button + button')?.click();
     const callback = () => {
         const fileInput = imgWrap.querySelector('input[type="file"]');
-        if ( fileInput ) {
+        if (fileInput) {
-            if ( files.length === 0 ) {
+            if (files.length === 0) {
                 files = new DataTransfer();
                 files.items.add(tmpFile);
                 fileInput.files = files.files;
@@ -26,34 +26,49 @@ function dropReplaceImage( imgWrap, files ) {
         }
     };
 
-    if ( imgWrap.closest('#pnginfo_image') ) {
+    if (imgWrap.closest('#pnginfo_image')) {
         // special treatment for PNG Info tab, wait for fetch request to finish
         const oldFetch = window.fetch;
-        window.fetch = async (input, options) => {
+        window.fetch = async(input, options) => {
             const response = await oldFetch(input, options);
-            if ( 'api/predict/' === input ) {
+            if ('api/predict/' === input) {
                 const content = await response.text();
                 window.fetch = oldFetch;
-                window.requestAnimationFrame( () => callback() );
+                window.requestAnimationFrame(() => callback());
                 return new Response(content, {
                     status: response.status,
                     statusText: response.statusText,
                     headers: response.headers
-                })
+                });
             }
             return response;
         };
     } else {
-        window.requestAnimationFrame( () => callback() );
+        window.requestAnimationFrame(() => callback());
     }
 }
 
+function eventHasFiles(e) {
+    if (!e.dataTransfer || !e.dataTransfer.files) return false;
+    if (e.dataTransfer.files.length > 0) return true;
+    if (e.dataTransfer.items.length > 0 && e.dataTransfer.items[0].kind == "file") return true;
+
+    return false;
+}
+
+function dragDropTargetIsPrompt(target) {
+    if (target?.placeholder && target?.placeholder.indexOf("Prompt") >= 0) return true;
+    if (target?.parentNode?.parentNode?.className?.indexOf("prompt") > 0) return true;
+    return false;
+}
+
 window.document.addEventListener('dragover', e => {
     const target = e.composedPath()[0];
-    const imgWrap = target.closest('[data-testid="image"]');
+    if (!eventHasFiles(e)) return;
-    if ( !imgWrap && target.placeholder && target.placeholder.indexOf("Prompt") == -1) {
+
-        return;
+    var targetImage = target.closest('[data-testid="image"]');
-    }
+    if (!dragDropTargetIsPrompt(target) && !targetImage) return;
+
     e.stopPropagation();
     e.preventDefault();
     e.dataTransfer.dropEffect = 'copy';
@@ -61,28 +76,45 @@ window.document.addEventListener('dragover', e => {
 
 window.document.addEventListener('drop', e => {
     const target = e.composedPath()[0];
-    if (target.placeholder.indexOf("Prompt") == -1) {
+    if (!eventHasFiles(e)) return;
-        return;
+
+    if (dragDropTargetIsPrompt(target)) {
+        e.stopPropagation();
+        e.preventDefault();
+
+        let prompt_target = get_tab_index('tabs') == 1 ? "img2img_prompt_image" : "txt2img_prompt_image";
+
+        const imgParent = gradioApp().getElementById(prompt_target);
+        const files = e.dataTransfer.files;
+        const fileInput = imgParent.querySelector('input[type="file"]');
+        if (fileInput) {
+            fileInput.files = files;
+            fileInput.dispatchEvent(new Event('change'));
         }
-    const imgWrap = target.closest('[data-testid="image"]');
-    if ( !imgWrap ) {
-        return;
     }
+
+    var targetImage = target.closest('[data-testid="image"]');
+    if (targetImage) {
         e.stopPropagation();
         e.preventDefault();
         const files = e.dataTransfer.files;
-    dropReplaceImage( imgWrap, files );
+        dropReplaceImage(targetImage, files);
+        return;
+    }
 });
 
 window.addEventListener('paste', e => {
     const files = e.clipboardData.files;
-    if ( ! isValidImageList( files ) ) {
+    if (!isValidImageList(files)) {
         return;
     }
 
     const visibleImageFields = [...gradioApp().querySelectorAll('[data-testid="image"]')]
-        .filter(el => uiElementIsVisible(el));
+        .filter(el => uiElementIsVisible(el))
-    if ( ! visibleImageFields.length ) {
+        .sort((a, b) => uiElementInSight(b) - uiElementInSight(a));
+
+
+    if (!visibleImageFields.length) {
         return;
     }
 
@@ -93,5 +125,6 @@ window.addEventListener('paste', e => {
         firstFreeImageField ?
             firstFreeImageField :
             visibleImageFields[visibleImageFields.length - 1]
-    , files );
+        , files
+    );
 });

javascript/edit-attention.js

@@ -1,17 +1,17 @@
-function keyupEditAttention(event){
+function keyupEditAttention(event) {
     let target = event.originalTarget || event.composedPath()[0];
-	if (! target.matches("[id*='_toprow'] [id*='_prompt'] textarea")) return;
+    if (!target.matches("*:is([id*='_toprow'] [id*='_prompt'], .prompt) textarea")) return;
-	if (! (event.metaKey || event.ctrlKey)) return;
+    if (!(event.metaKey || event.ctrlKey)) return;
 
-	let isPlus = event.key == "ArrowUp"
+    let isPlus = event.key == "ArrowUp";
-	let isMinus = event.key == "ArrowDown"
+    let isMinus = event.key == "ArrowDown";
     if (!isPlus && !isMinus) return;
 
     let selectionStart = target.selectionStart;
     let selectionEnd = target.selectionEnd;
     let text = target.value;
 
-    function selectCurrentParenthesisBlock(OPEN, CLOSE){
+    function selectCurrentParenthesisBlock(OPEN, CLOSE) {
         if (selectionStart !== selectionEnd) return false;
 
         // Find opening parenthesis around current cursor
@@ -44,7 +44,7 @@ function keyupEditAttention(event){
         return true;
     }
 
-    function selectCurrentWord(){
+    function selectCurrentWord() {
         if (selectionStart !== selectionEnd) return false;
         const delimiters = opts.keyedit_delimiters + " \r\n\t";
 
@@ -69,20 +69,20 @@ function keyupEditAttention(event){
 
     event.preventDefault();
 
-    var closeCharacter = ')'
+    var closeCharacter = ')';
-    var delta = opts.keyedit_precision_attention
+    var delta = opts.keyedit_precision_attention;
 
-    if (selectionStart > 0 && text[selectionStart - 1] == '<'){
+    if (selectionStart > 0 && text[selectionStart - 1] == '<') {
-        closeCharacter = '>'
+        closeCharacter = '>';
-        delta = opts.keyedit_precision_extra
+        delta = opts.keyedit_precision_extra;
     } else if (selectionStart == 0 || text[selectionStart - 1] != "(") {
 
         // do not include spaces at the end
-        while(selectionEnd > selectionStart && text[selectionEnd-1] == ' '){
+        while (selectionEnd > selectionStart && text[selectionEnd - 1] == ' ') {
             selectionEnd -= 1;
         }
-        if(selectionStart == selectionEnd){
+        if (selectionStart == selectionEnd) {
-            return
+            return;
         }
 
         text = text.slice(0, selectionStart) + "(" + text.slice(selectionStart, selectionEnd) + ":1.0)" + text.slice(selectionEnd);
@@ -97,14 +97,15 @@ function keyupEditAttention(event){
 
     weight += isPlus ? delta : -delta;
     weight = parseFloat(weight.toPrecision(12));
-	if(String(weight).length == 1) weight += ".0"
+    if (String(weight).length == 1) weight += ".0";
 
     if (closeCharacter == ')' && weight == 1) {
-        text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + 5);
+        var endParenPos = text.substring(selectionEnd).indexOf(')');
+        text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + endParenPos + 1);
         selectionStart--;
         selectionEnd--;
     } else {
-        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1);
+        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + end);
     }
 
     target.focus();
@@ -112,7 +113,7 @@ function keyupEditAttention(event){
     target.selectionStart = selectionStart;
     target.selectionEnd = selectionEnd;
 
-	updateInput(target)
+    updateInput(target);
 }
 
 addEventListener('keydown', (event) => {

javascript/edit-order.js

@@ -0,0 +1,41 @@
+/* alt+left/right moves text in prompt */
+
+function keyupEditOrder(event) {
+    if (!opts.keyedit_move) return;
+
+    let target = event.originalTarget || event.composedPath()[0];
+    if (!target.matches("*:is([id*='_toprow'] [id*='_prompt'], .prompt) textarea")) return;
+    if (!event.altKey) return;
+    event.preventDefault()
+
+    let isLeft = event.key == "ArrowLeft";
+    let isRight = event.key == "ArrowRight";
+    if (!isLeft && !isRight) return;
+
+    let selectionStart = target.selectionStart;
+    let selectionEnd = target.selectionEnd;
+    let text = target.value;
+    let items = text.split(",");
+    let indexStart = (text.slice(0, selectionStart).match(/,/g) || []).length;
+    let indexEnd = (text.slice(0, selectionEnd).match(/,/g) || []).length;
+    let range = indexEnd - indexStart + 1;
+
+    if (isLeft && indexStart > 0) {
+        items.splice(indexStart - 1, 0, ...items.splice(indexStart, range));
+        target.value = items.join();
+        target.selectionStart = items.slice(0, indexStart - 1).join().length + (indexStart == 1 ? 0 : 1);
+        target.selectionEnd = items.slice(0, indexEnd).join().length;
+    } else if (isRight && indexEnd < items.length - 1) {
+        items.splice(indexStart + 1, 0, ...items.splice(indexStart, range));
+        target.value = items.join();
+        target.selectionStart = items.slice(0, indexStart + 1).join().length + 1;
+        target.selectionEnd = items.slice(0, indexEnd + 2).join().length;
+    }
+
+    event.preventDefault();
+    updateInput(target);
+}
+
+addEventListener('keydown', (event) => {
+    keyupEditOrder(event);
+});

javascript/extensions.js

@@ -1,51 +1,54 @@
 
-function extensions_apply(_disabled_list, _update_list, disable_all){
+function extensions_apply(_disabled_list, _update_list, disable_all) {
-    var disable = []
+    var disable = [];
-    var update = []
+    var update = [];
 
-    gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x){
+    gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
-        if(x.name.startsWith("enable_") && ! x.checked)
+        if (x.name.startsWith("enable_") && !x.checked) {
-            disable.push(x.name.substring(7))
+            disable.push(x.name.substring(7));
+        }
 
-        if(x.name.startsWith("update_") && x.checked)
+        if (x.name.startsWith("update_") && x.checked) {
-            update.push(x.name.substring(7))
+            update.push(x.name.substring(7));
-    })
+        }
+    });
 
-    restart_reload()
+    restart_reload();
 
-    return [JSON.stringify(disable), JSON.stringify(update), disable_all]
+    return [JSON.stringify(disable), JSON.stringify(update), disable_all];
 }
 
-function extensions_check(){
+function extensions_check() {
-    var disable = []
+    var disable = [];
 
-    gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x){
+    gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
-        if(x.name.startsWith("enable_") && ! x.checked)
+        if (x.name.startsWith("enable_") && !x.checked) {
-            disable.push(x.name.substring(7))
+            disable.push(x.name.substring(7));
-    })
+        }
+    });
 
-    gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x){
+    gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x) {
-        x.innerHTML = "Loading..."
+        x.innerHTML = "Loading...";
-    })
+    });
 
 
-    var id = randomId()
+    var id = randomId();
-    requestProgress(id, gradioApp().getElementById('extensions_installed_top'), null, function(){
+    requestProgress(id, gradioApp().getElementById('extensions_installed_top'), null, function() {
 
-    })
+    });
 
-    return [id, JSON.stringify(disable)]
+    return [id, JSON.stringify(disable)];
 }
 
-function install_extension_from_index(button, url){
+function install_extension_from_index(button, url) {
-    button.disabled = "disabled"
+    button.disabled = "disabled";
-    button.value = "Installing..."
+    button.value = "Installing...";
 
-    var textarea = gradioApp().querySelector('#extension_to_install textarea')
+    var textarea = gradioApp().querySelector('#extension_to_install textarea');
-    textarea.value = url
+    textarea.value = url;
-    updateInput(textarea)
+    updateInput(textarea);
 
-    gradioApp().querySelector('#install_extension_button').click()
+    gradioApp().querySelector('#install_extension_button').click();
 }
 
 function config_state_confirm_restore(_, config_state_name, config_restore_type) {
@@ -63,9 +66,27 @@ function config_state_confirm_restore(_, config_state_name, config_restore_type)
     let confirmed = confirm("Are you sure you want to restore from this state?\nThis will reset " + restored + ".");
     if (confirmed) {
         restart_reload();
-        gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x){
+        gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x) {
-            x.innerHTML = "Loading..."
+            x.innerHTML = "Loading...";
-        })
+        });
     }
     return [confirmed, config_state_name, config_restore_type];
 }
+
+function toggle_all_extensions(event) {
+    gradioApp().querySelectorAll('#extensions .extension_toggle').forEach(function(checkbox_el) {
+        checkbox_el.checked = event.target.checked;
+    });
+}
+
+function toggle_extension() {
+    let all_extensions_toggled = true;
+    for (const checkbox_el of gradioApp().querySelectorAll('#extensions .extension_toggle')) {
+        if (!checkbox_el.checked) {
+            all_extensions_toggled = false;
+            break;
+        }
+    }
+
+    gradioApp().querySelector('#extensions .all_extensions_toggle').checked = all_extensions_toggled;
+}

javascript/extraNetworks.js

@@ -1,144 +1,209 @@
-function setupExtraNetworksForTab(tabname){
+function setupExtraNetworksForTab(tabname) {
-    gradioApp().querySelector('#'+tabname+'_extra_tabs').classList.add('extra-networks')
+    gradioApp().querySelector('#' + tabname + '_extra_tabs').classList.add('extra-networks');
 
-    var tabs = gradioApp().querySelector('#'+tabname+'_extra_tabs > div')
+    var tabs = gradioApp().querySelector('#' + tabname + '_extra_tabs > div');
-    var search = gradioApp().querySelector('#'+tabname+'_extra_search textarea')
+    var search = gradioApp().querySelector('#' + tabname + '_extra_search textarea');
-    var refresh = gradioApp().getElementById(tabname+'_extra_refresh')
+    var sort = gradioApp().getElementById(tabname + '_extra_sort');
+    var sortOrder = gradioApp().getElementById(tabname + '_extra_sortorder');
+    var refresh = gradioApp().getElementById(tabname + '_extra_refresh');
 
-    search.classList.add('search')
+    search.classList.add('search');
-    tabs.appendChild(search)
+    sort.classList.add('sort');
-    tabs.appendChild(refresh)
+    sortOrder.classList.add('sortorder');
+    sort.dataset.sortkey = 'sortDefault';
+    tabs.appendChild(search);
+    tabs.appendChild(sort);
+    tabs.appendChild(sortOrder);
+    tabs.appendChild(refresh);
 
-    var applyFilter = function(){
+    var applyFilter = function() {
-        var searchTerm = search.value.toLowerCase()
+        var searchTerm = search.value.toLowerCase();
 
-        gradioApp().querySelectorAll('#'+tabname+'_extra_tabs div.card').forEach(function(elem){
+        gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card').forEach(function(elem) {
-            var searchOnly = elem.querySelector('.search_only')
+            var searchOnly = elem.querySelector('.search_only');
-            var text = elem.querySelector('.name').textContent.toLowerCase() + " " + elem.querySelector('.search_term').textContent.toLowerCase()
+            var text = elem.querySelector('.name').textContent.toLowerCase() + " " + elem.querySelector('.search_term').textContent.toLowerCase();
 
-            var visible = text.indexOf(searchTerm) != -1
+            var visible = text.indexOf(searchTerm) != -1;
 
-            if(searchOnly && searchTerm.length < 4){
+            if (searchOnly && searchTerm.length < 4) {
-                visible = false
+                visible = false;
             }
 
-            elem.style.display = visible ? "" : "none"
+            elem.style.display = visible ? "" : "none";
-        })
+        });
+    };
+
+    var applySort = function() {
+        var reverse = sortOrder.classList.contains("sortReverse");
+        var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim();
+        sortKey = sortKey ? "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1) : "";
+        var sortKeyStore = sortKey ? sortKey + (reverse ? "Reverse" : "") : "";
+        if (!sortKey || sortKeyStore == sort.dataset.sortkey) {
+            return;
         }
 
+        sort.dataset.sortkey = sortKeyStore;
+
+        var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card');
+        cards.forEach(function(card) {
+            card.originalParentElement = card.parentElement;
+        });
+        var sortedCards = Array.from(cards);
+        sortedCards.sort(function(cardA, cardB) {
+            var a = cardA.dataset[sortKey];
+            var b = cardB.dataset[sortKey];
+            if (!isNaN(a) && !isNaN(b)) {
+                return parseInt(a) - parseInt(b);
+            }
+
+            return (a < b ? -1 : (a > b ? 1 : 0));
+        });
+        if (reverse) {
+            sortedCards.reverse();
+        }
+        cards.forEach(function(card) {
+            card.remove();
+        });
+        sortedCards.forEach(function(card) {
+            card.originalParentElement.appendChild(card);
+        });
+    };
+
     search.addEventListener("input", applyFilter);
     applyFilter();
+    ["change", "blur", "click"].forEach(function(evt) {
+        sort.querySelector("input").addEventListener(evt, applySort);
+    });
+    sortOrder.addEventListener("click", function() {
+        sortOrder.classList.toggle("sortReverse");
+        applySort();
+    });
 
     extraNetworksApplyFilter[tabname] = applyFilter;
 }
 
-function applyExtraNetworkFilter(tabname){
+function applyExtraNetworkFilter(tabname) {
     setTimeout(extraNetworksApplyFilter[tabname], 1);
 }
 
-var extraNetworksApplyFilter = {}
+var extraNetworksApplyFilter = {};
 var activePromptTextarea = {};
 
-function setupExtraNetworks(){
+function setupExtraNetworks() {
-    setupExtraNetworksForTab('txt2img')
+    setupExtraNetworksForTab('txt2img');
-    setupExtraNetworksForTab('img2img')
+    setupExtraNetworksForTab('img2img');
 
-    function registerPrompt(tabname, id){
+    function registerPrompt(tabname, id) {
         var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
 
-        if (! activePromptTextarea[tabname]){
+        if (!activePromptTextarea[tabname]) {
-            activePromptTextarea[tabname] = textarea
+            activePromptTextarea[tabname] = textarea;
         }
 
-		textarea.addEventListener("focus", function(){
+        textarea.addEventListener("focus", function() {
             activePromptTextarea[tabname] = textarea;
         });
     }
 
-    registerPrompt('txt2img', 'txt2img_prompt')
+    registerPrompt('txt2img', 'txt2img_prompt');
-    registerPrompt('txt2img', 'txt2img_neg_prompt')
+    registerPrompt('txt2img', 'txt2img_neg_prompt');
-    registerPrompt('img2img', 'img2img_prompt')
+    registerPrompt('img2img', 'img2img_prompt');
-    registerPrompt('img2img', 'img2img_neg_prompt')
+    registerPrompt('img2img', 'img2img_neg_prompt');
 }
 
-onUiLoaded(setupExtraNetworks)
+onUiLoaded(setupExtraNetworks);
 
-var re_extranet   =    /<([^:]+:[^:]+):[\d\.]+>/;
+var re_extranet = /<([^:]+:[^:]+):[\d.]+>/;
-var re_extranet_g = /\s+<([^:]+:[^:]+):[\d\.]+>/g;
+var re_extranet_g = /\s+<([^:]+:[^:]+):[\d.]+>/g;
 
-function tryToRemoveExtraNetworkFromPrompt(textarea, text){
+function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
-    var m = text.match(re_extranet)
+    var m = text.match(re_extranet);
-    if(! m) return false
+    var replaced = false;
-
+    var newTextareaText;
-    var partToSearch = m[1]
+    if (m) {
-    var replaced = false
+        var partToSearch = m[1];
-    var newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found){
+        newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found) {
             m = found.match(re_extranet);
-        if(m[1] == partToSearch){
+            if (m[1] == partToSearch) {
                 replaced = true;
-            return ""
+                return "";
             }
             return found;
-    })
+        });
+    } else {
+        newTextareaText = textarea.value.replaceAll(new RegExp(text, "g"), function(found) {
+            if (found == text) {
+                replaced = true;
+                return "";
+            }
+            return found;
+        });
+    }
 
-    if(replaced){
+    if (replaced) {
-        textarea.value = newTextareaText
+        textarea.value = newTextareaText;
         return true;
     }
 
-    return false
+    return false;
 }
 
-function cardClicked(tabname, textToAdd, allowNegativePrompt){
+function cardClicked(tabname, textToAdd, allowNegativePrompt) {
-    var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea")
+    var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea");
 
-    if(! tryToRemoveExtraNetworkFromPrompt(textarea, textToAdd)){
+    if (!tryToRemoveExtraNetworkFromPrompt(textarea, textToAdd)) {
-        textarea.value = textarea.value + opts.extra_networks_add_text_separator + textToAdd
+        textarea.value = textarea.value + opts.extra_networks_add_text_separator + textToAdd;
     }
 
-    updateInput(textarea)
+    updateInput(textarea);
 }
 
-function saveCardPreview(event, tabname, filename){
+function saveCardPreview(event, tabname, filename) {
-    var textarea = gradioApp().querySelector("#" + tabname + '_preview_filename  > label > textarea')
+    var textarea = gradioApp().querySelector("#" + tabname + '_preview_filename  > label > textarea');
-    var button = gradioApp().getElementById(tabname + '_save_preview')
+    var button = gradioApp().getElementById(tabname + '_save_preview');
 
-    textarea.value = filename
+    textarea.value = filename;
-    updateInput(textarea)
+    updateInput(textarea);
 
-    button.click()
+    button.click();
 
-    event.stopPropagation()
+    event.stopPropagation();
-    event.preventDefault()
+    event.preventDefault();
 }
 
-function extraNetworksSearchButton(tabs_id, event){
+function extraNetworksSearchButton(tabs_id, event) {
-    var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > div > textarea')
+    var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > div > textarea');
-    var button = event.target
+    var button = event.target;
-    var text = button.classList.contains("search-all") ? "" : button.textContent.trim()
+    var text = button.classList.contains("search-all") ? "" : button.textContent.trim();
 
-    searchTextarea.value = text
+    searchTextarea.value = text;
-    updateInput(searchTextarea)
+    updateInput(searchTextarea);
 }
 
 var globalPopup = null;
 var globalPopupInner = null;
-function popup(contents){
+function popup(contents) {
-    if(! globalPopup){
+    if (!globalPopup) {
-        globalPopup = document.createElement('div')
+        globalPopup = document.createElement('div');
-        globalPopup.onclick = function(){ globalPopup.style.display = "none"; };
+        globalPopup.onclick = function() {
+            globalPopup.style.display = "none";
+        };
         globalPopup.classList.add('global-popup');
 
-        var close = document.createElement('div')
+        var close = document.createElement('div');
         close.classList.add('global-popup-close');
-        close.onclick = function(){ globalPopup.style.display = "none"; };
+        close.onclick = function() {
+            globalPopup.style.display = "none";
+        };
         close.title = "Close";
-        globalPopup.appendChild(close)
+        globalPopup.appendChild(close);
 
-        globalPopupInner = document.createElement('div')
+        globalPopupInner = document.createElement('div');
-        globalPopupInner.onclick = function(event){ event.stopPropagation(); return false; };
+        globalPopupInner.onclick = function(event) {
+            event.stopPropagation(); return false;
+        };
         globalPopupInner.classList.add('global-popup-inner');
-        globalPopup.appendChild(globalPopupInner)
+        globalPopup.appendChild(globalPopupInner);
 
         gradioApp().appendChild(globalPopup);
     }
@@ -149,31 +214,33 @@ function popup(contents){
     globalPopup.style.display = "flex";
 }
 
-function extraNetworksShowMetadata(text){
+function extraNetworksShowMetadata(text) {
-    var elem = document.createElement('pre')
+    var elem = document.createElement('pre');
     elem.classList.add('popup-metadata');
     elem.textContent = text;
 
     popup(elem);
 }
 
-function requestGet(url, data, handler, errorHandler){
+function requestGet(url, data, handler, errorHandler) {
     var xhr = new XMLHttpRequest();
-    var args = Object.keys(data).map(function(k){ return encodeURIComponent(k) + '=' + encodeURIComponent(data[k]) }).join('&')
+    var args = Object.keys(data).map(function(k) {
+        return encodeURIComponent(k) + '=' + encodeURIComponent(data[k]);
+    }).join('&');
     xhr.open("GET", url + "?" + args, true);
 
-    xhr.onreadystatechange = function () {
+    xhr.onreadystatechange = function() {
         if (xhr.readyState === 4) {
             if (xhr.status === 200) {
                 try {
                     var js = JSON.parse(xhr.responseText);
-                    handler(js)
+                    handler(js);
                 } catch (error) {
                     console.error(error);
-                    errorHandler()
+                    errorHandler();
                 }
-            } else{
+            } else {
-                errorHandler()
+                errorHandler();
             }
         }
     };
@@ -181,16 +248,18 @@ function requestGet(url, data, handler, errorHandler){
     xhr.send(js);
 }
 
-function extraNetworksRequestMetadata(event, extraPage, cardName){
+function extraNetworksRequestMetadata(event, extraPage, cardName) {
-    var showError = function(){ extraNetworksShowMetadata("there was an error getting metadata"); }
+    var showError = function() {
+        extraNetworksShowMetadata("there was an error getting metadata");
+    };
 
-    requestGet("./sd_extra_networks/metadata", {"page": extraPage, "item": cardName}, function(data){
+    requestGet("./sd_extra_networks/metadata", {page: extraPage, item: cardName}, function(data) {
-        if(data && data.metadata){
+        if (data && data.metadata) {
-            extraNetworksShowMetadata(data.metadata)
+            extraNetworksShowMetadata(data.metadata);
-        } else{
+        } else {
-            showError()
+            showError();
         }
-    }, showError)
+    }, showError);
 
-    event.stopPropagation()
+    event.stopPropagation();
 }

javascript/generationParams.js

@@ -1,33 +1,35 @@
 // attaches listeners to the txt2img and img2img galleries to update displayed generation param text when the image changes
 
 let txt2img_gallery, img2img_gallery, modal = undefined;
-onUiUpdate(function(){
+onAfterUiUpdate(function() {
     if (!txt2img_gallery) {
-		txt2img_gallery = attachGalleryListeners("txt2img")
+        txt2img_gallery = attachGalleryListeners("txt2img");
     }
     if (!img2img_gallery) {
-		img2img_gallery = attachGalleryListeners("img2img")
+        img2img_gallery = attachGalleryListeners("img2img");
     }
     if (!modal) {
-		modal = gradioApp().getElementById('lightboxModal')
+        modal = gradioApp().getElementById('lightboxModal');
-		modalObserver.observe(modal,  { attributes : true, attributeFilter : ['style'] });
+        modalObserver.observe(modal, {attributes: true, attributeFilter: ['style']});
     }
 });
 
 let modalObserver = new MutationObserver(function(mutations) {
     mutations.forEach(function(mutationRecord) {
-		let selectedTab = gradioApp().querySelector('#tabs div button.selected')?.innerText
+        let selectedTab = gradioApp().querySelector('#tabs div button.selected')?.innerText;
-		if (mutationRecord.target.style.display === 'none' && (selectedTab === 'txt2img' || selectedTab === 'img2img'))
+        if (mutationRecord.target.style.display === 'none' && (selectedTab === 'txt2img' || selectedTab === 'img2img')) {
-			gradioApp().getElementById(selectedTab+"_generation_info_button")?.click()
+            gradioApp().getElementById(selectedTab + "_generation_info_button")?.click();
+        }
     });
 });
 
 function attachGalleryListeners(tab_name) {
-	var gallery = gradioApp().querySelector('#'+tab_name+'_gallery')
+    var gallery = gradioApp().querySelector('#' + tab_name + '_gallery');
-	gallery?.addEventListener('click', () => gradioApp().getElementById(tab_name+"_generation_info_button").click());
+    gallery?.addEventListener('click', () => gradioApp().getElementById(tab_name + "_generation_info_button").click());
     gallery?.addEventListener('keydown', (e) => {
-		if (e.keyCode == 37 || e.keyCode == 39) // left or right arrow
+        if (e.keyCode == 37 || e.keyCode == 39) { // left or right arrow
-			gradioApp().getElementById(tab_name+"_generation_info_button").click()
+            gradioApp().getElementById(tab_name + "_generation_info_button").click();
+        }
     });
     return gallery;
 }

javascript/hints.js

@@ -1,6 +1,6 @@
 // mouseover tooltips for various UI elements
 
-titles = {
+var titles = {
     "Sampling steps": "How many times to improve the generated image iteratively; higher values take longer; very low values can produce bad results",
     "Sampling method": "Which algorithm to use to produce the image",
     "GFPGAN": "Restore low quality faces using GFPGAN neural network",
@@ -9,12 +9,13 @@ titles = {
     "UniPC": "Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models",
     "DPM adaptive": "Ignores step count - uses a number of steps determined by the CFG and resolution",
 
+    "\u{1F4D0}": "Auto detect size from img2img",
     "Batch count": "How many batches of images to create (has no impact on generation performance or VRAM usage)",
     "Batch size": "How many image to create in a single batch (increases generation performance at cost of higher VRAM usage)",
     "CFG Scale": "Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results",
     "Seed": "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result",
     "\u{1f3b2}\ufe0f": "Set seed to -1, which will cause a new random number to be used every time",
-    "\u267b\ufe0f": "Reuse seed from last generation, mostly useful if it was randomed",
+    "\u267b\ufe0f": "Reuse seed from last generation, mostly useful if it was randomized",
     "\u2199\ufe0f": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
     "\u{1f4c2}": "Open images output directory",
     "\u{1f4be}": "Save style",
@@ -66,8 +67,8 @@ titles = {
 
     "Interrogate": "Reconstruct prompt from existing image and put it into the prompt field.",
 
-    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [denoising], [clip_skip], [batch_number], [generation_number], [prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp], [hasprompt<prompt1|default><prompt2>..]; leave empty for default.",
+    "Images filename pattern": "Use tags like [seed] and [date] to define how filenames for images are chosen. Leave empty for default.",
-    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [denoising], [clip_skip], [batch_number], [generation_number], [prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp], [hasprompt<prompt1|default><prompt2>..]; leave empty for default.",
+    "Directory name pattern": "Use tags like [seed] and [date] to define how subdirectories for images and grids are chosen. Leave empty for default.",
     "Max prompt words": "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle",
 
     "Loopback": "Performs img2img processing multiple times. Output images are used as input for the next loop.",
@@ -111,23 +112,29 @@ titles = {
     "Resize height to": "Resizes image to this height. If 0, height is inferred from either of two nearby sliders.",
     "Multiplier for extra networks": "When adding extra network such as Hypernetwork or Lora to prompt, use this multiplier for it.",
     "Discard weights with matching name": "Regular expression; if weights's name matches it, the weights is not written to the resulting checkpoint. Use ^model_ema to discard EMA weights.",
-    "Extra networks tab order": "Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order lsited.",
+    "Extra networks tab order": "Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order listed.",
     "Negative Guidance minimum sigma": "Skip negative prompt for steps where image is already mostly denoised; the higher this value, the more skips there will be; provides increased performance in exchange for minor quality reduction."
-}
+};
 
+function updateTooltip(element) {
+    if (element.title) return; // already has a title
 
-onUiUpdate(function(){
+    let text = element.textContent;
-	gradioApp().querySelectorAll('span, button, select, p').forEach(function(span){
+    let tooltip = localization[titles[text]] || titles[text];
-		if (span.title) return;  // already has a title
 
-		let tooltip = localization[titles[span.textContent]] || titles[span.textContent];
+    if (!tooltip) {
-
+        let value = element.value;
-    if(!tooltip){
+        if (value) tooltip = localization[titles[value]] || titles[value];
-		    tooltip = localization[titles[span.value]] || titles[span.value];
     }
 
-		if(!tooltip){
+    if (!tooltip) {
-			for (const c of span.classList) {
+        // Gradio dropdown options have `data-value`.
+        let dataValue = element.dataset.value;
+        if (dataValue) tooltip = localization[titles[dataValue]] || titles[dataValue];
+    }
+
+    if (!tooltip) {
+        for (const c of element.classList) {
             if (c in titles) {
                 tooltip = localization[titles[c]] || titles[c];
                 break;
@@ -135,16 +142,54 @@ onUiUpdate(function(){
         }
     }
 
-		if(tooltip){
+    if (tooltip) {
-			span.title = tooltip;
+        element.title = tooltip;
     }
-	})
+}
 
-	gradioApp().querySelectorAll('select').forEach(function(select){
+// Nodes to check for adding tooltips.
-	    if (select.onchange != null) return;
+const tooltipCheckNodes = new Set();
+// Timer for debouncing tooltip check.
+let tooltipCheckTimer = null;
 
-	    select.onchange = function(){
+function processTooltipCheckNodes() {
-            select.title = localization[titles[select.value]] || titles[select.value] || "";
+    for (const node of tooltipCheckNodes) {
+        updateTooltip(node);
     }
-	})
+    tooltipCheckNodes.clear();
-})
+}
+
+onUiUpdate(function(mutationRecords) {
+    for (const record of mutationRecords) {
+        if (record.type === "childList" && record.target.classList.contains("options")) {
+            // This smells like a Gradio dropdown menu having changed,
+            // so let's enqueue an update for the input element that shows the current value.
+            let wrap = record.target.parentNode;
+            let input = wrap?.querySelector("input");
+            if (input) {
+                input.title = ""; // So we'll even have a chance to update it.
+                tooltipCheckNodes.add(input);
+            }
+        }
+        for (const node of record.addedNodes) {
+            if (node.nodeType === Node.ELEMENT_NODE && !node.classList.contains("hide")) {
+                if (!node.title) {
+                    if (
+                        node.tagName === "SPAN" ||
+                        node.tagName === "BUTTON" ||
+                        node.tagName === "P" ||
+                        node.tagName === "INPUT" ||
+                        (node.tagName === "LI" && node.classList.contains("item")) // Gradio dropdown item
+                    ) {
+                        tooltipCheckNodes.add(node);
+                    }
+                }
+                node.querySelectorAll('span, button, p').forEach(n => tooltipCheckNodes.add(n));
+            }
+        }
+    }
+    if (tooltipCheckNodes.size) {
+        clearTimeout(tooltipCheckTimer);
+        tooltipCheckTimer = setTimeout(processTooltipCheckNodes, 1000);
+    }
+});

javascript/hires_fix.js

@@ -1,18 +1,18 @@
 
-function onCalcResolutionHires(enable, width, height, hr_scale, hr_resize_x, hr_resize_y){
+function onCalcResolutionHires(enable, width, height, hr_scale, hr_resize_x, hr_resize_y) {
-    function setInactive(elem, inactive){
+    function setInactive(elem, inactive) {
-        elem.classList.toggle('inactive', !!inactive)
+        elem.classList.toggle('inactive', !!inactive);
     }
 
-    var hrUpscaleBy = gradioApp().getElementById('txt2img_hr_scale')
+    var hrUpscaleBy = gradioApp().getElementById('txt2img_hr_scale');
-    var hrResizeX = gradioApp().getElementById('txt2img_hr_resize_x')
+    var hrResizeX = gradioApp().getElementById('txt2img_hr_resize_x');
-    var hrResizeY = gradioApp().getElementById('txt2img_hr_resize_y')
+    var hrResizeY = gradioApp().getElementById('txt2img_hr_resize_y');
 
-    gradioApp().getElementById('txt2img_hires_fix_row2').style.display = opts.use_old_hires_fix_width_height ? "none" : ""
+    gradioApp().getElementById('txt2img_hires_fix_row2').style.display = opts.use_old_hires_fix_width_height ? "none" : "";
 
-    setInactive(hrUpscaleBy, opts.use_old_hires_fix_width_height || hr_resize_x > 0 || hr_resize_y > 0)
+    setInactive(hrUpscaleBy, opts.use_old_hires_fix_width_height || hr_resize_x > 0 || hr_resize_y > 0);
-    setInactive(hrResizeX, opts.use_old_hires_fix_width_height || hr_resize_x == 0)
+    setInactive(hrResizeX, opts.use_old_hires_fix_width_height || hr_resize_x == 0);
-    setInactive(hrResizeY, opts.use_old_hires_fix_width_height || hr_resize_y == 0)
+    setInactive(hrResizeY, opts.use_old_hires_fix_width_height || hr_resize_y == 0);
 
-    return [enable, width, height, hr_scale, hr_resize_x, hr_resize_y]
+    return [enable, width, height, hr_scale, hr_resize_x, hr_resize_y];
 }

javascript/imageMaskFix.js

@@ -4,17 +4,16 @@
  */
 function imageMaskResize() {
     const canvases = gradioApp().querySelectorAll('#img2maskimg .touch-none canvas');
-    if ( ! canvases.length ) {
+    if (!canvases.length) {
-    canvases_fixed = false; // TODO: this is unused..?
+        window.removeEventListener('resize', imageMaskResize);
-    window.removeEventListener( 'resize', imageMaskResize );
         return;
     }
 
     const wrapper = canvases[0].closest('.touch-none');
     const previewImage = wrapper.previousElementSibling;
 
-    if ( ! previewImage.complete ) {
+    if (!previewImage.complete) {
-        previewImage.addEventListener( 'load', imageMaskResize);
+        previewImage.addEventListener('load', imageMaskResize);
         return;
     }
 
@@ -24,15 +23,15 @@ function imageMaskResize() {
     const nh = previewImage.naturalHeight;
     const portrait = nh > nw;
 
-    const wW = Math.min(w, portrait ? h/nh*nw : w/nw*nw);
+    const wW = Math.min(w, portrait ? h / nh * nw : w / nw * nw);
-    const wH = Math.min(h, portrait ? h/nh*nh : w/nw*nh);
+    const wH = Math.min(h, portrait ? h / nh * nh : w / nw * nh);
 
     wrapper.style.width = `${wW}px`;
     wrapper.style.height = `${wH}px`;
     wrapper.style.left = `0px`;
     wrapper.style.top = `0px`;
 
-    canvases.forEach( c => {
+    canvases.forEach(c => {
         c.style.width = c.style.height = '';
         c.style.maxWidth = '100%';
         c.style.maxHeight = '100%';
@@ -40,5 +39,5 @@ function imageMaskResize() {
     });
 }
 
-onUiUpdate(imageMaskResize);
+onAfterUiUpdate(imageMaskResize);
-window.addEventListener( 'resize', imageMaskResize);
+window.addEventListener('resize', imageMaskResize);

javascript/imageParams.js

@@ -1,18 +0,0 @@
-window.onload = (function(){
-    window.addEventListener('drop', e => {
-        const target = e.composedPath()[0];
-        if (target.placeholder.indexOf("Prompt") == -1) return;
-
-        let prompt_target = get_tab_index('tabs') == 1 ? "img2img_prompt_image" : "txt2img_prompt_image";
-
-        e.stopPropagation();
-        e.preventDefault();
-        const imgParent = gradioApp().getElementById(prompt_target);
-        const files = e.dataTransfer.files;
-        const fileInput = imgParent.querySelector('input[type="file"]');
-        if ( fileInput ) {
-            fileInput.files = files;
-            fileInput.dispatchEvent(new Event('change'));
-        }
-    });
-});

javascript/imageviewer.js

@@ -5,24 +5,24 @@ function closeModal() {
 
 function showModal(event) {
     const source = event.target || event.srcElement;
-    const modalImage = gradioApp().getElementById("modalImage")
+    const modalImage = gradioApp().getElementById("modalImage");
-    const lb = gradioApp().getElementById("lightboxModal")
+    const lb = gradioApp().getElementById("lightboxModal");
-    modalImage.src = source.src
+    modalImage.src = source.src;
     if (modalImage.style.display === 'none') {
         lb.style.setProperty('background-image', 'url(' + source.src + ')');
     }
     lb.style.display = "flex";
-    lb.focus()
+    lb.focus();
 
-    const tabTxt2Img = gradioApp().getElementById("tab_txt2img")
+    const tabTxt2Img = gradioApp().getElementById("tab_txt2img");
-    const tabImg2Img = gradioApp().getElementById("tab_img2img")
+    const tabImg2Img = gradioApp().getElementById("tab_img2img");
     // show the save button in modal only on txt2img or img2img tabs
     if (tabTxt2Img.style.display != "none" || tabImg2Img.style.display != "none") {
-        gradioApp().getElementById("modal_save").style.display = "inline"
+        gradioApp().getElementById("modal_save").style.display = "inline";
     } else {
-        gradioApp().getElementById("modal_save").style.display = "none"
+        gradioApp().getElementById("modal_save").style.display = "none";
     }
-    event.stopPropagation()
+    event.stopPropagation();
 }
 
 function negmod(n, m) {
@@ -30,14 +30,15 @@ function negmod(n, m) {
 }
 
 function updateOnBackgroundChange() {
-    const modalImage = gradioApp().getElementById("modalImage")
+    const modalImage = gradioApp().getElementById("modalImage");
     if (modalImage && modalImage.offsetParent) {
         let currentButton = selected_gallery_button();
 
         if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
             modalImage.src = currentButton.children[0].src;
             if (modalImage.style.display === 'none') {
-                modal.style.setProperty('background-image', `url(${modalImage.src})`)
+                const modal = gradioApp().getElementById("lightboxModal");
+                modal.style.setProperty('background-image', `url(${modalImage.src})`);
             }
         }
     }
@@ -49,68 +50,68 @@ function modalImageSwitch(offset) {
     if (galleryButtons.length > 1) {
         var currentButton = selected_gallery_button();
 
-        var result = -1
+        var result = -1;
         galleryButtons.forEach(function(v, i) {
             if (v == currentButton) {
-                result = i
+                result = i;
             }
-        })
+        });
 
         if (result != -1) {
-            var nextButton = galleryButtons[negmod((result + offset), galleryButtons.length)]
+            var nextButton = galleryButtons[negmod((result + offset), galleryButtons.length)];
-            nextButton.click()
+            nextButton.click();
             const modalImage = gradioApp().getElementById("modalImage");
             const modal = gradioApp().getElementById("lightboxModal");
             modalImage.src = nextButton.children[0].src;
             if (modalImage.style.display === 'none') {
-                modal.style.setProperty('background-image', `url(${modalImage.src})`)
+                modal.style.setProperty('background-image', `url(${modalImage.src})`);
             }
             setTimeout(function() {
-                modal.focus()
+                modal.focus();
-            }, 10)
+            }, 10);
         }
     }
 }
 
-function saveImage(){
+function saveImage() {
-    const tabTxt2Img = gradioApp().getElementById("tab_txt2img")
+    const tabTxt2Img = gradioApp().getElementById("tab_txt2img");
-    const tabImg2Img = gradioApp().getElementById("tab_img2img")
+    const tabImg2Img = gradioApp().getElementById("tab_img2img");
-    const saveTxt2Img = "save_txt2img"
+    const saveTxt2Img = "save_txt2img";
-    const saveImg2Img = "save_img2img"
+    const saveImg2Img = "save_img2img";
     if (tabTxt2Img.style.display != "none") {
-        gradioApp().getElementById(saveTxt2Img).click()
+        gradioApp().getElementById(saveTxt2Img).click();
     } else if (tabImg2Img.style.display != "none") {
-        gradioApp().getElementById(saveImg2Img).click()
+        gradioApp().getElementById(saveImg2Img).click();
     } else {
-        console.error("missing implementation for saving modal of this type")
+        console.error("missing implementation for saving modal of this type");
     }
 }
 
 function modalSaveImage(event) {
-    saveImage()
+    saveImage();
-    event.stopPropagation()
+    event.stopPropagation();
 }
 
 function modalNextImage(event) {
-    modalImageSwitch(1)
+    modalImageSwitch(1);
-    event.stopPropagation()
+    event.stopPropagation();
 }
 
 function modalPrevImage(event) {
-    modalImageSwitch(-1)
+    modalImageSwitch(-1);
-    event.stopPropagation()
+    event.stopPropagation();
 }
 
 function modalKeyHandler(event) {
     switch (event.key) {
     case "s":
-            saveImage()
+        saveImage();
         break;
     case "ArrowLeft":
-            modalPrevImage(event)
+        modalPrevImage(event);
         break;
     case "ArrowRight":
-            modalNextImage(event)
+        modalNextImage(event);
         break;
     case "Escape":
         closeModal();
@@ -119,38 +120,39 @@ function modalKeyHandler(event) {
 }
 
 function setupImageForLightbox(e) {
-	if (e.dataset.modded)
+    if (e.dataset.modded) {
         return;
+    }
 
     e.dataset.modded = true;
-	e.style.cursor='pointer'
+    e.style.cursor = 'pointer';
-	e.style.userSelect='none'
+    e.style.userSelect = 'none';
 
-	var isFirefox = navigator.userAgent.toLowerCase().indexOf('firefox') > -1
+    var isFirefox = navigator.userAgent.toLowerCase().indexOf('firefox') > -1;
 
     // For Firefox, listening on click first switched to next image then shows the lightbox.
     // If you know how to fix this without switching to mousedown event, please.
     // For other browsers the event is click to make it possiblr to drag picture.
-	var event = isFirefox ? 'mousedown' : 'click'
+    var event = isFirefox ? 'mousedown' : 'click';
 
-	e.addEventListener(event, function (evt) {
+    e.addEventListener(event, function(evt) {
-		if(!opts.js_modal_lightbox || evt.button != 0) return;
+        if (!opts.js_modal_lightbox || evt.button != 0) return;
 
-		modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed)
+        modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed);
-		evt.preventDefault()
+        evt.preventDefault();
-		showModal(evt)
+        showModal(evt);
     }, true);
 
 }
 
 function modalZoomSet(modalImage, enable) {
-    if(modalImage) modalImage.classList.toggle('modalImageFullscreen', !!enable);
+    if (modalImage) modalImage.classList.toggle('modalImageFullscreen', !!enable);
 }
 
 function modalZoomToggle(event) {
     var modalImage = gradioApp().getElementById("modalImage");
-    modalZoomSet(modalImage, !modalImage.classList.contains('modalImageFullscreen'))
+    modalZoomSet(modalImage, !modalImage.classList.contains('modalImageFullscreen'));
-    event.stopPropagation()
+    event.stopPropagation();
 }
 
 function modalTileImageToggle(event) {
@@ -159,93 +161,87 @@ function modalTileImageToggle(event) {
     const isTiling = modalImage.style.display === 'none';
     if (isTiling) {
         modalImage.style.display = 'block';
-        modal.style.setProperty('background-image', 'none')
+        modal.style.setProperty('background-image', 'none');
     } else {
         modalImage.style.display = 'none';
-        modal.style.setProperty('background-image', `url(${modalImage.src})`)
+        modal.style.setProperty('background-image', `url(${modalImage.src})`);
     }
 
-    event.stopPropagation()
+    event.stopPropagation();
 }
 
-function galleryImageHandler(e) {
+onAfterUiUpdate(function() {
-    //if (e && e.parentElement.tagName == 'BUTTON') {
+    var fullImg_preview = gradioApp().querySelectorAll('.gradio-gallery > div > img');
-        e.onclick = showGalleryImage;
-    //}
-}
-
-onUiUpdate(function() {
-    var fullImg_preview = gradioApp().querySelectorAll('.gradio-gallery > div > img')
     if (fullImg_preview != null) {
         fullImg_preview.forEach(setupImageForLightbox);
     }
     updateOnBackgroundChange();
-})
+});
 
 document.addEventListener("DOMContentLoaded", function() {
     //const modalFragment = document.createDocumentFragment();
-    const modal = document.createElement('div')
+    const modal = document.createElement('div');
     modal.onclick = closeModal;
     modal.id = "lightboxModal";
-    modal.tabIndex = 0
+    modal.tabIndex = 0;
-    modal.addEventListener('keydown', modalKeyHandler, true)
+    modal.addEventListener('keydown', modalKeyHandler, true);
 
-    const modalControls = document.createElement('div')
+    const modalControls = document.createElement('div');
     modalControls.className = 'modalControls gradio-container';
     modal.append(modalControls);
 
-    const modalZoom = document.createElement('span')
+    const modalZoom = document.createElement('span');
     modalZoom.className = 'modalZoom cursor';
-    modalZoom.innerHTML = '⤡'
+    modalZoom.innerHTML = '⤡';
-    modalZoom.addEventListener('click', modalZoomToggle, true)
+    modalZoom.addEventListener('click', modalZoomToggle, true);
     modalZoom.title = "Toggle zoomed view";
-    modalControls.appendChild(modalZoom)
+    modalControls.appendChild(modalZoom);
 
-    const modalTileImage = document.createElement('span')
+    const modalTileImage = document.createElement('span');
     modalTileImage.className = 'modalTileImage cursor';
-    modalTileImage.innerHTML = '⊞'
+    modalTileImage.innerHTML = '⊞';
-    modalTileImage.addEventListener('click', modalTileImageToggle, true)
+    modalTileImage.addEventListener('click', modalTileImageToggle, true);
     modalTileImage.title = "Preview tiling";
-    modalControls.appendChild(modalTileImage)
+    modalControls.appendChild(modalTileImage);
 
-    const modalSave = document.createElement("span")
+    const modalSave = document.createElement("span");
-    modalSave.className = "modalSave cursor"
+    modalSave.className = "modalSave cursor";
-    modalSave.id = "modal_save"
+    modalSave.id = "modal_save";
-    modalSave.innerHTML = "🖫"
+    modalSave.innerHTML = "🖫";
-    modalSave.addEventListener("click", modalSaveImage, true)
+    modalSave.addEventListener("click", modalSaveImage, true);
-    modalSave.title = "Save Image(s)"
+    modalSave.title = "Save Image(s)";
-    modalControls.appendChild(modalSave)
+    modalControls.appendChild(modalSave);
 
-    const modalClose = document.createElement('span')
+    const modalClose = document.createElement('span');
     modalClose.className = 'modalClose cursor';
-    modalClose.innerHTML = '×'
+    modalClose.innerHTML = '×';
     modalClose.onclick = closeModal;
     modalClose.title = "Close image viewer";
-    modalControls.appendChild(modalClose)
+    modalControls.appendChild(modalClose);
 
-    const modalImage = document.createElement('img')
+    const modalImage = document.createElement('img');
     modalImage.id = 'modalImage';
     modalImage.onclick = closeModal;
-    modalImage.tabIndex = 0
+    modalImage.tabIndex = 0;
-    modalImage.addEventListener('keydown', modalKeyHandler, true)
+    modalImage.addEventListener('keydown', modalKeyHandler, true);
-    modal.appendChild(modalImage)
+    modal.appendChild(modalImage);
 
-    const modalPrev = document.createElement('a')
+    const modalPrev = document.createElement('a');
     modalPrev.className = 'modalPrev';
-    modalPrev.innerHTML = '❮'
+    modalPrev.innerHTML = '❮';
-    modalPrev.tabIndex = 0
+    modalPrev.tabIndex = 0;
     modalPrev.addEventListener('click', modalPrevImage, true);
-    modalPrev.addEventListener('keydown', modalKeyHandler, true)
+    modalPrev.addEventListener('keydown', modalKeyHandler, true);
-    modal.appendChild(modalPrev)
+    modal.appendChild(modalPrev);
 
-    const modalNext = document.createElement('a')
+    const modalNext = document.createElement('a');
     modalNext.className = 'modalNext';
-    modalNext.innerHTML = '❯'
+    modalNext.innerHTML = '❯';
-    modalNext.tabIndex = 0
+    modalNext.tabIndex = 0;
     modalNext.addEventListener('click', modalNextImage, true);
-    modalNext.addEventListener('keydown', modalKeyHandler, true)
+    modalNext.addEventListener('keydown', modalKeyHandler, true);
 
-    modal.appendChild(modalNext)
+    modal.appendChild(modalNext);
 
     try {
         gradioApp().appendChild(modal);

javascript/imageviewerGamepad.js

@@ -1,7 +1,9 @@
+let gamepads = [];
+
 window.addEventListener('gamepadconnected', (e) => {
     const index = e.gamepad.index;
     let isWaiting = false;
-    setInterval(async () => {
+    gamepads[index] = setInterval(async() => {
         if (!opts.js_modal_lightbox_gamepad || isWaiting) return;
         const gamepad = navigator.getGamepads()[index];
         const xValue = gamepad.axes[0];
@@ -14,7 +16,7 @@ window.addEventListener('gamepadconnected', (e) => {
         }
         if (isWaiting) {
             await sleepUntil(() => {
-                const xValue = navigator.getGamepads()[index].axes[0]
+                const xValue = navigator.getGamepads()[index].axes[0];
                 if (xValue < 0.3 && xValue > -0.3) {
                     return true;
                 }
@@ -24,6 +26,10 @@ window.addEventListener('gamepadconnected', (e) => {
     }, 10);
 });
 
+window.addEventListener('gamepaddisconnected', (e) => {
+    clearInterval(gamepads[e.gamepad.index]);
+});
+
 /*
 Primarily for vr controller type pointer devices.
 I use the wheel event because there's currently no way to do it properly with web xr.

javascript/localization.js

@@ -1,10 +1,9 @@
 
 // localization = {} -- the dict with translations is created by the backend
 
-ignore_ids_for_localization={
+var ignore_ids_for_localization = {
     setting_sd_hypernetwork: 'OPTION',
     setting_sd_model_checkpoint: 'OPTION',
-    setting_realesrgan_enabled_models: 'OPTION',
     modelmerger_primary_model_name: 'OPTION',
     modelmerger_secondary_model_name: 'OPTION',
     modelmerger_tertiary_model_name: 'OPTION',
@@ -17,111 +16,111 @@ ignore_ids_for_localization={
     setting_realesrgan_enabled_models: 'SPAN',
     extras_upscaler_1: 'SPAN',
     extras_upscaler_2: 'SPAN',
-}
+};
 
-re_num = /^[\.\d]+$/
+var re_num = /^[.\d]+$/;
-re_emoji = /[\p{Extended_Pictographic}\u{1F3FB}-\u{1F3FF}\u{1F9B0}-\u{1F9B3}]/u
+var re_emoji = /[\p{Extended_Pictographic}\u{1F3FB}-\u{1F3FF}\u{1F9B0}-\u{1F9B3}]/u;
 
-original_lines = {}
+var original_lines = {};
-translated_lines = {}
+var translated_lines = {};
 
 function hasLocalization() {
     return window.localization && Object.keys(window.localization).length > 0;
 }
 
-function textNodesUnder(el){
+function textNodesUnder(el) {
-    var n, a=[], walk=document.createTreeWalker(el,NodeFilter.SHOW_TEXT,null,false);
+    var n, a = [], walk = document.createTreeWalker(el, NodeFilter.SHOW_TEXT, null, false);
-    while(n=walk.nextNode()) a.push(n);
+    while ((n = walk.nextNode())) a.push(n);
     return a;
 }
 
-function canBeTranslated(node, text){
+function canBeTranslated(node, text) {
-    if(! text) return false;
+    if (!text) return false;
-    if(! node.parentElement) return false;
+    if (!node.parentElement) return false;
 
-    var parentType = node.parentElement.nodeName
+    var parentType = node.parentElement.nodeName;
-    if(parentType=='SCRIPT' || parentType=='STYLE' || parentType=='TEXTAREA') return false;
+    if (parentType == 'SCRIPT' || parentType == 'STYLE' || parentType == 'TEXTAREA') return false;
 
-    if (parentType=='OPTION' || parentType=='SPAN'){
+    if (parentType == 'OPTION' || parentType == 'SPAN') {
-        var pnode = node
+        var pnode = node;
-        for(var level=0; level<4; level++){
+        for (var level = 0; level < 4; level++) {
-            pnode = pnode.parentElement
+            pnode = pnode.parentElement;
-            if(! pnode) break;
+            if (!pnode) break;
 
-            if(ignore_ids_for_localization[pnode.id] == parentType) return false;
+            if (ignore_ids_for_localization[pnode.id] == parentType) return false;
         }
     }
 
-    if(re_num.test(text)) return false;
+    if (re_num.test(text)) return false;
-    if(re_emoji.test(text)) return false;
+    if (re_emoji.test(text)) return false;
-    return true
+    return true;
 }
 
-function getTranslation(text){
+function getTranslation(text) {
-    if(! text) return undefined
+    if (!text) return undefined;
 
-    if(translated_lines[text] === undefined){
+    if (translated_lines[text] === undefined) {
-        original_lines[text] = 1
+        original_lines[text] = 1;
     }
 
-    tl = localization[text]
+    var tl = localization[text];
-    if(tl !== undefined){
+    if (tl !== undefined) {
-        translated_lines[tl] = 1
+        translated_lines[tl] = 1;
     }
 
-    return tl
+    return tl;
 }
 
-function processTextNode(node){
+function processTextNode(node) {
-    var text = node.textContent.trim()
+    var text = node.textContent.trim();
 
-    if(! canBeTranslated(node, text)) return
+    if (!canBeTranslated(node, text)) return;
 
-    tl = getTranslation(text)
+    var tl = getTranslation(text);
-    if(tl !== undefined){
+    if (tl !== undefined) {
-        node.textContent = tl
+        node.textContent = tl;
     }
 }
 
-function processNode(node){
+function processNode(node) {
-    if(node.nodeType == 3){
+    if (node.nodeType == 3) {
-        processTextNode(node)
+        processTextNode(node);
-        return
+        return;
     }
 
-    if(node.title){
+    if (node.title) {
-        tl = getTranslation(node.title)
+        let tl = getTranslation(node.title);
-        if(tl !== undefined){
+        if (tl !== undefined) {
-            node.title = tl
+            node.title = tl;
         }
     }
 
-    if(node.placeholder){
+    if (node.placeholder) {
-        tl = getTranslation(node.placeholder)
+        let tl = getTranslation(node.placeholder);
-        if(tl !== undefined){
+        if (tl !== undefined) {
-            node.placeholder = tl
+            node.placeholder = tl;
         }
     }
 
-    textNodesUnder(node).forEach(function(node){
+    textNodesUnder(node).forEach(function(node) {
-        processTextNode(node)
+        processTextNode(node);
-    })
+    });
 }
 
-function dumpTranslations(){
+function dumpTranslations() {
-    if(!hasLocalization()) {
+    if (!hasLocalization()) {
         // If we don't have any localization,
         // we will not have traversed the app to find
         // original_lines, so do that now.
         processNode(gradioApp());
     }
-    var dumped = {}
+    var dumped = {};
     if (localization.rtl) {
         dumped.rtl = true;
     }
 
     for (const text in original_lines) {
-        if(dumped[text] !== undefined) continue;
+        if (dumped[text] !== undefined) continue;
         dumped[text] = localization[text] || text;
     }
 
@@ -129,7 +128,7 @@ function dumpTranslations(){
 }
 
 function download_localization() {
-    var text = JSON.stringify(dumpTranslations(), null, 4)
+    var text = JSON.stringify(dumpTranslations(), null, 4);
 
     var element = document.createElement('a');
     element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(text));
@@ -142,20 +141,20 @@ function download_localization() {
     document.body.removeChild(element);
 }
 
-document.addEventListener("DOMContentLoaded", function () {
+document.addEventListener("DOMContentLoaded", function() {
     if (!hasLocalization()) {
         return;
     }
 
-    onUiUpdate(function (m) {
+    onUiUpdate(function(m) {
-        m.forEach(function (mutation) {
+        m.forEach(function(mutation) {
-            mutation.addedNodes.forEach(function (node) {
+            mutation.addedNodes.forEach(function(node) {
-                processNode(node)
+                processNode(node);
-            })
+            });
+        });
     });
-    })
 
-    processNode(gradioApp())
+    processNode(gradioApp());
 
     if (localization.rtl) { // if the language is from right to left,
         (new MutationObserver((mutations, observer) => { // wait for the style to load
@@ -170,8 +169,8 @@ document.addEventListener("DOMContentLoaded", function () {
                             }
                         }
                     }
-                })
                 });
-        })).observe(gradioApp(), { childList: true });
+            });
+        })).observe(gradioApp(), {childList: true});
     }
-})
+});

javascript/notification.js

@@ -4,14 +4,14 @@ let lastHeadImg = null;
 
 let notificationButton = null;
 
-onUiUpdate(function(){
+onAfterUiUpdate(function() {
-    if(notificationButton == null){
+    if (notificationButton == null) {
-        notificationButton = gradioApp().getElementById('request_notifications')
+        notificationButton = gradioApp().getElementById('request_notifications');
 
-        if(notificationButton != null){
+        if (notificationButton != null) {
             notificationButton.addEventListener('click', () => {
                 void Notification.requestPermission();
-            },true);
+            }, true);
         }
     }
 
@@ -42,7 +42,7 @@ onUiUpdate(function(){
         }
     );
 
-    notification.onclick = function(_){
+    notification.onclick = function(_) {
         parent.focus();
         this.close();
     };

javascript/profilerVisualization.js

@@ -0,0 +1,153 @@
+
+function createRow(table, cellName, items) {
+    var tr = document.createElement('tr');
+    var res = [];
+
+    items.forEach(function(x, i) {
+        if (x === undefined) {
+            res.push(null);
+            return;
+        }
+
+        var td = document.createElement(cellName);
+        td.textContent = x;
+        tr.appendChild(td);
+        res.push(td);
+
+        var colspan = 1;
+        for (var n = i + 1; n < items.length; n++) {
+            if (items[n] !== undefined) {
+                break;
+            }
+
+            colspan += 1;
+        }
+
+        if (colspan > 1) {
+            td.colSpan = colspan;
+        }
+    });
+
+    table.appendChild(tr);
+
+    return res;
+}
+
+function showProfile(path, cutoff = 0.05) {
+    requestGet(path, {}, function(data) {
+        var table = document.createElement('table');
+        table.className = 'popup-table';
+
+        data.records['total'] = data.total;
+        var keys = Object.keys(data.records).sort(function(a, b) {
+            return data.records[b] - data.records[a];
+        });
+        var items = keys.map(function(x) {
+            return {key: x, parts: x.split('/'), time: data.records[x]};
+        });
+        var maxLength = items.reduce(function(a, b) {
+            return Math.max(a, b.parts.length);
+        }, 0);
+
+        var cols = createRow(table, 'th', ['record', 'seconds']);
+        cols[0].colSpan = maxLength;
+
+        function arraysEqual(a, b) {
+            return !(a < b || b < a);
+        }
+
+        var addLevel = function(level, parent, hide) {
+            var matching = items.filter(function(x) {
+                return x.parts[level] && !x.parts[level + 1] && arraysEqual(x.parts.slice(0, level), parent);
+            });
+            var sorted = matching.sort(function(a, b) {
+                return b.time - a.time;
+            });
+            var othersTime = 0;
+            var othersList = [];
+            var othersRows = [];
+            var childrenRows = [];
+            sorted.forEach(function(x) {
+                var visible = x.time >= cutoff && !hide;
+
+                var cells = [];
+                for (var i = 0; i < maxLength; i++) {
+                    cells.push(x.parts[i]);
+                }
+                cells.push(x.time.toFixed(3));
+                var cols = createRow(table, 'td', cells);
+                for (i = 0; i < level; i++) {
+                    cols[i].className = 'muted';
+                }
+
+                var tr = cols[0].parentNode;
+                if (!visible) {
+                    tr.classList.add("hidden");
+                }
+
+                if (x.time >= cutoff) {
+                    childrenRows.push(tr);
+                } else {
+                    othersTime += x.time;
+                    othersList.push(x.parts[level]);
+                    othersRows.push(tr);
+                }
+
+                var children = addLevel(level + 1, parent.concat([x.parts[level]]), true);
+                if (children.length > 0) {
+                    var cell = cols[level];
+                    var onclick = function() {
+                        cell.classList.remove("link");
+                        cell.removeEventListener("click", onclick);
+                        children.forEach(function(x) {
+                            x.classList.remove("hidden");
+                        });
+                    };
+                    cell.classList.add("link");
+                    cell.addEventListener("click", onclick);
+                }
+            });
+
+            if (othersTime > 0) {
+                var cells = [];
+                for (var i = 0; i < maxLength; i++) {
+                    cells.push(parent[i]);
+                }
+                cells.push(othersTime.toFixed(3));
+                cells[level] = 'others';
+                var cols = createRow(table, 'td', cells);
+                for (i = 0; i < level; i++) {
+                    cols[i].className = 'muted';
+                }
+
+                var cell = cols[level];
+                var tr = cell.parentNode;
+                var onclick = function() {
+                    tr.classList.add("hidden");
+                    cell.classList.remove("link");
+                    cell.removeEventListener("click", onclick);
+                    othersRows.forEach(function(x) {
+                        x.classList.remove("hidden");
+                    });
+                };
+
+                cell.title = othersList.join(", ");
+                cell.classList.add("link");
+                cell.addEventListener("click", onclick);
+
+                if (hide) {
+                    tr.classList.add("hidden");
+                }
+
+                childrenRows.push(tr);
+            }
+
+            return childrenRows;
+        };
+
+        addLevel(0, []);
+
+        popup(table);
+    });
+}
+

javascript/progressbar.js

@@ -1,29 +1,29 @@
 // code related to showing and updating progressbar shown as the image is being made
 
-function rememberGallerySelection(){
+function rememberGallerySelection() {
 
 }
 
-function getGallerySelectedIndex(){
+function getGallerySelectedIndex() {
 
 }
 
-function request(url, data, handler, errorHandler){
+function request(url, data, handler, errorHandler) {
     var xhr = new XMLHttpRequest();
     xhr.open("POST", url, true);
     xhr.setRequestHeader("Content-Type", "application/json");
-    xhr.onreadystatechange = function () {
+    xhr.onreadystatechange = function() {
         if (xhr.readyState === 4) {
             if (xhr.status === 200) {
                 try {
                     var js = JSON.parse(xhr.responseText);
-                    handler(js)
+                    handler(js);
                 } catch (error) {
                     console.error(error);
-                    errorHandler()
+                    errorHandler();
                 }
-            } else{
+            } else {
-                errorHandler()
+                errorHandler();
             }
         }
     };
@@ -31,147 +31,147 @@ function request(url, data, handler, errorHandler){
     xhr.send(js);
 }
 
-function pad2(x){
+function pad2(x) {
-    return x<10 ? '0'+x : x
+    return x < 10 ? '0' + x : x;
 }
 
-function formatTime(secs){
+function formatTime(secs) {
-    if(secs > 3600){
+    if (secs > 3600) {
-        return pad2(Math.floor(secs/60/60)) + ":" + pad2(Math.floor(secs/60)%60) + ":" + pad2(Math.floor(secs)%60)
+        return pad2(Math.floor(secs / 60 / 60)) + ":" + pad2(Math.floor(secs / 60) % 60) + ":" + pad2(Math.floor(secs) % 60);
-    } else if(secs > 60){
+    } else if (secs > 60) {
-        return pad2(Math.floor(secs/60)) + ":" + pad2(Math.floor(secs)%60)
+        return pad2(Math.floor(secs / 60)) + ":" + pad2(Math.floor(secs) % 60);
-    } else{
+    } else {
-        return Math.floor(secs) + "s"
+        return Math.floor(secs) + "s";
     }
 }
 
-function setTitle(progress){
+function setTitle(progress) {
-    var title = 'Stable Diffusion'
+    var title = 'Stable Diffusion';
 
-    if(opts.show_progress_in_title && progress){
+    if (opts.show_progress_in_title && progress) {
         title = '[' + progress.trim() + '] ' + title;
     }
 
-    if(document.title != title){
+    if (document.title != title) {
         document.title = title;
     }
 }
 
 
-function randomId(){
+function randomId() {
-    return "task(" + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7)+")"
+    return "task(" + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + ")";
 }
 
 // starts sending progress requests to "/internal/progress" uri, creating progressbar above progressbarContainer element and
 // preview inside gallery element. Cleans up all created stuff when the task is over and calls atEnd.
 // calls onProgress every time there is a progress update
-function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgress, inactivityTimeout=40){
+function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgress, inactivityTimeout = 40) {
-    var dateStart = new Date()
+    var dateStart = new Date();
-    var wasEverActive = false
+    var wasEverActive = false;
-    var parentProgressbar = progressbarContainer.parentNode
+    var parentProgressbar = progressbarContainer.parentNode;
-    var parentGallery = gallery ? gallery.parentNode : null
+    var parentGallery = gallery ? gallery.parentNode : null;
 
-    var divProgress = document.createElement('div')
+    var divProgress = document.createElement('div');
-    divProgress.className='progressDiv'
+    divProgress.className = 'progressDiv';
-    divProgress.style.display = opts.show_progressbar ? "block" : "none"
+    divProgress.style.display = opts.show_progressbar ? "block" : "none";
-    var divInner = document.createElement('div')
+    var divInner = document.createElement('div');
-    divInner.className='progress'
+    divInner.className = 'progress';
 
-    divProgress.appendChild(divInner)
+    divProgress.appendChild(divInner);
-    parentProgressbar.insertBefore(divProgress, progressbarContainer)
+    parentProgressbar.insertBefore(divProgress, progressbarContainer);
 
-    if(parentGallery){
+    if (parentGallery) {
-        var livePreview = document.createElement('div')
+        var livePreview = document.createElement('div');
-        livePreview.className='livePreview'
+        livePreview.className = 'livePreview';
-        parentGallery.insertBefore(livePreview, gallery)
+        parentGallery.insertBefore(livePreview, gallery);
     }
 
-    var removeProgressBar = function(){
+    var removeProgressBar = function() {
-        setTitle("")
+        setTitle("");
-        parentProgressbar.removeChild(divProgress)
+        parentProgressbar.removeChild(divProgress);
-        if(parentGallery) parentGallery.removeChild(livePreview)
+        if (parentGallery) parentGallery.removeChild(livePreview);
-        atEnd()
+        atEnd();
+    };
+
+    var fun = function(id_task, id_live_preview) {
+        request("./internal/progress", {id_task: id_task, id_live_preview: id_live_preview}, function(res) {
+            if (res.completed) {
+                removeProgressBar();
+                return;
             }
 
-    var fun = function(id_task, id_live_preview){
+            var rect = progressbarContainer.getBoundingClientRect();
-        request("./internal/progress", {"id_task": id_task, "id_live_preview": id_live_preview}, function(res){
-            if(res.completed){
-                removeProgressBar()
-                return
-            }
 
-            var rect = progressbarContainer.getBoundingClientRect()
+            if (rect.width) {
-
-            if(rect.width){
                 divProgress.style.width = rect.width + "px";
             }
 
-            let progressText = ""
+            let progressText = "";
 
-            divInner.style.width = ((res.progress || 0) * 100.0) + '%'
+            divInner.style.width = ((res.progress || 0) * 100.0) + '%';
-            divInner.style.background = res.progress ? "" : "transparent"
+            divInner.style.background = res.progress ? "" : "transparent";
 
-            if(res.progress > 0){
+            if (res.progress > 0) {
-                progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%'
+                progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%';
             }
 
-            if(res.eta){
+            if (res.eta) {
-                progressText += " ETA: " + formatTime(res.eta)
+                progressText += " ETA: " + formatTime(res.eta);
             }
 
 
-            setTitle(progressText)
+            setTitle(progressText);
 
-            if(res.textinfo && res.textinfo.indexOf("\n") == -1){
+            if (res.textinfo && res.textinfo.indexOf("\n") == -1) {
-                progressText = res.textinfo + " " + progressText
+                progressText = res.textinfo + " " + progressText;
             }
 
-            divInner.textContent = progressText
+            divInner.textContent = progressText;
 
-            var elapsedFromStart = (new Date() - dateStart) / 1000
+            var elapsedFromStart = (new Date() - dateStart) / 1000;
 
-            if(res.active) wasEverActive = true;
+            if (res.active) wasEverActive = true;
 
-            if(! res.active && wasEverActive){
+            if (!res.active && wasEverActive) {
-                removeProgressBar()
+                removeProgressBar();
-                return
+                return;
             }
 
-            if(elapsedFromStart > inactivityTimeout && !res.queued && !res.active){
+            if (elapsedFromStart > inactivityTimeout && !res.queued && !res.active) {
-                removeProgressBar()
+                removeProgressBar();
-                return
+                return;
             }
 
 
-            if(res.live_preview && gallery){
+            if (res.live_preview && gallery) {
-                var rect = gallery.getBoundingClientRect()
+                rect = gallery.getBoundingClientRect();
-                if(rect.width){
+                if (rect.width) {
-                    livePreview.style.width = rect.width + "px"
+                    livePreview.style.width = rect.width + "px";
-                    livePreview.style.height = rect.height + "px"
+                    livePreview.style.height = rect.height + "px";
                 }
 
                 var img = new Image();
                 img.onload = function() {
-                    livePreview.appendChild(img)
+                    livePreview.appendChild(img);
-                    if(livePreview.childElementCount > 2){
+                    if (livePreview.childElementCount > 2) {
-                        livePreview.removeChild(livePreview.firstElementChild)
+                        livePreview.removeChild(livePreview.firstElementChild);
-                    }
                     }
+                };
                 img.src = res.live_preview;
             }
 
 
-            if(onProgress){
+            if (onProgress) {
-                onProgress(res)
+                onProgress(res);
             }
 
             setTimeout(() => {
                 fun(id_task, res.id_live_preview);
-            }, opts.live_preview_refresh_period || 500)
+            }, opts.live_preview_refresh_period || 500);
-        }, function(){
+        }, function() {
-            removeProgressBar()
+            removeProgressBar();
-        })
+        });
-    }
+    };
 
-    fun(id_task, 0)
+    fun(id_task, 0);
 }

javascript/textualInversion.js

@@ -1,17 +1,17 @@
 
 
 
-function start_training_textual_inversion(){
+function start_training_textual_inversion() {
-    gradioApp().querySelector('#ti_error').innerHTML=''
+    gradioApp().querySelector('#ti_error').innerHTML = '';
 
-    var id = randomId()
+    var id = randomId();
-    requestProgress(id, gradioApp().getElementById('ti_output'), gradioApp().getElementById('ti_gallery'), function(){}, function(progress){
+    requestProgress(id, gradioApp().getElementById('ti_output'), gradioApp().getElementById('ti_gallery'), function() {}, function(progress) {
-        gradioApp().getElementById('ti_progress').innerHTML = progress.textinfo
+        gradioApp().getElementById('ti_progress').innerHTML = progress.textinfo;
-    })
+    });
 
-    var res = args_to_array(arguments)
+    var res = Array.from(arguments);
 
-    res[0] = id
+    res[0] = id;
 
-    return res
+    return res;
 }

javascript/token-counters.js

@@ -0,0 +1,83 @@
+let promptTokenCountDebounceTime = 800;
+let promptTokenCountTimeouts = {};
+var promptTokenCountUpdateFunctions = {};
+
+function update_txt2img_tokens(...args) {
+    // Called from Gradio
+    update_token_counter("txt2img_token_button");
+    if (args.length == 2) {
+        return args[0];
+    }
+    return args;
+}
+
+function update_img2img_tokens(...args) {
+    // Called from Gradio
+    update_token_counter("img2img_token_button");
+    if (args.length == 2) {
+        return args[0];
+    }
+    return args;
+}
+
+function update_token_counter(button_id) {
+    if (opts.disable_token_counters) {
+        return;
+    }
+    if (promptTokenCountTimeouts[button_id]) {
+        clearTimeout(promptTokenCountTimeouts[button_id]);
+    }
+    promptTokenCountTimeouts[button_id] = setTimeout(
+        () => gradioApp().getElementById(button_id)?.click(),
+        promptTokenCountDebounceTime,
+    );
+}
+
+
+function recalculatePromptTokens(name) {
+    promptTokenCountUpdateFunctions[name]?.();
+}
+
+function recalculate_prompts_txt2img() {
+    // Called from Gradio
+    recalculatePromptTokens('txt2img_prompt');
+    recalculatePromptTokens('txt2img_neg_prompt');
+    return Array.from(arguments);
+}
+
+function recalculate_prompts_img2img() {
+    // Called from Gradio
+    recalculatePromptTokens('img2img_prompt');
+    recalculatePromptTokens('img2img_neg_prompt');
+    return Array.from(arguments);
+}
+
+function setupTokenCounting(id, id_counter, id_button) {
+    var prompt = gradioApp().getElementById(id);
+    var counter = gradioApp().getElementById(id_counter);
+    var textarea = gradioApp().querySelector(`#${id} > label > textarea`);
+
+    if (opts.disable_token_counters) {
+        counter.style.display = "none";
+        return;
+    }
+
+    if (counter.parentElement == prompt.parentElement) {
+        return;
+    }
+
+    prompt.parentElement.insertBefore(counter, prompt);
+    prompt.parentElement.style.position = "relative";
+
+    promptTokenCountUpdateFunctions[id] = function() {
+        update_token_counter(id_button);
+    };
+    textarea.addEventListener("input", promptTokenCountUpdateFunctions[id]);
+}
+
+function setupTokenCounters() {
+    setupTokenCounting('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button');
+    setupTokenCounting('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button');
+    setupTokenCounting('img2img_prompt', 'img2img_token_counter', 'img2img_token_button');
+    setupTokenCounting('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button');
+}

javascript/ui.js

@@ -1,7 +1,7 @@
 // various functions for interaction with ui.py not large enough to warrant putting them in separate files
 
-function set_theme(theme){
+function set_theme(theme) {
-    var gradioURL = window.location.href
+    var gradioURL = window.location.href;
     if (!gradioURL.includes('?__theme=')) {
         window.location.replace(gradioURL + '?__theme=' + theme);
     }
@@ -14,7 +14,7 @@ function all_gallery_buttons() {
         if (elem.parentElement.offsetParent) {
             visibleGalleryButtons.push(elem);
         }
-    })
+    });
     return visibleGalleryButtons;
 }
 
@@ -25,31 +25,35 @@ function selected_gallery_button() {
         if (elem.parentElement.offsetParent) {
             visibleCurrentButton = elem;
         }
-    })
+    });
     return visibleCurrentButton;
 }
 
-function selected_gallery_index(){
+function selected_gallery_index() {
     var buttons = all_gallery_buttons();
     var button = selected_gallery_button();
 
-    var result = -1
+    var result = -1;
-    buttons.forEach(function(v, i){ if(v==button) { result = i } })
+    buttons.forEach(function(v, i) {
+        if (v == button) {
+            result = i;
+        }
+    });
 
-    return result
+    return result;
 }
 
-function extract_image_from_gallery(gallery){
+function extract_image_from_gallery(gallery) {
-    if (gallery.length == 0){
+    if (gallery.length == 0) {
         return [null];
     }
-    if (gallery.length == 1){
+    if (gallery.length == 1) {
         return [gallery[0]];
     }
 
-    var index = selected_gallery_index()
+    var index = selected_gallery_index();
 
-    if (index < 0 || index >= gallery.length){
+    if (index < 0 || index >= gallery.length) {
         // Use the first image in the gallery as the default
         index = 0;
     }
@@ -57,249 +61,205 @@ function extract_image_from_gallery(gallery){
     return [gallery[index]];
 }
 
-function args_to_array(args){
+window.args_to_array = Array.from; // Compatibility with e.g. extensions that may expect this to be around
-    var res = []
-    for(var i=0;i<args.length;i++){
-        res.push(args[i])
-    }
-    return res
-}
 
-function switch_to_txt2img(){
+function switch_to_txt2img() {
     gradioApp().querySelector('#tabs').querySelectorAll('button')[0].click();
 
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
-function switch_to_img2img_tab(no){
+function switch_to_img2img_tab(no) {
     gradioApp().querySelector('#tabs').querySelectorAll('button')[1].click();
     gradioApp().getElementById('mode_img2img').querySelectorAll('button')[no].click();
 }
-function switch_to_img2img(){
+function switch_to_img2img() {
     switch_to_img2img_tab(0);
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
-function switch_to_sketch(){
+function switch_to_sketch() {
     switch_to_img2img_tab(1);
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
-function switch_to_inpaint(){
+function switch_to_inpaint() {
     switch_to_img2img_tab(2);
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
-function switch_to_inpaint_sketch(){
+function switch_to_inpaint_sketch() {
     switch_to_img2img_tab(3);
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
-function switch_to_inpaint(){
+function switch_to_extras() {
-    gradioApp().querySelector('#tabs').querySelectorAll('button')[1].click();
-    gradioApp().getElementById('mode_img2img').querySelectorAll('button')[2].click();
-
-    return args_to_array(arguments);
-}
-
-function switch_to_extras(){
     gradioApp().querySelector('#tabs').querySelectorAll('button')[2].click();
 
-    return args_to_array(arguments);
+    return Array.from(arguments);
 }
 
-function get_tab_index(tabId){
+function get_tab_index(tabId) {
-    var res = 0
+    let buttons = gradioApp().getElementById(tabId).querySelector('div').querySelectorAll('button');
-
+    for (let i = 0; i < buttons.length; i++) {
-    gradioApp().getElementById(tabId).querySelector('div').querySelectorAll('button').forEach(function(button, i){
+        if (buttons[i].classList.contains('selected')) {
-        if(button.className.indexOf('selected') != -1)
+            return i;
-            res = i
-    })
-
-    return res
-}
-
-function create_tab_index_args(tabId, args){
-    var res = []
-    for(var i=0; i<args.length; i++){
-        res.push(args[i])
         }
+    }
+    return 0;
+}
 
-    res[0] = get_tab_index(tabId)
+function create_tab_index_args(tabId, args) {
-
+    var res = Array.from(args);
-    return res
+    res[0] = get_tab_index(tabId);
+    return res;
 }
 
 function get_img2img_tab_index() {
-    let res = args_to_array(arguments)
+    let res = Array.from(arguments);
-    res.splice(-2)
+    res.splice(-2);
-    res[0] = get_tab_index('mode_img2img')
+    res[0] = get_tab_index('mode_img2img');
-    return res
+    return res;
 }
 
-function create_submit_args(args){
+function create_submit_args(args) {
-    var res = []
+    var res = Array.from(args);
-    for(var i=0;i<args.length;i++){
-        res.push(args[i])
-    }
 
     // As it is currently, txt2img and img2img send back the previous output args (txt2img_gallery, generation_info, html_info) whenever you generate a new image.
     // This can lead to uploading a huge gallery of previously generated images, which leads to an unnecessary delay between submitting and beginning to generate.
     // I don't know why gradio is sending outputs along with inputs, but we can prevent sending the image gallery here, which seems to be an issue for some.
     // If gradio at some point stops sending outputs, this may break something
-    if(Array.isArray(res[res.length - 3])){
+    if (Array.isArray(res[res.length - 3])) {
-        res[res.length - 3] = null
+        res[res.length - 3] = null;
     }
 
-    return res
+    return res;
 }
 
-function showSubmitButtons(tabname, show){
+function showSubmitButtons(tabname, show) {
-    gradioApp().getElementById(tabname+'_interrupt').style.display = show ? "none" : "block"
+    gradioApp().getElementById(tabname + '_interrupt').style.display = show ? "none" : "block";
-    gradioApp().getElementById(tabname+'_skip').style.display = show ? "none" : "block"
+    gradioApp().getElementById(tabname + '_skip').style.display = show ? "none" : "block";
 }
 
-function showRestoreProgressButton(tabname, show){
+function showRestoreProgressButton(tabname, show) {
-    var button = gradioApp().getElementById(tabname + "_restore_progress")
+    var button = gradioApp().getElementById(tabname + "_restore_progress");
-    if(! button) return
+    if (!button) return;
 
-    button.style.display = show ? "flex" : "none"
+    button.style.display = show ? "flex" : "none";
 }
 
-function submit(){
+function submit() {
-    rememberGallerySelection('txt2img_gallery')
+    showSubmitButtons('txt2img', false);
-    showSubmitButtons('txt2img', false)
 
-    var id = randomId()
+    var id = randomId();
     localStorage.setItem("txt2img_task_id", id);
 
-    requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function(){
+    requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
-        showSubmitButtons('txt2img', true)
+        showSubmitButtons('txt2img', true);
-        localStorage.removeItem("txt2img_task_id")
+        localStorage.removeItem("txt2img_task_id");
-        showRestoreProgressButton('txt2img', false)
+        showRestoreProgressButton('txt2img', false);
-    })
+    });
 
-    var res = create_submit_args(arguments)
+    var res = create_submit_args(arguments);
 
-    res[0] = id
+    res[0] = id;
 
-    return res
+    return res;
 }
 
-function submit_img2img(){
+function submit_img2img() {
-    rememberGallerySelection('img2img_gallery')
+    showSubmitButtons('img2img', false);
-    showSubmitButtons('img2img', false)
 
-    var id = randomId()
+    var id = randomId();
     localStorage.setItem("img2img_task_id", id);
 
-    requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function(){
+    requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
-        showSubmitButtons('img2img', true)
+        showSubmitButtons('img2img', true);
-        localStorage.removeItem("img2img_task_id")
+        localStorage.removeItem("img2img_task_id");
-        showRestoreProgressButton('img2img', false)
+        showRestoreProgressButton('img2img', false);
-    })
+    });
 
-    var res = create_submit_args(arguments)
+    var res = create_submit_args(arguments);
 
-    res[0] = id
+    res[0] = id;
-    res[1] = get_tab_index('mode_img2img')
+    res[1] = get_tab_index('mode_img2img');
 
-    return res
+    return res;
 }
 
-function restoreProgressTxt2img(){
+function restoreProgressTxt2img() {
-    showRestoreProgressButton("txt2img", false)
+    showRestoreProgressButton("txt2img", false);
-    var id = localStorage.getItem("txt2img_task_id")
+    var id = localStorage.getItem("txt2img_task_id");
 
-    id = localStorage.getItem("txt2img_task_id")
+    id = localStorage.getItem("txt2img_task_id");
 
-    if(id) {
+    if (id) {
-        requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function(){
+        requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
-            showSubmitButtons('txt2img', true)
+            showSubmitButtons('txt2img', true);
-        }, null, 0)
+        }, null, 0);
     }
 
-    return id
+    return id;
 }
 
-function restoreProgressImg2img(){
+function restoreProgressImg2img() {
-    showRestoreProgressButton("img2img", false)
+    showRestoreProgressButton("img2img", false);
 
-    var id = localStorage.getItem("img2img_task_id")
+    var id = localStorage.getItem("img2img_task_id");
 
-    if(id) {
+    if (id) {
-        requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function(){
+        requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
-            showSubmitButtons('img2img', true)
+            showSubmitButtons('img2img', true);
-        }, null, 0)
+        }, null, 0);
     }
 
-    return id
+    return id;
 }
 
 
-onUiLoaded(function () {
+onUiLoaded(function() {
-    showRestoreProgressButton('txt2img', localStorage.getItem("txt2img_task_id"))
+    showRestoreProgressButton('txt2img', localStorage.getItem("txt2img_task_id"));
-    showRestoreProgressButton('img2img', localStorage.getItem("img2img_task_id"))
+    showRestoreProgressButton('img2img', localStorage.getItem("img2img_task_id"));
 });
 
 
-function modelmerger(){
+function modelmerger() {
-    var id = randomId()
+    var id = randomId();
-    requestProgress(id, gradioApp().getElementById('modelmerger_results_panel'), null, function(){})
+    requestProgress(id, gradioApp().getElementById('modelmerger_results_panel'), null, function() {});
 
-    var res = create_submit_args(arguments)
+    var res = create_submit_args(arguments);
-    res[0] = id
+    res[0] = id;
-    return res
+    return res;
 }
 
 
 function ask_for_style_name(_, prompt_text, negative_prompt_text) {
-    var name_ = prompt('Style name:')
+    var name_ = prompt('Style name:');
-    return [name_, prompt_text, negative_prompt_text]
+    return [name_, prompt_text, negative_prompt_text];
 }
 
 function confirm_clear_prompt(prompt, negative_prompt) {
-    if(confirm("Delete prompt?")) {
+    if (confirm("Delete prompt?")) {
-        prompt = ""
+        prompt = "";
-        negative_prompt = ""
+        negative_prompt = "";
     }
 
-    return [prompt, negative_prompt]
+    return [prompt, negative_prompt];
 }
 
 
-promptTokecountUpdateFuncs = {}
+var opts = {};
+onAfterUiUpdate(function() {
+    if (Object.keys(opts).length != 0) return;
 
-function recalculatePromptTokens(name){
+    var json_elem = gradioApp().getElementById('settings_json');
-    if(promptTokecountUpdateFuncs[name]){
+    if (json_elem == null) return;
-        promptTokecountUpdateFuncs[name]()
-    }
-}
 
-function recalculate_prompts_txt2img(){
+    var textarea = json_elem.querySelector('textarea');
-    recalculatePromptTokens('txt2img_prompt')
+    var jsdata = textarea.value;
-    recalculatePromptTokens('txt2img_neg_prompt')
+    opts = JSON.parse(jsdata);
-    return args_to_array(arguments);
-}
 
-function recalculate_prompts_img2img(){
+    executeCallbacks(optionsChangedCallbacks); /*global optionsChangedCallbacks*/
-    recalculatePromptTokens('img2img_prompt')
-    recalculatePromptTokens('img2img_neg_prompt')
-    return args_to_array(arguments);
-}
-
-
-var opts = {}
-onUiUpdate(function(){
-	if(Object.keys(opts).length != 0) return;
-
-	var json_elem = gradioApp().getElementById('settings_json')
-	if(json_elem == null) return;
-
-    var textarea = json_elem.querySelector('textarea')
-    var jsdata = textarea.value
-    opts = JSON.parse(jsdata)
-    executeCallbacks(optionsChangedCallbacks);
 
     Object.defineProperty(textarea, 'value', {
         set: function(newValue) {
@@ -308,7 +268,7 @@ onUiUpdate(function(){
             valueProp.set.call(textarea, newValue);
 
             if (oldValue != newValue) {
-                opts = JSON.parse(textarea.value)
+                opts = JSON.parse(textarea.value);
             }
 
             executeCallbacks(optionsChangedCallbacks);
@@ -319,123 +279,109 @@ onUiUpdate(function(){
         }
     });
 
-    json_elem.parentElement.style.display="none"
+    json_elem.parentElement.style.display = "none";
 
-    function registerTextarea(id, id_counter, id_button){
+    setupTokenCounters();
-        var prompt = gradioApp().getElementById(id)
-        var counter = gradioApp().getElementById(id_counter)
-        var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
 
-        if(counter.parentElement == prompt.parentElement){
+    var show_all_pages = gradioApp().getElementById('settings_show_all_pages');
-            return
+    var settings_tabs = gradioApp().querySelector('#settings div');
-        }
+    if (show_all_pages && settings_tabs) {
-
+        settings_tabs.appendChild(show_all_pages);
-        prompt.parentElement.insertBefore(counter, prompt)
+        show_all_pages.onclick = function() {
-        prompt.parentElement.style.position = "relative"
+            gradioApp().querySelectorAll('#settings > div').forEach(function(elem) {
-
+                if (elem.id == "settings_tab_licenses") {
-		promptTokecountUpdateFuncs[id] = function(){ update_token_counter(id_button); }
-		textarea.addEventListener("input", promptTokecountUpdateFuncs[id]);
-    }
-
-    registerTextarea('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button')
-    registerTextarea('txt2img_neg_prompt', 'txt2img_negative_token_counter', 'txt2img_negative_token_button')
-    registerTextarea('img2img_prompt', 'img2img_token_counter', 'img2img_token_button')
-    registerTextarea('img2img_neg_prompt', 'img2img_negative_token_counter', 'img2img_negative_token_button')
-
-    var show_all_pages = gradioApp().getElementById('settings_show_all_pages')
-    var settings_tabs = gradioApp().querySelector('#settings div')
-    if(show_all_pages && settings_tabs){
-        settings_tabs.appendChild(show_all_pages)
-        show_all_pages.onclick = function(){
-            gradioApp().querySelectorAll('#settings > div').forEach(function(elem){
-                if(elem.id == "settings_tab_licenses")
                     return;
+                }
 
                 elem.style.display = "block";
-            })
+            });
+        };
     }
-    }
+});
-})
 
-onOptionsChanged(function(){
+onOptionsChanged(function() {
-    var elem = gradioApp().getElementById('sd_checkpoint_hash')
+    var elem = gradioApp().getElementById('sd_checkpoint_hash');
-    var sd_checkpoint_hash = opts.sd_checkpoint_hash || ""
+    var sd_checkpoint_hash = opts.sd_checkpoint_hash || "";
-    var shorthash = sd_checkpoint_hash.substring(0,10)
+    var shorthash = sd_checkpoint_hash.substring(0, 10);
 
-	if(elem && elem.textContent != shorthash){
+    if (elem && elem.textContent != shorthash) {
-	    elem.textContent = shorthash
+        elem.textContent = shorthash;
-	    elem.title = sd_checkpoint_hash
+        elem.title = sd_checkpoint_hash;
-	    elem.href = "https://google.com/search?q=" + sd_checkpoint_hash
+        elem.href = "https://google.com/search?q=" + sd_checkpoint_hash;
     }
-})
+});
 
 let txt2img_textarea, img2img_textarea = undefined;
-let wait_time = 800
-let token_timeouts = {};
 
-function update_txt2img_tokens(...args) {
+function restart_reload() {
-	update_token_counter("txt2img_token_button")
+    document.body.innerHTML = '<h1 style="font-family:monospace;margin-top:20%;color:lightgray;text-align:center;">Reloading...</h1>';
-	if (args.length == 2)
-		return args[0]
-	return args;
-}
 
-function update_img2img_tokens(...args) {
+    var requestPing = function() {
-	update_token_counter("img2img_token_button")
+        requestGet("./internal/ping", {}, function(data) {
-	if (args.length == 2)
-		return args[0]
-	return args;
-}
-
-function update_token_counter(button_id) {
-	if (token_timeouts[button_id])
-		clearTimeout(token_timeouts[button_id]);
-	token_timeouts[button_id] = setTimeout(() => gradioApp().getElementById(button_id)?.click(), wait_time);
-}
-
-function restart_reload(){
-    document.body.innerHTML='<h1 style="font-family:monospace;margin-top:20%;color:lightgray;text-align:center;">Reloading...</h1>';
-
-    var requestPing = function(){
-        requestGet("./internal/ping", {}, function(data){
             location.reload();
-        }, function(){
+        }, function() {
             setTimeout(requestPing, 500);
-        })
+        });
-    }
+    };
 
     setTimeout(requestPing, 2000);
 
-    return []
+    return [];
 }
 
 // Simulate an `input` DOM event for Gradio Textbox component. Needed after you edit its contents in javascript, otherwise your edits
 // will only visible on web page and not sent to python.
-function updateInput(target){
+function updateInput(target) {
-	let e = new Event("input", { bubbles: true })
+    let e = new Event("input", {bubbles: true});
-	Object.defineProperty(e, "target", {value: target})
+    Object.defineProperty(e, "target", {value: target});
     target.dispatchEvent(e);
 }
 
 
 var desiredCheckpointName = null;
-function selectCheckpoint(name){
+function selectCheckpoint(name) {
     desiredCheckpointName = name;
-    gradioApp().getElementById('change_checkpoint').click()
+    gradioApp().getElementById('change_checkpoint').click();
 }
 
-function currentImg2imgSourceResolution(_, _, scaleBy){
+function currentImg2imgSourceResolution(w, h, scaleBy) {
-    var img = gradioApp().querySelector('#mode_img2img > div[style="display: block;"] img')
+    var img = gradioApp().querySelector('#mode_img2img > div[style="display: block;"] img');
-    return img ? [img.naturalWidth, img.naturalHeight, scaleBy] : [0, 0, scaleBy]
+    return img ? [img.naturalWidth, img.naturalHeight, scaleBy] : [0, 0, scaleBy];
 }
 
-function updateImg2imgResizeToTextAfterChangingImage(){
+function updateImg2imgResizeToTextAfterChangingImage() {
     // At the time this is called from gradio, the image has no yet been replaced.
     // There may be a better solution, but this is simple and straightforward so I'm going with it.
 
     setTimeout(function() {
-        gradioApp().getElementById('img2img_update_resize_to').click()
+        gradioApp().getElementById('img2img_update_resize_to').click();
     }, 500);
 
-    return []
+    return [];
+
+}
+
+
+
+function setRandomSeed(elem_id) {
+    var input = gradioApp().querySelector("#" + elem_id + " input");
+    if (!input) return [];
+
+    input.value = "-1";
+    updateInput(input);
+    return [];
+}
+
+function switchWidthHeight(tabname) {
+    var width = gradioApp().querySelector("#" + tabname + "_width input[type=number]");
+    var height = gradioApp().querySelector("#" + tabname + "_height input[type=number]");
+    if (!width || !height) return [];
+
+    var tmp = width.value;
+    width.value = height.value;
+    height.value = tmp;
+
+    updateInput(width);
+    updateInput(height);
+    return [];
 }

javascript/ui_settings_hints.js

@@ -1,41 +1,62 @@
 // various hints and extra info for the settings tab
 
-onUiLoaded(function(){
+var settingsHintsSetup = false;
-    createLink = function(elem_id, text, href){
-        var a = document.createElement('A')
-        a.textContent = text
-        a.target = '_blank';
 
-        elem = gradioApp().querySelector('#'+elem_id)
+onOptionsChanged(function() {
-        elem.insertBefore(a, elem.querySelector('label'))
+    if (settingsHintsSetup) return;
+    settingsHintsSetup = true;
 
-        return a
+    gradioApp().querySelectorAll('#settings [id^=setting_]').forEach(function(div) {
+        var name = div.id.substr(8);
+        var commentBefore = opts._comments_before[name];
+        var commentAfter = opts._comments_after[name];
+
+        if (!commentBefore && !commentAfter) return;
+
+        var span = null;
+        if (div.classList.contains('gradio-checkbox')) span = div.querySelector('label span');
+        else if (div.classList.contains('gradio-checkboxgroup')) span = div.querySelector('span').firstChild;
+        else if (div.classList.contains('gradio-radio')) span = div.querySelector('span').firstChild;
+        else span = div.querySelector('label span').firstChild;
+
+        if (!span) return;
+
+        if (commentBefore) {
+            var comment = document.createElement('DIV');
+            comment.className = 'settings-comment';
+            comment.innerHTML = commentBefore;
+            span.parentElement.insertBefore(document.createTextNode('\xa0'), span);
+            span.parentElement.insertBefore(comment, span);
+            span.parentElement.insertBefore(document.createTextNode('\xa0'), span);
         }
+        if (commentAfter) {
+            comment = document.createElement('DIV');
+            comment.className = 'settings-comment';
+            comment.innerHTML = commentAfter;
+            span.parentElement.insertBefore(comment, span.nextSibling);
+            span.parentElement.insertBefore(document.createTextNode('\xa0'), span.nextSibling);
+        }
+    });
+});
 
-    createLink("setting_samples_filename_pattern", "[wiki] ").href = "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"
+function settingsHintsShowQuicksettings() {
-    createLink("setting_directories_filename_pattern", "[wiki] ").href = "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"
+    requestGet("./internal/quicksettings-hint", {}, function(data) {
+        var table = document.createElement('table');
+        table.className = 'popup-table';
 
-    createLink("setting_quicksettings_list", "[info] ").addEventListener("click", function(event){
+        data.forEach(function(obj) {
-        requestGet("./internal/quicksettings-hint", {}, function(data){
+            var tr = document.createElement('tr');
-            var table = document.createElement('table')
+            var td = document.createElement('td');
-            table.className = 'settings-value-table'
+            td.textContent = obj.name;
+            tr.appendChild(td);
 
-            data.forEach(function(obj){
+            td = document.createElement('td');
-                var tr = document.createElement('tr')
+            td.textContent = obj.label;
-                var td = document.createElement('td')
+            tr.appendChild(td);
-                td.textContent = obj.name
-                tr.appendChild(td)
 
-                var td = document.createElement('td')
+            table.appendChild(tr);
-                td.textContent = obj.label
+        });
-                tr.appendChild(td)
-
-                table.appendChild(tr)
-            })
 
         popup(table);
-        })
     });
-})
+}
-
-

launch.py

@@ -1,370 +1,38 @@
-# this scripts installs necessary requirements and launches main program in webui.py
+from modules import launch_utils
-import subprocess
-import os
-import sys
-import importlib.util
-import shlex
-import platform
-import json
 
-from modules import cmd_args
-from modules.paths_internal import script_path, extensions_dir
 
-commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
+args = launch_utils.args
-sys.argv += shlex.split(commandline_args)
+python = launch_utils.python
+git = launch_utils.git
+index_url = launch_utils.index_url
+dir_repos = launch_utils.dir_repos
 
-args, _ = cmd_args.parser.parse_known_args()
+commit_hash = launch_utils.commit_hash
+git_tag = launch_utils.git_tag
 
-python = sys.executable
+run = launch_utils.run
-git = os.environ.get('GIT', "git")
+is_installed = launch_utils.is_installed
-index_url = os.environ.get('INDEX_URL', "")
+repo_dir = launch_utils.repo_dir
-stored_commit_hash = None
-stored_git_tag = None
-dir_repos = "repositories"
 
-if 'GRADIO_ANALYTICS_ENABLED' not in os.environ:
+run_pip = launch_utils.run_pip
-    os.environ['GRADIO_ANALYTICS_ENABLED'] = 'False'
+check_run_python = launch_utils.check_run_python
+git_clone = launch_utils.git_clone
+git_pull_recursive = launch_utils.git_pull_recursive
+run_extension_installer = launch_utils.run_extension_installer
+prepare_environment = launch_utils.prepare_environment
+configure_for_tests = launch_utils.configure_for_tests
+start = launch_utils.start
 
 
-def check_python_version():
+def main():
-    is_windows = platform.system() == "Windows"
+    if not args.skip_prepare_environment:
-    major = sys.version_info.major
+        prepare_environment()
-    minor = sys.version_info.minor
-    micro = sys.version_info.micro
 
-    if is_windows:
+    if args.test_server:
-        supported_minors = [10]
+        configure_for_tests()
-    else:
-        supported_minors = [7, 8, 9, 10, 11]
 
-    if not (major == 3 and minor in supported_minors):
+    start()
-        import modules.errors
-
-        modules.errors.print_error_explanation(f"""
-INCOMPATIBLE PYTHON VERSION
-
-This program is tested with 3.10.6 Python, but you have {major}.{minor}.{micro}.
-If you encounter an error with "RuntimeError: Couldn't install torch." message,
-or any other error regarding unsuccessful package (library) installation,
-please downgrade (or upgrade) to the latest version of 3.10 Python
-and delete current Python and "venv" folder in WebUI's directory.
-
-You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
-
-{"Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases" if is_windows else ""}
-
-Use --skip-python-version-check to suppress this warning.
-""")
-
-
-def commit_hash():
-    global stored_commit_hash
-
-    if stored_commit_hash is not None:
-        return stored_commit_hash
-
-    try:
-        stored_commit_hash = run(f"{git} rev-parse HEAD").strip()
-    except Exception:
-        stored_commit_hash = "<none>"
-
-    return stored_commit_hash
-
-
-def git_tag():
-    global stored_git_tag
-
-    if stored_git_tag is not None:
-        return stored_git_tag
-
-    try:
-        stored_git_tag = run(f"{git} describe --tags").strip()
-    except Exception:
-        stored_git_tag = "<none>"
-
-    return stored_git_tag
-
-
-def run(command, desc=None, errdesc=None, custom_env=None, live=False):
-    if desc is not None:
-        print(desc)
-
-    if live:
-        result = subprocess.run(command, shell=True, env=os.environ if custom_env is None else custom_env)
-        if result.returncode != 0:
-            raise RuntimeError(f"""{errdesc or 'Error running command'}.
-Command: {command}
-Error code: {result.returncode}""")
-
-        return ""
-
-    result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True, env=os.environ if custom_env is None else custom_env)
-
-    if result.returncode != 0:
-
-        message = f"""{errdesc or 'Error running command'}.
-Command: {command}
-Error code: {result.returncode}
-stdout: {result.stdout.decode(encoding="utf8", errors="ignore") if len(result.stdout)>0 else '<empty>'}
-stderr: {result.stderr.decode(encoding="utf8", errors="ignore") if len(result.stderr)>0 else '<empty>'}
-"""
-        raise RuntimeError(message)
-
-    return result.stdout.decode(encoding="utf8", errors="ignore")
-
-
-def check_run(command):
-    result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
-    return result.returncode == 0
-
-
-def is_installed(package):
-    try:
-        spec = importlib.util.find_spec(package)
-    except ModuleNotFoundError:
-        return False
-
-    return spec is not None
-
-
-def repo_dir(name):
-    return os.path.join(script_path, dir_repos, name)
-
-
-def run_python(code, desc=None, errdesc=None):
-    return run(f'"{python}" -c "{code}"', desc, errdesc)
-
-
-def run_pip(command, desc=None, live=False):
-    if args.skip_install:
-        return
-
-    index_url_line = f' --index-url {index_url}' if index_url != '' else ''
-    return run(f'"{python}" -m pip {command} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}", live=live)
-
-
-def check_run_python(code):
-    return check_run(f'"{python}" -c "{code}"')
-
-
-def git_clone(url, dir, name, commithash=None):
-    # TODO clone into temporary dir and move if successful
-
-    if os.path.exists(dir):
-        if commithash is None:
-            return
-
-        current_hash = run(f'"{git}" -C "{dir}" rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}").strip()
-        if current_hash == commithash:
-            return
-
-        run(f'"{git}" -C "{dir}" fetch', f"Fetching updates for {name}...", f"Couldn't fetch {name}")
-        run(f'"{git}" -C "{dir}" checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}")
-        return
-
-    run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}")
-
-    if commithash is not None:
-        run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
-
-
-def git_pull_recursive(dir):
-    for subdir, _, _ in os.walk(dir):
-        if os.path.exists(os.path.join(subdir, '.git')):
-            try:
-                output = subprocess.check_output([git, '-C', subdir, 'pull', '--autostash'])
-                print(f"Pulled changes for repository in '{subdir}':\n{output.decode('utf-8').strip()}\n")
-            except subprocess.CalledProcessError as e:
-                print(f"Couldn't perform 'git pull' on repository in '{subdir}':\n{e.output.decode('utf-8').strip()}\n")
-
-
-def version_check(commit):
-    try:
-        import requests
-        commits = requests.get('https://api.github.com/repos/AUTOMATIC1111/stable-diffusion-webui/branches/master').json()
-        if commit != "<none>" and commits['commit']['sha'] != commit:
-            print("--------------------------------------------------------")
-            print("| You are not up to date with the most recent release. |")
-            print("| Consider running `git pull` to update.               |")
-            print("--------------------------------------------------------")
-        elif commits['commit']['sha'] == commit:
-            print("You are up to date with the most recent release.")
-        else:
-            print("Not a git clone, can't perform version check.")
-    except Exception as e:
-        print("version check failed", e)
-
-
-def run_extension_installer(extension_dir):
-    path_installer = os.path.join(extension_dir, "install.py")
-    if not os.path.isfile(path_installer):
-        return
-
-    try:
-        env = os.environ.copy()
-        env['PYTHONPATH'] = os.path.abspath(".")
-
-        print(run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env))
-    except Exception as e:
-        print(e, file=sys.stderr)
-
-
-def list_extensions(settings_file):
-    settings = {}
-
-    try:
-        if os.path.isfile(settings_file):
-            with open(settings_file, "r", encoding="utf8") as file:
-                settings = json.load(file)
-    except Exception as e:
-        print(e, file=sys.stderr)
-
-    disabled_extensions = set(settings.get('disabled_extensions', []))
-    disable_all_extensions = settings.get('disable_all_extensions', 'none')
-
-    if disable_all_extensions != 'none':
-        return []
-
-    return [x for x in os.listdir(extensions_dir) if x not in disabled_extensions]
-
-
-def run_extensions_installers(settings_file):
-    if not os.path.isdir(extensions_dir):
-        return
-
-    for dirname_extension in list_extensions(settings_file):
-        run_extension_installer(os.path.join(extensions_dir, dirname_extension))
-
-
-def prepare_environment():
-    torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url https://download.pytorch.org/whl/cu118")
-    requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
-
-    xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.17')
-    gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379")
-    clip_package = os.environ.get('CLIP_PACKAGE', "git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1")
-    openclip_package = os.environ.get('OPENCLIP_PACKAGE', "git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b")
-
-    stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/Stability-AI/stablediffusion.git")
-    taming_transformers_repo = os.environ.get('TAMING_TRANSFORMERS_REPO', "https://github.com/CompVis/taming-transformers.git")
-    k_diffusion_repo = os.environ.get('K_DIFFUSION_REPO', 'https://github.com/crowsonkb/k-diffusion.git')
-    codeformer_repo = os.environ.get('CODEFORMER_REPO', 'https://github.com/sczhou/CodeFormer.git')
-    blip_repo = os.environ.get('BLIP_REPO', 'https://github.com/salesforce/BLIP.git')
-
-    stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf")
-    taming_transformers_commit_hash = os.environ.get('TAMING_TRANSFORMERS_COMMIT_HASH', "24268930bf1dce879235a7fddd0b2355b84d7ea6")
-    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "5b3af030dd83e0297272d861c19477735d0317ec")
-    codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
-    blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
-
-    if not args.skip_python_version_check:
-        check_python_version()
-
-    commit = commit_hash()
-    tag = git_tag()
-
-    print(f"Python {sys.version}")
-    print(f"Version: {tag}")
-    print(f"Commit hash: {commit}")
-
-    if args.reinstall_torch or not is_installed("torch") or not is_installed("torchvision"):
-        run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True)
-
-    if not args.skip_torch_cuda_test:
-        run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
-
-    if not is_installed("gfpgan"):
-        run_pip(f"install {gfpgan_package}", "gfpgan")
-
-    if not is_installed("clip"):
-        run_pip(f"install {clip_package}", "clip")
-
-    if not is_installed("open_clip"):
-        run_pip(f"install {openclip_package}", "open_clip")
-
-    if (not is_installed("xformers") or args.reinstall_xformers) and args.xformers:
-        if platform.system() == "Windows":
-            if platform.python_version().startswith("3.10"):
-                run_pip(f"install -U -I --no-deps {xformers_package}", "xformers", live=True)
-            else:
-                print("Installation of xformers is not supported in this version of Python.")
-                print("You can also check this and build manually: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers#building-xformers-on-windows-by-duckness")
-                if not is_installed("xformers"):
-                    exit(0)
-        elif platform.system() == "Linux":
-            run_pip(f"install {xformers_package}", "xformers")
-
-    if not is_installed("pyngrok") and args.ngrok:
-        run_pip("install pyngrok", "ngrok")
-
-    os.makedirs(os.path.join(script_path, dir_repos), exist_ok=True)
-
-    git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash)
-    git_clone(taming_transformers_repo, repo_dir('taming-transformers'), "Taming Transformers", taming_transformers_commit_hash)
-    git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
-    git_clone(codeformer_repo, repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
-    git_clone(blip_repo, repo_dir('BLIP'), "BLIP", blip_commit_hash)
-
-    if not is_installed("lpips"):
-        run_pip(f"install -r \"{os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}\"", "requirements for CodeFormer")
-
-    if not os.path.isfile(requirements_file):
-        requirements_file = os.path.join(script_path, requirements_file)
-    run_pip(f"install -r \"{requirements_file}\"", "requirements")
-
-    run_extensions_installers(settings_file=args.ui_settings_file)
-
-    if args.update_check:
-        version_check(commit)
-
-    if args.update_all_extensions:
-        git_pull_recursive(extensions_dir)
-    
-    if "--exit" in sys.argv:
-        print("Exiting because of --exit argument")
-        exit(0)
-
-    if args.tests and not args.no_tests:
-        exitcode = tests(args.tests)
-        exit(exitcode)
-
-
-def tests(test_dir):
-    if "--api" not in sys.argv:
-        sys.argv.append("--api")
-    if "--ckpt" not in sys.argv:
-        sys.argv.append("--ckpt")
-        sys.argv.append(os.path.join(script_path, "test/test_files/empty.pt"))
-    if "--skip-torch-cuda-test" not in sys.argv:
-        sys.argv.append("--skip-torch-cuda-test")
-    if "--disable-nan-check" not in sys.argv:
-        sys.argv.append("--disable-nan-check")
-    if "--no-tests" not in sys.argv:
-        sys.argv.append("--no-tests")
-
-    print(f"Launching Web UI in another process for testing with arguments: {' '.join(sys.argv[1:])}")
-
-    os.environ['COMMANDLINE_ARGS'] = ""
-    with open(os.path.join(script_path, 'test/stdout.txt'), "w", encoding="utf8") as stdout, open(os.path.join(script_path, 'test/stderr.txt'), "w", encoding="utf8") as stderr:
-        proc = subprocess.Popen([sys.executable, *sys.argv], stdout=stdout, stderr=stderr)
-
-    import test.server_poll
-    exitcode = test.server_poll.run_tests(proc, test_dir)
-
-    print(f"Stopping Web UI process with id {proc.pid}")
-    proc.kill()
-    return exitcode
-
-
-def start():
-    print(f"Launching {'API server' if '--nowebui' in sys.argv else 'Web UI'} with arguments: {' '.join(sys.argv[1:])}")
-    import webui
-    if '--nowebui' in sys.argv:
-        webui.api_only()
-    else:
-        webui.webui()
 
 
 if __name__ == "__main__":
-    prepare_environment()
+    main()
-    start()

modules/api/api.py

@@ -14,32 +14,31 @@ from fastapi.encoders import jsonable_encoder
 from secrets import compare_digest
 
 import modules.shared as shared
-from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing
+from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart
-from modules.api.models import *
+from modules.api import models
+from modules.shared import opts
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
 from modules.textual_inversion.textual_inversion import create_embedding, train_embedding
 from modules.textual_inversion.preprocess import preprocess
 from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork
 from PIL import PngImagePlugin,Image
-from modules.sd_models import checkpoints_list, unload_model_weights, reload_model_weights
+from modules.sd_models import checkpoints_list, unload_model_weights, reload_model_weights, checkpoint_alisases
+from modules.sd_vae import vae_dict
 from modules.sd_models_config import find_checkpoint_config_near_filename
 from modules.realesrgan_model import get_realesrgan_models
 from modules import devices
-from typing import List
+from typing import Dict, List, Any
 import piexif
 import piexif.helper
+from contextlib import closing
 
-def upscaler_to_index(name: str):
-    try:
-        return [x.name.lower() for x in shared.sd_upscalers].index(name.lower())
-    except:
-        raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in sd_upscalers])}")
 
 def script_name_to_index(name, scripts):
     try:
         return [script.title().lower() for script in scripts].index(name.lower())
-    except:
+    except Exception as e:
-        raise HTTPException(status_code=422, detail=f"Script '{name}' not found")
+        raise HTTPException(status_code=422, detail=f"Script '{name}' not found") from e
+
 
 def validate_sampler_name(name):
     config = sd_samplers.all_samplers_map.get(name, None)
@@ -48,20 +47,23 @@ def validate_sampler_name(name):
 
     return name
 
+
 def setUpscalers(req: dict):
     reqDict = vars(req)
     reqDict['extras_upscaler_1'] = reqDict.pop('upscaler_1', None)
     reqDict['extras_upscaler_2'] = reqDict.pop('upscaler_2', None)
     return reqDict
 
+
 def decode_base64_to_image(encoding):
     if encoding.startswith("data:image/"):
         encoding = encoding.split(";")[1].split(",")[1]
     try:
         image = Image.open(BytesIO(base64.b64decode(encoding)))
         return image
-    except Exception as err:
+    except Exception as e:
-        raise HTTPException(status_code=500, detail="Invalid encoded image")
+        raise HTTPException(status_code=500, detail="Invalid encoded image") from e
+
 
 def encode_pil_to_base64(image):
     with io.BytesIO() as output_bytes:
@@ -76,6 +78,8 @@ def encode_pil_to_base64(image):
             image.save(output_bytes, format="PNG", pnginfo=(metadata if use_metadata else None), quality=opts.jpeg_quality)
 
         elif opts.samples_format.lower() in ("jpg", "jpeg", "webp"):
+            if image.mode == "RGBA":
+                image = image.convert("RGB")
             parameters = image.info.get('parameters', None)
             exif_bytes = piexif.dump({
                 "Exif": { piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(parameters or "", encoding="unicode") }
@@ -92,6 +96,7 @@ def encode_pil_to_base64(image):
 
     return base64.b64encode(bytes_data)
 
+
 def api_middleware(app: FastAPI):
     rich_available = True
     try:
@@ -99,8 +104,7 @@ def api_middleware(app: FastAPI):
         import starlette # importing just so it can be placed on silent list
         from rich.console import Console
         console = Console()
-    except:
+    except Exception:
-        import traceback
         rich_available = False
 
     @app.middleware("http")
@@ -131,11 +135,12 @@ def api_middleware(app: FastAPI):
             "errors": str(e),
         }
         if not isinstance(e, HTTPException): # do not print backtrace on known httpexceptions
-            print(f"API error: {request.method}: {request.url} {err}")
+            message = f"API error: {request.method}: {request.url} {err}"
             if rich_available:
+                print(message)
                 console.print_exception(show_locals=True, max_frames=2, extra_lines=1, suppress=[anyio, starlette], word_wrap=False, width=min([console.width, 200]))
             else:
-                traceback.print_exc()
+                errors.report(message, exc_info=True)
         return JSONResponse(status_code=vars(e).get('status_code', 500), content=jsonable_encoder(err))
 
     @app.middleware("http")
@@ -157,7 +162,7 @@ def api_middleware(app: FastAPI):
 class Api:
     def __init__(self, app: FastAPI, queue_lock: Lock):
         if shared.cmd_opts.api_auth:
-            self.credentials = dict()
+            self.credentials = {}
             for auth in shared.cmd_opts.api_auth.split(","):
                 user, password = auth.split(":")
                 self.credentials[user] = password
@@ -166,36 +171,44 @@ class Api:
         self.app = app
         self.queue_lock = queue_lock
         api_middleware(self.app)
-        self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=TextToImageResponse)
+        self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=models.TextToImageResponse)
-        self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=ImageToImageResponse)
+        self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=models.ImageToImageResponse)
-        self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse)
+        self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=models.ExtrasSingleImageResponse)
-        self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=ExtrasBatchImagesResponse)
+        self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=models.ExtrasBatchImagesResponse)
-        self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=PNGInfoResponse)
+        self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=models.PNGInfoResponse)
-        self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=ProgressResponse)
+        self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=models.ProgressResponse)
         self.add_api_route("/sdapi/v1/interrogate", self.interrogateapi, methods=["POST"])
         self.add_api_route("/sdapi/v1/interrupt", self.interruptapi, methods=["POST"])
         self.add_api_route("/sdapi/v1/skip", self.skip, methods=["POST"])
-        self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=OptionsModel)
+        self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=models.OptionsModel)
         self.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"])
-        self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=FlagsModel)
+        self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=models.FlagsModel)
-        self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[SamplerItem])
+        self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[models.SamplerItem])
-        self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[UpscalerItem])
+        self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[models.UpscalerItem])
-        self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[SDModelItem])
+        self.add_api_route("/sdapi/v1/latent-upscale-modes", self.get_latent_upscale_modes, methods=["GET"], response_model=List[models.LatentUpscalerModeItem])
-        self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem])
+        self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[models.SDModelItem])
-        self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem])
+        self.add_api_route("/sdapi/v1/sd-vae", self.get_sd_vaes, methods=["GET"], response_model=List[models.SDVaeItem])
-        self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem])
+        self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[models.HypernetworkItem])
-        self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem])
+        self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[models.FaceRestorerItem])
-        self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse)
+        self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[models.RealesrganItem])
+        self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[models.PromptStyleItem])
+        self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse)
         self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"])
-        self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse)
+        self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse)
-        self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse)
+        self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse)
-        self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=PreprocessResponse)
+        self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse)
-        self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=TrainResponse)
+        self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=models.TrainResponse)
-        self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=TrainResponse)
+        self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=models.TrainResponse)
-        self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=MemoryResponse)
+        self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=models.MemoryResponse)
         self.add_api_route("/sdapi/v1/unload-checkpoint", self.unloadapi, methods=["POST"])
         self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"])
-        self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=ScriptsList)
+        self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=models.ScriptsList)
+        self.add_api_route("/sdapi/v1/script-info", self.get_script_info, methods=["GET"], response_model=List[models.ScriptInfo])
+
+        if shared.cmd_opts.api_server_stop:
+            self.add_api_route("/sdapi/v1/server-kill", self.kill_webui, methods=["POST"])
+            self.add_api_route("/sdapi/v1/server-restart", self.restart_webui, methods=["POST"])
+            self.add_api_route("/sdapi/v1/server-stop", self.stop_webui, methods=["POST"])
 
         self.default_script_arg_txt2img = []
         self.default_script_arg_img2img = []
@@ -221,10 +234,18 @@ class Api:
         return script, script_idx
 
     def get_scripts_list(self):
-        t2ilist = [str(title.lower()) for title in scripts.scripts_txt2img.titles]
+        t2ilist = [script.name for script in scripts.scripts_txt2img.scripts if script.name is not None]
-        i2ilist = [str(title.lower()) for title in scripts.scripts_img2img.titles]
+        i2ilist = [script.name for script in scripts.scripts_img2img.scripts if script.name is not None]
 
-        return ScriptsList(txt2img = t2ilist, img2img = i2ilist)  
+        return models.ScriptsList(txt2img=t2ilist, img2img=i2ilist)
+
+    def get_script_info(self):
+        res = []
+
+        for script_list in [scripts.scripts_txt2img.scripts, scripts.scripts_img2img.scripts]:
+            res += [script.api_info for script in script_list if script.api_info is not None]
+
+        return res
 
     def get_script(self, script_name, script_runner):
         if script_name is None or script_name == "":
@@ -261,14 +282,14 @@ class Api:
             script_args[0] = selectable_idx + 1
 
         # Now check for always on scripts
-        if request.alwayson_scripts and (len(request.alwayson_scripts) > 0):
+        if request.alwayson_scripts:
             for alwayson_script_name in request.alwayson_scripts.keys():
                 alwayson_script = self.get_script(alwayson_script_name, script_runner)
-                if alwayson_script == None:
+                if alwayson_script is None:
                     raise HTTPException(status_code=422, detail=f"always on script {alwayson_script_name} not found")
                 # Selectable script in always on script param check
-                if alwayson_script.alwayson == False:
+                if alwayson_script.alwayson is False:
-                    raise HTTPException(status_code=422, detail=f"Cannot have a selectable script in the always on scripts params")
+                    raise HTTPException(status_code=422, detail="Cannot have a selectable script in the always on scripts params")
                 # always on script with no arg should always run so you don't really need to add them to the requests
                 if "args" in request.alwayson_scripts[alwayson_script_name]:
                     # min between arg length in scriptrunner and arg length in the request
@@ -276,7 +297,7 @@ class Api:
                         script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx]
         return script_args
 
-    def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
+    def text2imgapi(self, txt2imgreq: models.StableDiffusionTxt2ImgProcessingAPI):
         script_runner = scripts.scripts_txt2img
         if not script_runner.scripts:
             script_runner.initialize_scripts(False)
@@ -304,13 +325,13 @@ class Api:
         args.pop('save_images', None)
 
         with self.queue_lock:
-            p = StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)
+            with closing(StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)) as p:
                 p.scripts = script_runner
                 p.outpath_grids = opts.outdir_txt2img_grids
                 p.outpath_samples = opts.outdir_txt2img_samples
 
-            shared.state.begin()
+                shared.state.begin(job="scripts_txt2img")
-            if selectable_scripts != None:
+                if selectable_scripts is not None:
                     p.script_args = script_args
                     processed = scripts.scripts_txt2img.run(p, *p.script_args) # Need to pass args as list here
                 else:
@@ -320,9 +341,9 @@ class Api:
 
         b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else []
 
-        return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
+        return models.TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
 
-    def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI):
+    def img2imgapi(self, img2imgreq: models.StableDiffusionImg2ImgProcessingAPI):
         init_images = img2imgreq.init_images
         if init_images is None:
             raise HTTPException(status_code=404, detail="Init image not found")
@@ -360,14 +381,14 @@ class Api:
         args.pop('save_images', None)
 
         with self.queue_lock:
-            p = StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)
+            with closing(StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)) as p:
                 p.init_images = [decode_base64_to_image(x) for x in init_images]
                 p.scripts = script_runner
                 p.outpath_grids = opts.outdir_img2img_grids
                 p.outpath_samples = opts.outdir_img2img_samples
 
-            shared.state.begin()
+                shared.state.begin(job="scripts_img2img")
-            if selectable_scripts != None:
+                if selectable_scripts is not None:
                     p.script_args = script_args
                     processed = scripts.scripts_img2img.run(p, *p.script_args) # Need to pass args as list here
                 else:
@@ -381,9 +402,9 @@ class Api:
             img2imgreq.init_images = None
             img2imgreq.mask = None
 
-        return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js())
+        return models.ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js())
 
-    def extras_single_image_api(self, req: ExtrasSingleImageRequest):
+    def extras_single_image_api(self, req: models.ExtrasSingleImageRequest):
         reqDict = setUpscalers(req)
 
         reqDict['image'] = decode_base64_to_image(reqDict['image'])
@@ -391,9 +412,9 @@ class Api:
         with self.queue_lock:
             result = postprocessing.run_extras(extras_mode=0, image_folder="", input_dir="", output_dir="", save_output=False, **reqDict)
 
-        return ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1])
+        return models.ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1])
 
-    def extras_batch_images_api(self, req: ExtrasBatchImagesRequest):
+    def extras_batch_images_api(self, req: models.ExtrasBatchImagesRequest):
         reqDict = setUpscalers(req)
 
         image_list = reqDict.pop('imageList', [])
@@ -402,15 +423,15 @@ class Api:
         with self.queue_lock:
             result = postprocessing.run_extras(extras_mode=1, image_folder=image_folder, image="", input_dir="", output_dir="", save_output=False, **reqDict)
 
-        return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
+        return models.ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
 
-    def pnginfoapi(self, req: PNGInfoRequest):
+    def pnginfoapi(self, req: models.PNGInfoRequest):
         if(not req.image.strip()):
-            return PNGInfoResponse(info="")
+            return models.PNGInfoResponse(info="")
 
         image = decode_base64_to_image(req.image.strip())
         if image is None:
-            return PNGInfoResponse(info="")
+            return models.PNGInfoResponse(info="")
 
         geninfo, items = images.read_info_from_image(image)
         if geninfo is None:
@@ -418,13 +439,13 @@ class Api:
 
         items = {**{'parameters': geninfo}, **items}
 
-        return PNGInfoResponse(info=geninfo, items=items)
+        return models.PNGInfoResponse(info=geninfo, items=items)
 
-    def progressapi(self, req: ProgressRequest = Depends()):
+    def progressapi(self, req: models.ProgressRequest = Depends()):
         # copy from check_progress_call of ui.py
 
         if shared.state.job_count == 0:
-            return ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo)
+            return models.ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo)
 
         # avoid dividing zero
         progress = 0.01
@@ -446,9 +467,9 @@ class Api:
         if shared.state.current_image and not req.skip_current_image:
             current_image = encode_pil_to_base64(shared.state.current_image)
 
-        return ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo)
+        return models.ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo)
 
-    def interrogateapi(self, interrogatereq: InterrogateRequest):
+    def interrogateapi(self, interrogatereq: models.InterrogateRequest):
         image_b64 = interrogatereq.image
         if image_b64 is None:
             raise HTTPException(status_code=404, detail="Image not found")
@@ -465,7 +486,7 @@ class Api:
             else:
                 raise HTTPException(status_code=404, detail="Model not found")
 
-        return InterrogateResponse(caption=processed)
+        return models.InterrogateResponse(caption=processed)
 
     def interruptapi(self):
         shared.state.interrupt()
@@ -497,6 +518,10 @@ class Api:
         return options
 
     def set_config(self, req: Dict[str, Any]):
+        checkpoint_name = req.get("sd_model_checkpoint", None)
+        if checkpoint_name is not None and checkpoint_name not in checkpoint_alisases:
+            raise RuntimeError(f"model {checkpoint_name!r} not found")
+
         for k, v in req.items():
             shared.opts.set(k, v)
 
@@ -521,9 +546,20 @@ class Api:
             for upscaler in shared.sd_upscalers
         ]
 
+    def get_latent_upscale_modes(self):
+        return [
+            {
+                "name": upscale_mode,
+            }
+            for upscale_mode in [*(shared.latent_upscale_modes or {})]
+        ]
+
     def get_sd_models(self):
         return [{"title": x.title, "model_name": x.model_name, "hash": x.shorthash, "sha256": x.sha256, "filename": x.filename, "config": find_checkpoint_config_near_filename(x)} for x in checkpoints_list.values()]
 
+    def get_sd_vaes(self):
+        return [{"model_name": x, "filename": vae_dict[x]} for x in vae_dict.keys()]
+
     def get_hypernetworks(self):
         return [{"name": name, "path": shared.hypernetworks[name]} for name in shared.hypernetworks]
 
@@ -566,44 +602,42 @@ class Api:
 
     def create_embedding(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="create_embedding")
             filename = create_embedding(**args) # create empty embedding
             sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings() # reload embeddings so new one can be immediately used
-            shared.state.end()
+            return models.CreateResponse(info=f"create embedding filename: {filename}")
-            return CreateResponse(info=f"create embedding filename: {filename}")
         except AssertionError as e:
+            return models.TrainResponse(info=f"create embedding error: {e}")
+        finally:
             shared.state.end()
-            return TrainResponse(info=f"create embedding error: {e}")
+
 
     def create_hypernetwork(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="create_hypernetwork")
             filename = create_hypernetwork(**args) # create empty embedding
-            shared.state.end()
+            return models.CreateResponse(info=f"create hypernetwork filename: {filename}")
-            return CreateResponse(info=f"create hypernetwork filename: {filename}")
         except AssertionError as e:
+            return models.TrainResponse(info=f"create hypernetwork error: {e}")
+        finally:
             shared.state.end()
-            return TrainResponse(info=f"create hypernetwork error: {e}")
 
     def preprocess(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="preprocess")
             preprocess(**args) # quick operation unless blip/booru interrogation is enabled
             shared.state.end()
-            return PreprocessResponse(info = 'preprocess complete')
+            return models.PreprocessResponse(info='preprocess complete')
         except KeyError as e:
+            return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}")
+        except Exception as e:
+            return models.PreprocessResponse(info=f"preprocess error: {e}")
+        finally:
             shared.state.end()
-            return PreprocessResponse(info=f"preprocess error: invalid token: {e}")
-        except AssertionError as e:
-            shared.state.end()
-            return PreprocessResponse(info=f"preprocess error: {e}")
-        except FileNotFoundError as e:
-            shared.state.end()
-            return PreprocessResponse(info=f'preprocess error: {e}')
 
     def train_embedding(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="train_embedding")
             apply_optimizations = shared.opts.training_xattention_optimizations
             error = None
             filename = ''
@@ -616,15 +650,15 @@ class Api:
             finally:
                 if not apply_optimizations:
                     sd_hijack.apply_optimizations()
+            return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
+        except Exception as msg:
+            return models.TrainResponse(info=f"train embedding error: {msg}")
+        finally:
             shared.state.end()
-            return TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
-        except AssertionError as msg:
-            shared.state.end()
-            return TrainResponse(info=f"train embedding error: {msg}")
 
     def train_hypernetwork(self, args: dict):
         try:
-            shared.state.begin()
+            shared.state.begin(job="train_hypernetwork")
             shared.loaded_hypernetworks = []
             apply_optimizations = shared.opts.training_xattention_optimizations
             error = None
@@ -641,14 +675,16 @@ class Api:
                 if not apply_optimizations:
                     sd_hijack.apply_optimizations()
                 shared.state.end()
-            return TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
+            return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
-        except AssertionError as msg:
+        except Exception as exc:
+            return models.TrainResponse(info=f"train embedding error: {exc}")
+        finally:
             shared.state.end()
-            return TrainResponse(info=f"train embedding error: {error}")
 
     def get_memory(self):
         try:
-            import os, psutil
+            import os
+            import psutil
             process = psutil.Process(os.getpid())
             res = process.memory_info() # only rss is cross-platform guaranteed so we dont rely on other values
             ram_total = 100 * res.rss / process.memory_percent() # and total memory is calculated as actual value is not cross-platform safe
@@ -675,11 +711,23 @@ class Api:
                     'events': warnings,
                 }
             else:
-                cuda = { 'error': 'unavailable' }
+                cuda = {'error': 'unavailable'}
         except Exception as err:
-            cuda = { 'error': f'{err}' }
+            cuda = {'error': f'{err}'}
-        return MemoryResponse(ram = ram, cuda = cuda)
+        return models.MemoryResponse(ram=ram, cuda=cuda)
 
     def launch(self, server_name, port):
         self.app.include_router(self.router)
-        uvicorn.run(self.app, host=server_name, port=port)
+        uvicorn.run(self.app, host=server_name, port=port, timeout_keep_alive=0)
+
+    def kill_webui(self):
+        restart.stop_program()
+
+    def restart_webui(self):
+        if restart.is_restartable():
+            restart.restart_program()
+        return Response(status_code=501)
+
+    def stop_webui(request):
+        shared.state.server_command = "stop"
+        return Response("Stopping.")

modules/api/models.py

@@ -223,8 +223,9 @@ for key in _options:
     if(_options[key].dest != 'help'):
         flag = _options[key]
         _type = str
-        if _options[key].default is not None: _type = type(_options[key].default)
+        if _options[key].default is not None:
-        flags.update({flag.dest: (_type,Field(default=flag.default, description=flag.help))})
+            _type = type(_options[key].default)
+        flags.update({flag.dest: (_type, Field(default=flag.default, description=flag.help))})
 
 FlagsModel = create_model("Flags", **flags)
 
@@ -240,6 +241,9 @@ class UpscalerItem(BaseModel):
     model_url: Optional[str] = Field(title="URL")
     scale: Optional[float] = Field(title="Scale")
 
+class LatentUpscalerModeItem(BaseModel):
+    name: str = Field(title="Name")
+
 class SDModelItem(BaseModel):
     title: str = Field(title="Title")
     model_name: str = Field(title="Model Name")
@@ -248,6 +252,10 @@ class SDModelItem(BaseModel):
     filename: str = Field(title="Filename")
     config: Optional[str] = Field(title="Config file")
 
+class SDVaeItem(BaseModel):
+    model_name: str = Field(title="Model Name")
+    filename: str = Field(title="Filename")
+
 class HypernetworkItem(BaseModel):
     name: str = Field(title="Name")
     path: Optional[str] = Field(title="Path")
@@ -266,10 +274,6 @@ class PromptStyleItem(BaseModel):
     prompt: Optional[str] = Field(title="Prompt")
     negative_prompt: Optional[str] = Field(title="Negative Prompt")
 
-class ArtistItem(BaseModel):
-    name: str = Field(title="Name")
-    score: float = Field(title="Score")
-    category: str = Field(title="Category")
 
 class EmbeddingItem(BaseModel):
     step: Optional[int] = Field(title="Step", description="The number of steps that were used to train this embedding, if available")
@@ -286,6 +290,23 @@ class MemoryResponse(BaseModel):
     ram: dict = Field(title="RAM", description="System memory stats")
     cuda: dict = Field(title="CUDA", description="nVidia CUDA memory stats")
 
+
 class ScriptsList(BaseModel):
-    txt2img: list = Field(default=None,title="Txt2img", description="Titles of scripts (txt2img)")
+    txt2img: list = Field(default=None, title="Txt2img", description="Titles of scripts (txt2img)")
-    img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)")
+    img2img: list = Field(default=None, title="Img2img", description="Titles of scripts (img2img)")
+
+
+class ScriptArg(BaseModel):
+    label: str = Field(default=None, title="Label", description="Name of the argument in UI")
+    value: Optional[Any] = Field(default=None, title="Value", description="Default value of the argument")
+    minimum: Optional[Any] = Field(default=None, title="Minimum", description="Minimum allowed value for the argumentin UI")
+    maximum: Optional[Any] = Field(default=None, title="Minimum", description="Maximum allowed value for the argumentin UI")
+    step: Optional[Any] = Field(default=None, title="Minimum", description="Step for changing value of the argumentin UI")
+    choices: Optional[List[str]] = Field(default=None, title="Choices", description="Possible values for the argument")
+
+
+class ScriptInfo(BaseModel):
+    name: str = Field(default=None, title="Name", description="Script name")
+    is_alwayson: bool = Field(default=None, title="IsAlwayson", description="Flag specifying whether this script is an alwayson script")
+    is_img2img: bool = Field(default=None, title="IsImg2img", description="Flag specifying whether this script is an img2img script")
+    args: List[ScriptArg] = Field(title="Arguments", description="List of script's arguments")

modules/call_queue.py

@@ -1,10 +1,9 @@
+from functools import wraps
 import html
-import sys
 import threading
-import traceback
 import time
 
-from modules import shared, progress
+from modules import shared, progress, errors
 
 queue_lock = threading.Lock()
 
@@ -20,17 +19,18 @@ def wrap_queued_call(func):
 
 
 def wrap_gradio_gpu_call(func, extra_outputs=None):
+    @wraps(func)
     def f(*args, **kwargs):
 
         # if the first argument is a string that says "task(...)", it is treated as a job id
-        if len(args) > 0 and type(args[0]) == str and args[0][0:5] == "task(" and args[0][-1] == ")":
+        if args and type(args[0]) == str and args[0].startswith("task(") and args[0].endswith(")"):
             id_task = args[0]
             progress.add_task_to_queue(id_task)
         else:
             id_task = None
 
         with queue_lock:
-            shared.state.begin()
+            shared.state.begin(job=id_task)
             progress.start_task(id_task)
 
             try:
@@ -47,6 +47,7 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
 
 
 def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
+    @wraps(func)
     def f(*args, extra_outputs_array=extra_outputs, **kwargs):
         run_memmon = shared.opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled and add_stats
         if run_memmon:
@@ -56,16 +57,14 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
         try:
             res = list(func(*args, **kwargs))
         except Exception as e:
-            # When printing out our debug argument list, do not print out more than a MB of text
+            # When printing out our debug argument list,
-            max_debug_str_len = 131072 # (1024*1024)/8
+            # do not print out more than a 100 KB of text
-
+            max_debug_str_len = 131072
-            print("Error completing request", file=sys.stderr)
+            message = "Error completing request"
-            argStr = f"Arguments: {args} {kwargs}"
+            arg_str = f"Arguments: {args} {kwargs}"[:max_debug_str_len]
-            print(argStr[:max_debug_str_len], file=sys.stderr)
+            if len(arg_str) > max_debug_str_len:
-            if len(argStr) > max_debug_str_len:
+                arg_str += f" (Argument list truncated at {max_debug_str_len}/{len(arg_str)} characters)"
-                print(f"(Argument list truncated at {max_debug_str_len}/{len(argStr)} characters)", file=sys.stderr)
+            errors.report(f"{message}\n{arg_str}", exc_info=True)
-
-            print(traceback.format_exc(), file=sys.stderr)
 
             shared.state.job = ""
             shared.state.job_count = 0
@@ -108,4 +107,3 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
         return tuple(res)
 
     return f
-

modules/cmd_args.py

@@ -1,6 +1,7 @@
 import argparse
+import json
 import os
-from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file
+from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file  # noqa: F401
 
 parser = argparse.ArgumentParser()
 
@@ -10,9 +11,9 @@ parser.add_argument("--skip-python-version-check", action='store_true', help="la
 parser.add_argument("--skip-torch-cuda-test", action='store_true', help="launch.py argument: do not check if CUDA is able to work properly")
 parser.add_argument("--reinstall-xformers", action='store_true', help="launch.py argument: install the appropriate version of xformers even if you have some version already installed")
 parser.add_argument("--reinstall-torch", action='store_true', help="launch.py argument: install the appropriate version of torch even if you have some version already installed")
-parser.add_argument("--update-check", action='store_true', help="launch.py argument: chck for updates at startup")
+parser.add_argument("--update-check", action='store_true', help="launch.py argument: check for updates at startup")
-parser.add_argument("--tests", type=str, default=None, help="launch.py argument: run tests in the specified directory")
+parser.add_argument("--test-server", action='store_true', help="launch.py argument: configure server for testing")
-parser.add_argument("--no-tests", action='store_true', help="launch.py argument: do not run tests even if --tests option is specified")
+parser.add_argument("--skip-prepare-environment", action='store_true', help="launch.py argument: skip all environment preparation")
 parser.add_argument("--skip-install", action='store_true', help="launch.py argument: skip installation of packages")
 parser.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored")
 parser.add_argument("--config", type=str, default=sd_default_config, help="path to config which constructs model",)
@@ -39,7 +40,8 @@ parser.add_argument("--precision", type=str, help="evaluate at this precision",
 parser.add_argument("--upcast-sampling", action='store_true', help="upcast sampling. No effect with --no-half. Usually produces similar results to --no-half with better performance while using less memory.")
 parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site")
 parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None)
-parser.add_argument("--ngrok-region", type=str, help="The region in which ngrok should start.", default="us")
+parser.add_argument("--ngrok-region", type=str, help="does not do anything.", default="")
+parser.add_argument("--ngrok-options", type=json.loads, help='The options to pass to ngrok in JSON format, e.g.: \'{"authtoken_from_env":true, "basic_auth":"user:password", "oauth_provider":"google", "oauth_allow_emails":"user@asdf.com"}\'', default=dict())
 parser.add_argument("--enable-insecure-extension-access", action='store_true', help="enable extensions tab regardless of other options")
 parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
 parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
@@ -51,16 +53,16 @@ parser.add_argument("--xformers", action='store_true', help="enable xformers for
 parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
 parser.add_argument("--xformers-flash-attention", action='store_true', help="enable xformers with Flash Attention to improve reproducibility (supported for SD2.x or variant only)")
 parser.add_argument("--deepdanbooru", action='store_true', help="does not do anything")
-parser.add_argument("--opt-split-attention", action='store_true', help="force-enables Doggettx's cross-attention layer optimization. By default, it's on for torch cuda.")
+parser.add_argument("--opt-split-attention", action='store_true', help="prefer Doggettx's cross-attention layer optimization for automatic choice of optimization")
-parser.add_argument("--opt-sub-quad-attention", action='store_true', help="enable memory efficient sub-quadratic cross-attention layer optimization")
+parser.add_argument("--opt-sub-quad-attention", action='store_true', help="prefer memory efficient sub-quadratic cross-attention layer optimization for automatic choice of optimization")
 parser.add_argument("--sub-quad-q-chunk-size", type=int, help="query chunk size for the sub-quadratic cross-attention layer optimization to use", default=1024)
 parser.add_argument("--sub-quad-kv-chunk-size", type=int, help="kv chunk size for the sub-quadratic cross-attention layer optimization to use", default=None)
 parser.add_argument("--sub-quad-chunk-threshold", type=int, help="the percentage of VRAM threshold for the sub-quadratic cross-attention layer optimization to use chunking", default=None)
-parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
+parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="prefer InvokeAI's cross-attention layer optimization for automatic choice of optimization")
-parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
+parser.add_argument("--opt-split-attention-v1", action='store_true', help="prefer older version of split attention optimization for automatic choice of optimization")
-parser.add_argument("--opt-sdp-attention", action='store_true', help="enable scaled dot product cross-attention layer optimization; requires PyTorch 2.*")
+parser.add_argument("--opt-sdp-attention", action='store_true', help="prefer scaled dot product cross-attention layer optimization for automatic choice of optimization; requires PyTorch 2.*")
-parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="enable scaled dot product cross-attention layer optimization without memory efficient attention, makes image generation deterministic; requires PyTorch 2.*")
+parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="prefer scaled dot product cross-attention layer optimization without memory efficient attention for automatic choice of optimization, makes image generation deterministic; requires PyTorch 2.*")
-parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
+parser.add_argument("--disable-opt-split-attention", action='store_true', help="prefer no cross-attention layer optimization for automatic choice of optimization")
 parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
 parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
@@ -75,6 +77,7 @@ parser.add_argument("--gradio-auth", type=str, help='set gradio authentication l
 parser.add_argument("--gradio-auth-path", type=str, help='set gradio authentication file path ex. "/path/to/auth/file" same auth format as --gradio-auth', default=None)
 parser.add_argument("--gradio-img2img-tool", type=str, help='does not do anything')
 parser.add_argument("--gradio-inpaint-tool", type=str, help="does not do anything")
+parser.add_argument("--gradio-allowed-path", action='append', help="add path to gradio's allowed_paths, make it possible to serve files from it")
 parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")
 parser.add_argument("--styles-file", type=str, help="filename to use for styles", default=os.path.join(data_path, 'styles.csv'))
 parser.add_argument("--autolaunch", action='store_true', help="open the webui URL in the system's default browser upon launch", default=False)
@@ -103,3 +106,4 @@ parser.add_argument("--skip-version-check", action='store_true', help="Do not ch
 parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
 parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False)
 parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy')
+parser.add_argument('--api-server-stop', action='store_true', help='enable server stop/restart/kill via api')

modules/codeformer/codeformer_arch.py

@@ -1,14 +1,12 @@
 # this file is copied from CodeFormer repository. Please see comment in modules/codeformer_model.py
 
 import math
-import numpy as np
 import torch
 from torch import nn, Tensor
 import torch.nn.functional as F
-from typing import Optional, List
+from typing import Optional
 
-from modules.codeformer.vqgan_arch import *
+from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock
-from basicsr.utils import get_root_logger
 from basicsr.utils.registry import ARCH_REGISTRY
 
 def calc_mean_std(feat, eps=1e-5):
@@ -163,8 +161,8 @@ class Fuse_sft_block(nn.Module):
 class CodeFormer(VQAutoEncoder):
     def __init__(self, dim_embd=512, n_head=8, n_layers=9,
                 codebook_size=1024, latent_size=256,
-                connect_list=['32', '64', '128', '256'],
+                connect_list=('32', '64', '128', '256'),
-                fix_modules=['quantize','generator']):
+                fix_modules=('quantize', 'generator')):
         super(CodeFormer, self).__init__(512, 64, [1, 2, 2, 4, 4, 8], 'nearest',2, [16], codebook_size)
 
         if fix_modules is not None:

modules/codeformer/vqgan_arch.py

@@ -5,11 +5,9 @@ VQGAN code, adapted from the original created by the Unleashing Transformers aut
 https://github.com/samb-t/unleashing-transformers/blob/master/models/vqgan.py
 
 '''
-import numpy as np
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-import copy
 from basicsr.utils import get_root_logger
 from basicsr.utils.registry import ARCH_REGISTRY
 
@@ -328,7 +326,7 @@ class Generator(nn.Module):
 
 @ARCH_REGISTRY.register()
 class VQAutoEncoder(nn.Module):
-    def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=[16], codebook_size=1024, emb_dim=256,
+    def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=None, codebook_size=1024, emb_dim=256,
                 beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None):
         super().__init__()
         logger = get_root_logger()
@@ -339,7 +337,7 @@ class VQAutoEncoder(nn.Module):
         self.embed_dim = emb_dim
         self.ch_mult = ch_mult
         self.resolution = img_size
-        self.attn_resolutions = attn_resolutions
+        self.attn_resolutions = attn_resolutions or [16]
         self.quantizer_type = quantizer
         self.encoder = Encoder(
             self.in_channels,

modules/codeformer_model.py

@@ -1,13 +1,11 @@
 import os
-import sys
-import traceback
 
 import cv2
 import torch
 
 import modules.face_restoration
 import modules.shared
-from modules import shared, devices, modelloader
+from modules import shared, devices, modelloader, errors
 from modules.paths import models_path
 
 # codeformer people made a choice to include modified basicsr library to their project which makes
@@ -17,14 +15,11 @@ model_dir = "Codeformer"
 model_path = os.path.join(models_path, model_dir)
 model_url = 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth'
 
-have_codeformer = False
 codeformer = None
 
 
 def setup_model(dirname):
-    global model_path
+    os.makedirs(model_path, exist_ok=True)
-    if not os.path.exists(model_path):
-        os.makedirs(model_path)
 
     path = modules.paths.paths.get("CodeFormer", None)
     if path is None:
@@ -33,11 +28,9 @@ def setup_model(dirname):
     try:
         from torchvision.transforms.functional import normalize
         from modules.codeformer.codeformer_arch import CodeFormer
-        from basicsr.utils.download_util import load_file_from_url
+        from basicsr.utils import img2tensor, tensor2img
-        from basicsr.utils import imwrite, img2tensor, tensor2img
         from facelib.utils.face_restoration_helper import FaceRestoreHelper
         from facelib.detection.retinaface import retinaface
-        from modules.shared import cmd_opts
 
         net_class = CodeFormer
 
@@ -96,7 +89,7 @@ def setup_model(dirname):
                 self.face_helper.get_face_landmarks_5(only_center_face=False, resize=640, eye_dist_threshold=5)
                 self.face_helper.align_warp_face()
 
-                for idx, cropped_face in enumerate(self.face_helper.cropped_faces):
+                for cropped_face in self.face_helper.cropped_faces:
                     cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True)
                     normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
                     cropped_face_t = cropped_face_t.unsqueeze(0).to(devices.device_codeformer)
@@ -107,8 +100,8 @@ def setup_model(dirname):
                             restored_face = tensor2img(output, rgb2bgr=True, min_max=(-1, 1))
                         del output
                         torch.cuda.empty_cache()
-                    except Exception as error:
+                    except Exception:
-                        print(f'\tFailed inference for CodeFormer: {error}', file=sys.stderr)
+                        errors.report('Failed inference for CodeFormer', exc_info=True)
                         restored_face = tensor2img(cropped_face_t, rgb2bgr=True, min_max=(-1, 1))
 
                     restored_face = restored_face.astype('uint8')
@@ -129,15 +122,11 @@ def setup_model(dirname):
 
                 return restored_img
 
-        global have_codeformer
-        have_codeformer = True
-
         global codeformer
         codeformer = FaceRestorerCodeFormer(dirname)
         shared.face_restorers.append(codeformer)
 
     except Exception:
-        print("Error setting up CodeFormer:", file=sys.stderr)
+        errors.report("Error setting up CodeFormer", exc_info=True)
-        print(traceback.format_exc(), file=sys.stderr)
 
    # sys.path = stored_sys_path

modules/config_states.py

@@ -3,8 +3,6 @@ Supports saving and restoring webui and extensions from a known working set of c
 """
 
 import os
-import sys
-import traceback
 import json
 import time
 import tqdm
@@ -13,8 +11,8 @@ from datetime import datetime
 from collections import OrderedDict
 import git
 
-from modules import shared, extensions
+from modules import shared, extensions, errors
-from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path, config_states_dir
+from modules.paths_internal import script_path, config_states_dir
 
 
 all_config_states = OrderedDict()
@@ -35,7 +33,7 @@ def list_config_states():
                 j["filepath"] = path
                 config_states.append(j)
 
-    config_states = list(sorted(config_states, key=lambda cs: cs["created_at"], reverse=True))
+    config_states = sorted(config_states, key=lambda cs: cs["created_at"], reverse=True)
 
     for cs in config_states:
         timestamp = time.asctime(time.gmtime(cs["created_at"]))
@@ -53,8 +51,7 @@ def get_webui_config():
         if os.path.exists(os.path.join(script_path, ".git")):
             webui_repo = git.Repo(script_path)
     except Exception:
-        print(f"Error reading webui git info from {script_path}:", file=sys.stderr)
+        errors.report(f"Error reading webui git info from {script_path}", exc_info=True)
-        print(traceback.format_exc(), file=sys.stderr)
 
     webui_remote = None
     webui_commit_hash = None
@@ -83,6 +80,8 @@ def get_extension_config():
     ext_config = {}
 
     for ext in extensions.extensions:
+        ext.read_info_from_repo()
+
         entry = {
             "name": ext.name,
             "path": ext.path,
@@ -132,8 +131,7 @@ def restore_webui_config(config):
         if os.path.exists(os.path.join(script_path, ".git")):
             webui_repo = git.Repo(script_path)
     except Exception:
-        print(f"Error reading webui git info from {script_path}:", file=sys.stderr)
+        errors.report(f"Error reading webui git info from {script_path}", exc_info=True)
-        print(traceback.format_exc(), file=sys.stderr)
         return
 
     try:
@@ -141,8 +139,7 @@ def restore_webui_config(config):
         webui_repo.git.reset(webui_commit_hash, hard=True)
         print(f"* Restored webui to commit {webui_commit_hash}.")
     except Exception:
-        print(f"Error restoring webui to commit {webui_commit_hash}:", file=sys.stderr)
+        errors.report(f"Error restoring webui to commit{webui_commit_hash}")
-        print(traceback.format_exc(), file=sys.stderr)
 
 
 def restore_extension_config(config):

modules/deepbooru.py

@@ -2,7 +2,6 @@ import os
 import re
 
 import torch
-from PIL import Image
 import numpy as np
 
 from modules import modelloader, paths, deepbooru_model, devices, images, shared
@@ -79,7 +78,7 @@ class DeepDanbooru:
 
         res = []
 
-        filtertags = set([x.strip().replace(' ', '_') for x in shared.opts.deepbooru_filter_tags.split(",")])
+        filtertags = {x.strip().replace(' ', '_') for x in shared.opts.deepbooru_filter_tags.split(",")}
 
         for tag in [x for x in tags if x not in filtertags]:
             probability = probability_dict[tag]

modules/devices.py

@@ -1,5 +1,7 @@
 import sys
 import contextlib
+from functools import lru_cache
+
 import torch
 from modules import errors
 
@@ -13,13 +15,6 @@ def has_mps() -> bool:
     else:
         return mac_specific.has_mps
 
-def extract_device_id(args, name):
-    for x in range(len(args)):
-        if name in args[x]:
-            return args[x + 1]
-
-    return None
-
 
 def get_cuda_device_string():
     from modules import shared
@@ -65,7 +60,7 @@ def enable_tf32():
 
         # enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't
         # see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407
-        if any([torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())]):
+        if any(torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())):
             torch.backends.cudnn.benchmark = True
 
         torch.backends.cuda.matmul.allow_tf32 = True
@@ -154,3 +149,19 @@ def test_for_nans(x, where):
     message += " Use --disable-nan-check commandline argument to disable this check."
 
     raise NansException(message)
+
+
+@lru_cache
+def first_time_calculation():
+    """
+    just do any calculation with pytorch layers - the first time this is done it allocaltes about 700MB of memory and
+    spends about 2.7 seconds doing that, at least wih NVidia.
+    """
+
+    x = torch.zeros((1, 1)).to(device, dtype)
+    linear = torch.nn.Linear(1, 1).to(device, dtype)
+    linear(x)
+
+    x = torch.zeros((1, 1, 3, 3)).to(device, dtype)
+    conv2d = torch.nn.Conv2d(1, 1, (3, 3)).to(device, dtype)
+    conv2d(x)

modules/errors.py

@@ -1,8 +1,42 @@
 import sys
+import textwrap
 import traceback
 
 
+exception_records = []
+
+
+def record_exception():
+    _, e, tb = sys.exc_info()
+    if e is None:
+        return
+
+    if exception_records and exception_records[-1] == e:
+        return
+
+    exception_records.append((e, tb))
+
+    if len(exception_records) > 5:
+        exception_records.pop(0)
+
+
+def report(message: str, *, exc_info: bool = False) -> None:
+    """
+    Print an error message to stderr, with optional traceback.
+    """
+
+    record_exception()
+
+    for line in message.splitlines():
+        print("***", line, file=sys.stderr)
+    if exc_info:
+        print(textwrap.indent(traceback.format_exc(), "    "), file=sys.stderr)
+        print("---", file=sys.stderr)
+
+
 def print_error_explanation(message):
+    record_exception()
+
     lines = message.strip().split("\n")
     max_len = max([len(x) for x in lines])
 
@@ -12,9 +46,15 @@ def print_error_explanation(message):
     print('=' * max_len, file=sys.stderr)
 
 
-def display(e: Exception, task):
+def display(e: Exception, task, *, full_traceback=False):
+    record_exception()
+
     print(f"{task or 'error'}: {type(e).__name__}", file=sys.stderr)
-    print(traceback.format_exc(), file=sys.stderr)
+    te = traceback.TracebackException.from_exception(e)
+    if full_traceback:
+        # include frames leading up to the try-catch block
+        te.stack = traceback.StackSummary(traceback.extract_stack()[:-2] + te.stack)
+    print(*te.format(), sep="", file=sys.stderr)
 
     message = str(e)
     if "copying a param with shape torch.Size([640, 1024]) from checkpoint, the shape in current model is torch.Size([640, 768])" in message:
@@ -28,6 +68,8 @@ already_displayed = {}
 
 
 def display_once(e: Exception, task):
+    record_exception()
+
     if task in already_displayed:
         return
 

modules/esrgan_model.py

@@ -1,24 +1,20 @@
-import os
+import sys
 
 import numpy as np
 import torch
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 
 import modules.esrgan_model_arch as arch
-from modules import shared, modelloader, images, devices
+from modules import modelloader, images, devices
-from modules.upscaler import Upscaler, UpscalerData
 from modules.shared import opts
-
+from modules.upscaler import Upscaler, UpscalerData
 
 
 def mod2normal(state_dict):
     # this code is copied from https://github.com/victorca25/iNNfer
     if 'conv_first.weight' in state_dict:
         crt_net = {}
-        items = []
+        items = list(state_dict)
-        for k, v in state_dict.items():
-            items.append(k)
 
         crt_net['model.0.weight'] = state_dict['conv_first.weight']
         crt_net['model.0.bias'] = state_dict['conv_first.bias']
@@ -52,9 +48,7 @@ def resrgan2normal(state_dict, nb=23):
     if "conv_first.weight" in state_dict and "body.0.rdb1.conv1.weight" in state_dict:
         re8x = 0
         crt_net = {}
-        items = []
+        items = list(state_dict)
-        for k, v in state_dict.items():
-            items.append(k)
 
         crt_net['model.0.weight'] = state_dict['conv_first.weight']
         crt_net['model.0.bias'] = state_dict['conv_first.bias']
@@ -138,7 +132,7 @@ class UpscalerESRGAN(Upscaler):
             scaler_data = UpscalerData(self.model_name, self.model_url, self, 4)
             scalers.append(scaler_data)
         for file in model_paths:
-            if "http" in file:
+            if file.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(file)
@@ -147,26 +141,25 @@ class UpscalerESRGAN(Upscaler):
             self.scalers.append(scaler_data)
 
     def do_upscale(self, img, selected_model):
+        try:
             model = self.load_model(selected_model)
-        if model is None:
+        except Exception as e:
+            print(f"Unable to load ESRGAN model {selected_model}: {e}", file=sys.stderr)
             return img
         model.to(devices.device_esrgan)
         img = esrgan_upscale(model, img)
         return img
 
     def load_model(self, path: str):
-        if "http" in path:
+        if path.startswith("http"):
-            filename = load_file_from_url(
+            # TODO: this doesn't use `path` at all?
+            filename = modelloader.load_file_from_url(
                 url=self.model_url,
-                model_dir=self.model_path,
+                model_dir=self.model_download_path,
                 file_name=f"{self.model_name}.pth",
-                progress=True,
             )
         else:
             filename = path
-        if not os.path.exists(filename) or filename is None:
-            print(f"Unable to load {self.model_path} from {filename}")
-            return None
 
         state_dict = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
 

modules/esrgan_model_arch.py

@@ -2,7 +2,6 @@
 
 from collections import OrderedDict
 import math
-import functools
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -438,9 +437,11 @@ def conv_block(in_nc, out_nc, kernel_size, stride=1, dilation=1, groups=1, bias=
     padding = padding if pad_type == 'zero' else 0
 
     if convtype=='PartialConv2D':
+        from torchvision.ops import PartialConv2d  # this is definitely not going to work, but PartialConv2d doesn't work anyway and this shuts up static analyzer
         c = PartialConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
                dilation=dilation, bias=bias, groups=groups)
     elif convtype=='DeformConv2D':
+        from torchvision.ops import DeformConv2d  # not tested
         c = DeformConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
                dilation=dilation, bias=bias, groups=groups)
     elif convtype=='Conv3D':

modules/extensions.py

@@ -1,18 +1,13 @@
 import os
-import sys
+import threading
-import traceback
 
-import time
+from modules import shared, errors
-from datetime import datetime
+from modules.gitpython_hack import Repo
-import git
+from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path  # noqa: F401
-
-from modules import shared
-from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path
 
 extensions = []
 
-if not os.path.exists(extensions_dir):
+os.makedirs(extensions_dir, exist_ok=True)
-    os.makedirs(extensions_dir)
 
 
 def active():
@@ -25,6 +20,8 @@ def active():
 
 
 class Extension:
+    lock = threading.Lock()
+
     def __init__(self, name, path, enabled=True, is_builtin=False):
         self.name = name
         self.path = path
@@ -43,15 +40,19 @@ class Extension:
         if self.is_builtin or self.have_info_from_repo:
             return
 
-        self.have_info_from_repo = True
+        with self.lock:
+            if self.have_info_from_repo:
+                return
 
+            self.do_read_info_from_repo()
+
+    def do_read_info_from_repo(self):
         repo = None
         try:
             if os.path.exists(os.path.join(self.path, ".git")):
-                repo = git.Repo(self.path)
+                repo = Repo(self.path)
         except Exception:
-            print(f"Error reading github repository info from {self.path}:", file=sys.stderr)
+            errors.report(f"Error reading github repository info from {self.path}", exc_info=True)
-            print(traceback.format_exc(), file=sys.stderr)
 
         if repo is None or repo.bare:
             self.remote = None
@@ -59,18 +60,19 @@ class Extension:
             try:
                 self.status = 'unknown'
                 self.remote = next(repo.remote().urls, None)
-                head = repo.head.commit
+                commit = repo.head.commit
-                self.commit_date = repo.head.commit.committed_date
+                self.commit_date = commit.committed_date
-                ts = time.asctime(time.gmtime(self.commit_date))
                 if repo.active_branch:
                     self.branch = repo.active_branch.name
-                self.commit_hash = head.hexsha
+                self.commit_hash = commit.hexsha
-                self.version = f'{self.commit_hash[:8]} ({ts})'
+                self.version = self.commit_hash[:8]
 
-            except Exception as ex:
+            except Exception:
-                print(f"Failed reading extension data from Git repository ({self.name}): {ex}", file=sys.stderr)
+                errors.report(f"Failed reading extension data from Git repository ({self.name})", exc_info=True)
                 self.remote = None
 
+        self.have_info_from_repo = True
+
     def list_files(self, subdir, extension):
         from modules import scripts
 
@@ -87,7 +89,7 @@ class Extension:
         return res
 
     def check_updates(self):
-        repo = git.Repo(self.path)
+        repo = Repo(self.path)
         for fetch in repo.remote().fetch(dry_run=True):
             if fetch.flags != fetch.HEAD_UPTODATE:
                 self.can_update = True
@@ -109,7 +111,7 @@ class Extension:
         self.status = "latest"
 
     def fetch_and_reset_hard(self, commit='origin'):
-        repo = git.Repo(self.path)
+        repo = Repo(self.path)
         # Fix: `error: Your local changes to the following files would be overwritten by merge`,
         # because WSL2 Docker set 755 file permissions instead of 644, this results to the error.
         repo.git.fetch(all=True)

modules/extra_networks.py

@@ -14,9 +14,26 @@ def register_extra_network(extra_network):
     extra_network_registry[extra_network.name] = extra_network
 
 
+def register_default_extra_networks():
+    from modules.extra_networks_hypernet import ExtraNetworkHypernet
+    register_extra_network(ExtraNetworkHypernet())
+
+
 class ExtraNetworkParams:
     def __init__(self, items=None):
         self.items = items or []
+        self.positional = []
+        self.named = {}
+
+        for item in self.items:
+            parts = item.split('=', 2) if isinstance(item, str) else [item]
+            if len(parts) == 2:
+                self.named[parts[0]] = parts[1]
+            else:
+                self.positional.append(item)
+
+    def __eq__(self, other):
+        return self.items == other.items
 
 
 class ExtraNetwork:
@@ -86,12 +103,15 @@ def activate(p, extra_network_data):
         except Exception as e:
             errors.display(e, f"activating extra network {extra_network_name}")
 
+    if p.scripts is not None:
+        p.scripts.after_extra_networks_activate(p, batch_number=p.iteration, prompts=p.prompts, seeds=p.seeds, subseeds=p.subseeds, extra_network_data=extra_network_data)
+
 
 def deactivate(p, extra_network_data):
     """call deactivate for extra networks in extra_network_data in specified order, then call
     deactivate for all remaining registered networks"""
 
-    for extra_network_name, extra_network_args in extra_network_data.items():
+    for extra_network_name in extra_network_data:
         extra_network = extra_network_registry.get(extra_network_name, None)
         if extra_network is None:
             continue

modules/extra_networks_hypernet.py

@@ -1,4 +1,4 @@
-from modules import extra_networks, shared, extra_networks
+from modules import extra_networks, shared
 from modules.hypernetworks import hypernetwork
 
 
@@ -9,7 +9,7 @@ class ExtraNetworkHypernet(extra_networks.ExtraNetwork):
     def activate(self, p, params_list):
         additional = shared.opts.sd_hypernetwork
 
-        if additional != "None" and additional in shared.hypernetworks and len([x for x in params_list if x.items[0] == additional]) == 0:
+        if additional != "None" and additional in shared.hypernetworks and not any(x for x in params_list if x.items[0] == additional):
             hypernet_prompt_text = f"<hypernet:{additional}:{shared.opts.extra_networks_default_multiplier}>"
             p.all_prompts = [f"{prompt}{hypernet_prompt_text}" for prompt in p.all_prompts]
             params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
@@ -17,7 +17,7 @@ class ExtraNetworkHypernet(extra_networks.ExtraNetwork):
         names = []
         multipliers = []
         for params in params_list:
-            assert len(params.items) > 0
+            assert params.items
 
             names.append(params.items[0])
             multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)

modules/extras.py

@@ -73,8 +73,7 @@ def to_half(tensor, enable):
 
 
 def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata):
-    shared.state.begin()
+    shared.state.begin(job="model-merge")
-    shared.state.job = 'model-merge'
 
     def fail(message):
         shared.state.textinfo = message
@@ -136,14 +135,14 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
     result_is_instruct_pix2pix_model = False
 
     if theta_func2:
-        shared.state.textinfo = f"Loading B"
+        shared.state.textinfo = "Loading B"
         print(f"Loading {secondary_model_info.filename}...")
         theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')
     else:
         theta_1 = None
 
     if theta_func1:
-        shared.state.textinfo = f"Loading C"
+        shared.state.textinfo = "Loading C"
         print(f"Loading {tertiary_model_info.filename}...")
         theta_2 = sd_models.read_state_dict(tertiary_model_info.filename, map_location='cpu')
 
@@ -242,9 +241,11 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
     shared.state.textinfo = "Saving"
     print(f"Saving to {output_modelname}...")
 
-    metadata = {"format": "pt", "sd_merge_models": {}, "sd_merge_recipe": None}
+    metadata = None
 
     if save_metadata:
+        metadata = {"format": "pt"}
+
         merge_recipe = {
             "type": "webui", # indicate this model was merged with webui's built-in merger
             "primary_model_hash": primary_model_info.sha256,
@@ -262,15 +263,17 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
         }
         metadata["sd_merge_recipe"] = json.dumps(merge_recipe)
 
+        sd_merge_models = {}
+
         def add_model_metadata(checkpoint_info):
             checkpoint_info.calculate_shorthash()
-            metadata["sd_merge_models"][checkpoint_info.sha256] = {
+            sd_merge_models[checkpoint_info.sha256] = {
                 "name": checkpoint_info.name,
                 "legacy_hash": checkpoint_info.hash,
                 "sd_merge_recipe": checkpoint_info.metadata.get("sd_merge_recipe", None)
             }
 
-            metadata["sd_merge_models"].update(checkpoint_info.metadata.get("sd_merge_models", {}))
+            sd_merge_models.update(checkpoint_info.metadata.get("sd_merge_models", {}))
 
         add_model_metadata(primary_model_info)
         if secondary_model_info:
@@ -278,7 +281,7 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
         if tertiary_model_info:
             add_model_metadata(tertiary_model_info)
 
-        metadata["sd_merge_models"] = json.dumps(metadata["sd_merge_models"])
+        metadata["sd_merge_models"] = json.dumps(sd_merge_models)
 
     _, extension = os.path.splitext(output_modelname)
     if extension.lower() == ".safetensors":

modules/generation_parameters_copypaste.py

@@ -1,15 +1,12 @@
 import base64
-import html
 import io
-import math
+import json
 import os
 import re
-from pathlib import Path
 
 import gradio as gr
 from modules.paths import data_path
 from modules import shared, ui_tempdir, script_callbacks
-import tempfile
 from PIL import Image
 
 re_param_code = r'\s*([\w ]+):\s*("(?:\\"[^,]|\\"|\\|[^\"])+"|[^,]*)(?:,|$)'
@@ -23,14 +20,14 @@ registered_param_bindings = []
 
 
 class ParamBinding:
-    def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None, paste_field_names=[]):
+    def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None, paste_field_names=None):
         self.paste_button = paste_button
         self.tabname = tabname
         self.source_text_component = source_text_component
         self.source_image_component = source_image_component
         self.source_tabname = source_tabname
         self.override_settings_component = override_settings_component
-        self.paste_field_names = paste_field_names
+        self.paste_field_names = paste_field_names or []
 
 
 def reset():
@@ -38,20 +35,27 @@ def reset():
 
 
 def quote(text):
-    if ',' not in str(text):
+    if ',' not in str(text) and '\n' not in str(text) and ':' not in str(text):
         return text
 
-    text = str(text)
+    return json.dumps(text, ensure_ascii=False)
-    text = text.replace('\\', '\\\\')
+
-    text = text.replace('"', '\\"')
+
-    return f'"{text}"'
+def unquote(text):
+    if len(text) == 0 or text[0] != '"' or text[-1] != '"':
+        return text
+
+    try:
+        return json.loads(text)
+    except Exception:
+        return text
 
 
 def image_from_url_text(filedata):
     if filedata is None:
         return None
 
-    if type(filedata) == list and len(filedata) > 0 and type(filedata[0]) == dict and filedata[0].get("is_file", False):
+    if type(filedata) == list and filedata and type(filedata[0]) == dict and filedata[0].get("is_file", False):
         filedata = filedata[0]
 
     if type(filedata) == dict and filedata.get("is_file", False):
@@ -170,31 +174,6 @@ def send_image_and_dimensions(x):
     return img, w, h
 
 
-
-def find_hypernetwork_key(hypernet_name, hypernet_hash=None):
-    """Determines the config parameter name to use for the hypernet based on the parameters in the infotext.
-
-    Example: an infotext provides "Hypernet: ke-ta" and "Hypernet hash: 1234abcd". For the "Hypernet" config
-    parameter this means there should be an entry that looks like "ke-ta-10000(1234abcd)" to set it to.
-
-    If the infotext has no hash, then a hypernet with the same name will be selected instead.
-    """
-    hypernet_name = hypernet_name.lower()
-    if hypernet_hash is not None:
-        # Try to match the hash in the name
-        for hypernet_key in shared.hypernetworks.keys():
-            result = re_hypernet_hash.search(hypernet_key)
-            if result is not None and result[1] == hypernet_hash:
-                return hypernet_key
-    else:
-        # Fall back to a hypernet with the same name
-        for hypernet_key in shared.hypernetworks.keys():
-            if hypernet_key.lower().startswith(hypernet_name):
-                return hypernet_key
-
-    return None
-
-
 def restore_old_hires_fix_params(res):
     """for infotexts that specify old First pass size parameter, convert it into
     width, height, and hr scale"""
@@ -251,28 +230,40 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         lines.append(lastline)
         lastline = ''
 
-    for i, line in enumerate(lines):
+    for line in lines:
         line = line.strip()
         if line.startswith("Negative prompt:"):
             done_with_prompt = True
             line = line[16:].strip()
-
         if done_with_prompt:
             negative_prompt += ("" if negative_prompt == "" else "\n") + line
         else:
             prompt += ("" if prompt == "" else "\n") + line
 
+    if shared.opts.infotext_styles != "Ignore":
+        found_styles, prompt, negative_prompt = shared.prompt_styles.extract_styles_from_prompt(prompt, negative_prompt)
+
+        if shared.opts.infotext_styles == "Apply":
+            res["Styles array"] = found_styles
+        elif shared.opts.infotext_styles == "Apply if any" and found_styles:
+            res["Styles array"] = found_styles
+
     res["Prompt"] = prompt
     res["Negative prompt"] = negative_prompt
 
     for k, v in re_param.findall(lastline):
-        v = v[1:-1] if v[0] == '"' and v[-1] == '"' else v
+        try:
+            if v[0] == '"' and v[-1] == '"':
+                v = unquote(v)
+
             m = re_imagesize.match(v)
             if m is not None:
                 res[f"{k}-1"] = m.group(1)
                 res[f"{k}-2"] = m.group(2)
             else:
                 res[k] = v
+        except Exception:
+            print(f"Error parsing \"{k}: {v}\"")
 
     # Missing CLIP skip means it was set to 1 (the default)
     if "Clip skip" not in res:
@@ -286,24 +277,45 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         res["Hires resize-1"] = 0
         res["Hires resize-2"] = 0
 
+    if "Hires sampler" not in res:
+        res["Hires sampler"] = "Use same sampler"
+
+    if "Hires prompt" not in res:
+        res["Hires prompt"] = ""
+
+    if "Hires negative prompt" not in res:
+        res["Hires negative prompt"] = ""
+
     restore_old_hires_fix_params(res)
 
     # Missing RNG means the default was set, which is GPU RNG
     if "RNG" not in res:
         res["RNG"] = "GPU"
 
+    if "Schedule type" not in res:
+        res["Schedule type"] = "Automatic"
+
+    if "Schedule max sigma" not in res:
+        res["Schedule max sigma"] = 0
+
+    if "Schedule min sigma" not in res:
+        res["Schedule min sigma"] = 0
+
+    if "Schedule rho" not in res:
+        res["Schedule rho"] = 0
+
     return res
 
 
-settings_map = {}
-
-
-
 infotext_to_setting_name_mapping = [
     ('Clip skip', 'CLIP_stop_at_last_layers', ),
     ('Conditional mask weight', 'inpainting_mask_weight'),
     ('Model hash', 'sd_model_checkpoint'),
     ('ENSD', 'eta_noise_seed_delta'),
+    ('Schedule type', 'k_sched_type'),
+    ('Schedule max sigma', 'sigma_max'),
+    ('Schedule min sigma', 'sigma_min'),
+    ('Schedule rho', 'rho'),
     ('Noise multiplier', 'initial_noise_multiplier'),
     ('Eta', 'eta_ancestral'),
     ('Eta DDIM', 'eta_ddim'),
@@ -312,8 +324,11 @@ infotext_to_setting_name_mapping = [
     ('UniPC skip type', 'uni_pc_skip_type'),
     ('UniPC order', 'uni_pc_order'),
     ('UniPC lower order final', 'uni_pc_lower_order_final'),
+    ('Token merging ratio', 'token_merging_ratio'),
+    ('Token merging ratio hr', 'token_merging_ratio_hr'),
     ('RNG', 'randn_source'),
     ('NGMS', 's_min_uncond'),
+    ('Pad conds', 'pad_cond_uncond'),
 ]
 
 
@@ -405,7 +420,7 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
 
             vals_pairs = [f"{k}: {v}" for k, v in vals.items()]
 
-            return gr.Dropdown.update(value=vals_pairs, choices=vals_pairs, visible=len(vals_pairs) > 0)
+            return gr.Dropdown.update(value=vals_pairs, choices=vals_pairs, visible=bool(vals_pairs))
 
         paste_fields = paste_fields + [(override_settings_component, paste_settings)]
 
@@ -422,5 +437,3 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
         outputs=[],
         show_progress=False,
     )
-
-

modules/gfpgan_model.py

@@ -1,12 +1,10 @@
 import os
-import sys
-import traceback
 
 import facexlib
 import gfpgan
 
 import modules.face_restoration
-from modules import paths, shared, devices, modelloader
+from modules import paths, shared, devices, modelloader, errors
 
 model_dir = "GFPGAN"
 user_path = None
@@ -27,7 +25,7 @@ def gfpgann():
         return None
 
     models = modelloader.load_models(model_path, model_url, user_path, ext_filter="GFPGAN")
-    if len(models) == 1 and "http" in models[0]:
+    if len(models) == 1 and models[0].startswith("http"):
         model_file = models[0]
     elif len(models) != 0:
         latest_file = max(models, key=os.path.getctime)
@@ -72,13 +70,10 @@ gfpgan_constructor = None
 
 
 def setup_model(dirname):
-    global model_path
-    if not os.path.exists(model_path):
-        os.makedirs(model_path)
-
     try:
+        os.makedirs(model_path, exist_ok=True)
         from gfpgan import GFPGANer
-        from facexlib import detection, parsing
+        from facexlib import detection, parsing  # noqa: F401
         global user_path
         global have_gfpgan
         global gfpgan_constructor
@@ -112,5 +107,4 @@ def setup_model(dirname):
 
         shared.face_restorers.append(FaceRestorerGFPGAN())
     except Exception:
-        print("Error setting up GFPGAN:", file=sys.stderr)
+        errors.report("Error setting up GFPGAN", exc_info=True)
-        print(traceback.format_exc(), file=sys.stderr)

modules/gitpython_hack.py

@@ -0,0 +1,42 @@
+from __future__ import annotations
+
+import io
+import subprocess
+
+import git
+
+
+class Git(git.Git):
+    """
+    Git subclassed to never use persistent processes.
+    """
+
+    def _get_persistent_cmd(self, attr_name, cmd_name, *args, **kwargs):
+        raise NotImplementedError(f"Refusing to use persistent process: {attr_name} ({cmd_name} {args} {kwargs})")
+
+    def get_object_header(self, ref: str | bytes) -> tuple[str, str, int]:
+        ret = subprocess.check_output(
+            [self.GIT_PYTHON_GIT_EXECUTABLE, "cat-file", "--batch-check"],
+            input=self._prepare_ref(ref),
+            cwd=self._working_dir,
+            timeout=2,
+        )
+        return self._parse_object_header(ret)
+
+    def stream_object_data(self, ref: str) -> tuple[str, str, int, "Git.CatFileContentStream"]:
+        # Not really streaming, per se; this buffers the entire object in memory.
+        # Shouldn't be a problem for our use case, since we're only using this for
+        # object headers (commit objects).
+        ret = subprocess.check_output(
+            [self.GIT_PYTHON_GIT_EXECUTABLE, "cat-file", "--batch"],
+            input=self._prepare_ref(ref),
+            cwd=self._working_dir,
+            timeout=30,
+        )
+        bio = io.BytesIO(ret)
+        hexsha, typename, size = self._parse_object_header(bio.readline())
+        return (hexsha, typename, size, self.CatFileContentStream(size, bio))
+
+
+class Repo(git.Repo):
+    GitCommandWrapperType = Git

modules/hashes.py

@@ -46,8 +46,8 @@ def calculate_sha256(filename):
     return hash_sha256.hexdigest()
 
 
-def sha256_from_cache(filename, title):
+def sha256_from_cache(filename, title, use_addnet_hash=False):
-    hashes = cache("hashes")
+    hashes = cache("hashes-addnet") if use_addnet_hash else cache("hashes")
     ondisk_mtime = os.path.getmtime(filename)
 
     if title not in hashes:
@@ -62,10 +62,10 @@ def sha256_from_cache(filename, title):
     return cached_sha256
 
 
-def sha256(filename, title):
+def sha256(filename, title, use_addnet_hash=False):
-    hashes = cache("hashes")
+    hashes = cache("hashes-addnet") if use_addnet_hash else cache("hashes")
 
-    sha256_value = sha256_from_cache(filename, title)
+    sha256_value = sha256_from_cache(filename, title, use_addnet_hash)
     if sha256_value is not None:
         return sha256_value
 
@@ -73,6 +73,10 @@ def sha256(filename, title):
         return None
 
     print(f"Calculating sha256 for {filename}: ", end='')
+    if use_addnet_hash:
+        with open(filename, "rb") as file:
+            sha256_value = addnet_hash_safetensors(file)
+    else:
         sha256_value = calculate_sha256(filename)
     print(f"{sha256_value}")
 
@@ -86,6 +90,19 @@ def sha256(filename, title):
     return sha256_value
 
 
+def addnet_hash_safetensors(b):
+    """kohya-ss hash for safetensors from https://github.com/kohya-ss/sd-scripts/blob/main/library/train_util.py"""
+    hash_sha256 = hashlib.sha256()
+    blksize = 1024 * 1024
 
+    b.seek(0)
+    header = b.read(8)
+    n = int.from_bytes(header, "little")
 
+    offset = n + 8
+    b.seek(offset)
+    for chunk in iter(lambda: b.read(blksize), b""):
+        hash_sha256.update(chunk)
+
+    return hash_sha256.hexdigest()
 

modules/hypernetworks/hypernetwork.py

@@ -1,10 +1,7 @@
-import csv
 import datetime
 import glob
 import html
 import os
-import sys
-import traceback
 import inspect
 
 import modules.textual_inversion.dataset
@@ -12,13 +9,13 @@ import torch
 import tqdm
 from einops import rearrange, repeat
 from ldm.util import default
-from modules import devices, processing, sd_models, shared, sd_samplers, hashes, sd_hijack_checkpoint
+from modules import devices, processing, sd_models, shared, sd_samplers, hashes, sd_hijack_checkpoint, errors
 from modules.textual_inversion import textual_inversion, logging
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
 from torch import einsum
 from torch.nn.init import normal_, xavier_normal_, xavier_uniform_, kaiming_normal_, kaiming_uniform_, zeros_
 
-from collections import defaultdict, deque
+from collections import deque
 from statistics import stdev, mean
 
 
@@ -178,34 +175,34 @@ class Hypernetwork:
 
     def weights(self):
         res = []
-        for k, layers in self.layers.items():
+        for layers in self.layers.values():
             for layer in layers:
                 res += layer.parameters()
         return res
 
     def train(self, mode=True):
-        for k, layers in self.layers.items():
+        for layers in self.layers.values():
             for layer in layers:
                 layer.train(mode=mode)
                 for param in layer.parameters():
                     param.requires_grad = mode
 
     def to(self, device):
-        for k, layers in self.layers.items():
+        for layers in self.layers.values():
             for layer in layers:
                 layer.to(device)
 
         return self
 
     def set_multiplier(self, multiplier):
-        for k, layers in self.layers.items():
+        for layers in self.layers.values():
             for layer in layers:
                 layer.multiplier = multiplier
 
         return self
 
     def eval(self):
-        for k, layers in self.layers.items():
+        for layers in self.layers.values():
             for layer in layers:
                 layer.eval()
                 for param in layer.parameters():
@@ -326,16 +323,13 @@ def load_hypernetwork(name):
     if path is None:
         return None
 
-    hypernetwork = Hypernetwork()
-
     try:
+        hypernetwork = Hypernetwork()
         hypernetwork.load(path)
-    except Exception:
-        print(f"Error loading hypernetwork {path}", file=sys.stderr)
-        print(traceback.format_exc(), file=sys.stderr)
-        return None
-
         return hypernetwork
+    except Exception:
+        errors.report(f"Error loading hypernetwork {path}", exc_info=True)
+        return None
 
 
 def load_hypernetworks(names, multipliers=None):
@@ -359,17 +353,6 @@ def load_hypernetworks(names, multipliers=None):
         shared.loaded_hypernetworks.append(hypernetwork)
 
 
-def find_closest_hypernetwork_name(search: str):
-    if not search:
-        return None
-    search = search.lower()
-    applicable = [name for name in shared.hypernetworks if search in name.lower()]
-    if not applicable:
-        return None
-    applicable = sorted(applicable, key=lambda name: len(name))
-    return applicable[0]
-
-
 def apply_single_hypernetwork(hypernetwork, context_k, context_v, layer=None):
     hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context_k.shape[2], None)
 
@@ -404,7 +387,7 @@ def attention_CrossAttention_forward(self, x, context=None, mask=None):
     k = self.to_k(context_k)
     v = self.to_v(context_v)
 
-    q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
+    q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q, k, v))
 
     sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
 
@@ -452,18 +435,6 @@ def statistics(data):
     return total_information, recent_information
 
 
-def report_statistics(loss_info:dict):
-    keys = sorted(loss_info.keys(), key=lambda x: sum(loss_info[x]) / len(loss_info[x]))
-    for key in keys:
-        try:
-            print("Loss statistics for file " + key)
-            info, recent = statistics(list(loss_info[key]))
-            print(info)
-            print(recent)
-        except Exception as e:
-            print(e)
-
-
 def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False, dropout_structure=None):
     # Remove illegal characters from name.
     name = "".join( x for x in name if (x.isalnum() or x in "._- "))
@@ -620,7 +591,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
     try:
         sd_hijack_checkpoint.add()
 
-        for i in range((steps-initial_step) * gradient_step):
+        for _ in range((steps-initial_step) * gradient_step):
             if scheduler.finished:
                 break
             if shared.state.interrupted:
@@ -771,12 +742,11 @@ Last saved image: {html.escape(last_saved_image)}<br/>
 </p>
 """
     except Exception:
-        print(traceback.format_exc(), file=sys.stderr)
+        errors.report("Exception in training hypernetwork", exc_info=True)
     finally:
         pbar.leave = False
         pbar.close()
         hypernetwork.eval()
-        #report_statistics(loss_dict)
         sd_hijack_checkpoint.remove()
 
 

modules/hypernetworks/ui.py

@@ -1,19 +1,17 @@
 import html
-import os
-import re
 
 import gradio as gr
 import modules.hypernetworks.hypernetwork
 from modules import devices, sd_hijack, shared
 
 not_available = ["hardswish", "multiheadattention"]
-keys = list(x for x in modules.hypernetworks.hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available)
+keys = [x for x in modules.hypernetworks.hypernetwork.HypernetworkModule.activation_dict if x not in not_available]
 
 
 def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False, dropout_structure=None):
     filename = modules.hypernetworks.hypernetwork.create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure, activation_func, weight_init, add_layer_norm, use_dropout, dropout_structure)
 
-    return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {filename}", ""
+    return gr.Dropdown.update(choices=sorted(shared.hypernetworks)), f"Created: {filename}", ""
 
 
 def train_hypernetwork(*args):

modules/images.py

@@ -1,6 +1,6 @@
+from __future__ import annotations
+
 import datetime
-import sys
-import traceback
 
 import pytz
 import io
@@ -12,18 +12,27 @@ import re
 import numpy as np
 import piexif
 import piexif.helper
-from PIL import Image, ImageFont, ImageDraw, PngImagePlugin
+from PIL import Image, ImageFont, ImageDraw, ImageColor, PngImagePlugin
-from fonts.ttf import Roboto
 import string
 import json
 import hashlib
 
 from modules import sd_samplers, shared, script_callbacks, errors
-from modules.shared import opts, cmd_opts
+from modules.paths_internal import roboto_ttf_file
+from modules.shared import opts
+
+import modules.sd_vae as sd_vae
 
 LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)
 
 
+def get_font(fontsize: int):
+    try:
+        return ImageFont.truetype(opts.font or roboto_ttf_file, fontsize)
+    except Exception:
+        return ImageFont.truetype(roboto_ttf_file, fontsize)
+
+
 def image_grid(imgs, batch_size=1, rows=None):
     if rows is None:
         if opts.n_rows > 0:
@@ -132,6 +141,11 @@ class GridAnnotation:
 
 
 def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
+
+    color_active = ImageColor.getcolor(opts.grid_text_active_color, 'RGB')
+    color_inactive = ImageColor.getcolor(opts.grid_text_inactive_color, 'RGB')
+    color_background = ImageColor.getcolor(opts.grid_background_color, 'RGB')
+
     def wrap(drawing, text, font, line_length):
         lines = ['']
         for word in text.split():
@@ -142,14 +156,8 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
                 lines.append(word)
         return lines
 
-    def get_font(fontsize):
-        try:
-            return ImageFont.truetype(opts.font or Roboto, fontsize)
-        except Exception:
-            return ImageFont.truetype(Roboto, fontsize)
-
     def draw_texts(drawing, draw_x, draw_y, lines, initial_fnt, initial_fontsize):
-        for i, line in enumerate(lines):
+        for line in lines:
             fnt = initial_fnt
             fontsize = initial_fontsize
             while drawing.multiline_textsize(line.text, font=fnt)[0] > line.allowed_width and fontsize > 0:
@@ -167,9 +175,6 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
 
     fnt = get_font(fontsize)
 
-    color_active = (0, 0, 0)
-    color_inactive = (153, 153, 153)
-
     pad_left = 0 if sum([sum([len(line.text) for line in lines]) for lines in ver_texts]) == 0 else width * 3 // 4
 
     cols = im.width // width
@@ -178,7 +183,7 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
     assert cols == len(hor_texts), f'bad number of horizontal texts: {len(hor_texts)}; must be {cols}'
     assert rows == len(ver_texts), f'bad number of vertical texts: {len(ver_texts)}; must be {rows}'
 
-    calc_img = Image.new("RGB", (1, 1), "white")
+    calc_img = Image.new("RGB", (1, 1), color_background)
     calc_d = ImageDraw.Draw(calc_img)
 
     for texts, allowed_width in zip(hor_texts + ver_texts, [width] * len(hor_texts) + [pad_left] * len(ver_texts)):
@@ -199,7 +204,7 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
 
     pad_top = 0 if sum(hor_text_heights) == 0 else max(hor_text_heights) + line_spacing * 2
 
-    result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), "white")
+    result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), color_background)
 
     for row in range(rows):
         for col in range(cols):
@@ -335,8 +340,20 @@ def sanitize_filename_part(text, replace_spaces=True):
 
 
 class FilenameGenerator:
+    def get_vae_filename(self): #get the name of the VAE file.
+        if sd_vae.loaded_vae_file is None:
+            return "NoneType"
+        file_name = os.path.basename(sd_vae.loaded_vae_file)
+        split_file_name = file_name.split('.')
+        if len(split_file_name) > 1 and split_file_name[0] == '':
+            return split_file_name[1] # if the first character of the filename is "." then [1] is obtained.
+        else:
+            return split_file_name[0]
+
     replacements = {
         'seed': lambda self: self.seed if self.seed is not None else '',
+        'seed_first': lambda self: self.seed if self.p.batch_size == 1 else self.p.all_seeds[0],
+        'seed_last': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.batch_size == 1 else self.p.all_seeds[-1],
         'steps': lambda self:  self.p and self.p.steps,
         'cfg': lambda self: self.p and self.p.cfg_scale,
         'width': lambda self: self.image.width,
@@ -353,19 +370,23 @@ class FilenameGenerator:
         'prompt_no_styles': lambda self: self.prompt_no_style(),
         'prompt_spaces': lambda self: sanitize_filename_part(self.prompt, replace_spaces=False),
         'prompt_words': lambda self: self.prompt_words(),
-        'batch_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.batch_size == 1 else self.p.batch_index + 1,
+        'batch_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.batch_size == 1 or self.zip else self.p.batch_index + 1,
-        'generation_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.n_iter == 1 and self.p.batch_size == 1 else self.p.iteration * self.p.batch_size + self.p.batch_index + 1,
+        'batch_size': lambda self: self.p.batch_size,
+        'generation_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if (self.p.n_iter == 1 and self.p.batch_size == 1) or self.zip else self.p.iteration * self.p.batch_size + self.p.batch_index + 1,
         'hasprompt': lambda self, *args: self.hasprompt(*args),  # accepts formats:[hasprompt<prompt1|default><prompt2>..]
         'clip_skip': lambda self: opts.data["CLIP_stop_at_last_layers"],
         'denoising': lambda self: self.p.denoising_strength if self.p and self.p.denoising_strength else NOTHING_AND_SKIP_PREVIOUS_TEXT,
+        'user': lambda self: self.p.user,
+        'vae_filename': lambda self: self.get_vae_filename(),
     }
     default_time_format = '%Y%m%d%H%M%S'
 
-    def __init__(self, p, seed, prompt, image):
+    def __init__(self, p, seed, prompt, image, zip=False):
         self.p = p
         self.seed = seed
         self.prompt = prompt
         self.image = image
+        self.zip = zip
 
     def hasprompt(self, *args):
         lower = self.prompt.lower()
@@ -389,7 +410,7 @@ class FilenameGenerator:
 
         prompt_no_style = self.prompt
         for style in shared.prompt_styles.get_style_prompts(self.p.styles):
-            if len(style) > 0:
+            if style:
                 for part in style.split("{prompt}"):
                     prompt_no_style = prompt_no_style.replace(part, "").replace(", ,", ",").strip().strip(',')
 
@@ -398,7 +419,7 @@ class FilenameGenerator:
         return sanitize_filename_part(prompt_no_style, replace_spaces=False)
 
     def prompt_words(self):
-        words = [x for x in re_nonletters.split(self.prompt or "") if len(x) > 0]
+        words = [x for x in re_nonletters.split(self.prompt or "") if x]
         if len(words) == 0:
             words = ["empty"]
         return sanitize_filename_part(" ".join(words[0:opts.directories_max_prompt_words]), replace_spaces=False)
@@ -406,16 +427,16 @@ class FilenameGenerator:
     def datetime(self, *args):
         time_datetime = datetime.datetime.now()
 
-        time_format = args[0] if len(args) > 0 and args[0] != "" else self.default_time_format
+        time_format = args[0] if (args and args[0] != "") else self.default_time_format
         try:
             time_zone = pytz.timezone(args[1]) if len(args) > 1 else None
-        except pytz.exceptions.UnknownTimeZoneError as _:
+        except pytz.exceptions.UnknownTimeZoneError:
             time_zone = None
 
         time_zone_time = time_datetime.astimezone(time_zone)
         try:
             formatted_time = time_zone_time.strftime(time_format)
-        except (ValueError, TypeError) as _:
+        except (ValueError, TypeError):
             formatted_time = time_zone_time.strftime(self.default_time_format)
 
         return sanitize_filename_part(formatted_time, replace_spaces=False)
@@ -445,8 +466,7 @@ class FilenameGenerator:
                     replacement = fun(self, *pattern_args)
                 except Exception:
                     replacement = None
-                    print(f"Error adding [{pattern}] to filename", file=sys.stderr)
+                    errors.report(f"Error adding [{pattern}] to filename", exc_info=True)
-                    print(traceback.format_exc(), file=sys.stderr)
 
                 if replacement == NOTHING_AND_SKIP_PREVIOUS_TEXT:
                     continue
@@ -472,15 +492,61 @@ def get_next_sequence_number(path, basename):
     prefix_length = len(basename)
     for p in os.listdir(path):
         if p.startswith(basename):
-            l = os.path.splitext(p[prefix_length:])[0].split('-')  # splits the filename (removing the basename first if one is defined, so the sequence number is always the first element)
+            parts = os.path.splitext(p[prefix_length:])[0].split('-')  # splits the filename (removing the basename first if one is defined, so the sequence number is always the first element)
             try:
-                result = max(int(l[0]), result)
+                result = max(int(parts[0]), result)
             except ValueError:
                 pass
 
     return result + 1
 
 
+def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_pnginfo=None, pnginfo_section_name='parameters'):
+    """
+    Saves image to filename, including geninfo as text information for generation info.
+    For PNG images, geninfo is added to existing pnginfo dictionary using the pnginfo_section_name argument as key.
+    For JPG images, there's no dictionary and geninfo just replaces the EXIF description.
+    """
+
+    if extension is None:
+        extension = os.path.splitext(filename)[1]
+
+    image_format = Image.registered_extensions()[extension]
+
+    if extension.lower() == '.png':
+        existing_pnginfo = existing_pnginfo or {}
+        if opts.enable_pnginfo:
+            existing_pnginfo[pnginfo_section_name] = geninfo
+
+        if opts.enable_pnginfo:
+            pnginfo_data = PngImagePlugin.PngInfo()
+            for k, v in (existing_pnginfo or {}).items():
+                pnginfo_data.add_text(k, str(v))
+        else:
+            pnginfo_data = None
+
+        image.save(filename, format=image_format, quality=opts.jpeg_quality, pnginfo=pnginfo_data)
+
+    elif extension.lower() in (".jpg", ".jpeg", ".webp"):
+        if image.mode == 'RGBA':
+            image = image.convert("RGB")
+        elif image.mode == 'I;16':
+            image = image.point(lambda p: p * 0.0038910505836576).convert("RGB" if extension.lower() == ".webp" else "L")
+
+        image.save(filename, format=image_format, quality=opts.jpeg_quality, lossless=opts.webp_lossless)
+
+        if opts.enable_pnginfo and geninfo is not None:
+            exif_bytes = piexif.dump({
+                "Exif": {
+                    piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(geninfo or "", encoding="unicode")
+                },
+            })
+
+            piexif.insert(exif_bytes, filename)
+    else:
+        image.save(filename, format=image_format, quality=opts.jpeg_quality)
+
+
 def save_image(image, path, basename, seed=None, prompt=None, extension='png', info=None, short_filename=False, no_prompt=False, grid=False, pnginfo_section_name='parameters', p=None, existing_info=None, forced_filename=None, suffix="", save_to_dirs=None):
     """Save an image.
 
@@ -565,38 +631,13 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     info = params.pnginfo.get(pnginfo_section_name, None)
 
     def _atomically_save_image(image_to_save, filename_without_extension, extension):
-        # save image with .tmp extension to avoid race condition when another process detects new image in the directory
+        """
+        save image with .tmp extension to avoid race condition when another process detects new image in the directory
+        """
         temp_file_path = f"{filename_without_extension}.tmp"
-        image_format = Image.registered_extensions()[extension]
 
-        if extension.lower() == '.png':
+        save_image_with_geninfo(image_to_save, info, temp_file_path, extension, existing_pnginfo=params.pnginfo, pnginfo_section_name=pnginfo_section_name)
-            pnginfo_data = PngImagePlugin.PngInfo()
-            if opts.enable_pnginfo:
-                for k, v in params.pnginfo.items():
-                    pnginfo_data.add_text(k, str(v))
 
-            image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality, pnginfo=pnginfo_data)
-
-        elif extension.lower() in (".jpg", ".jpeg", ".webp"):
-            if image_to_save.mode == 'RGBA':
-                image_to_save = image_to_save.convert("RGB")
-            elif image_to_save.mode == 'I;16':
-                image_to_save = image_to_save.point(lambda p: p * 0.0038910505836576).convert("RGB" if extension.lower() == ".webp" else "L")
-
-            image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality, lossless=opts.webp_lossless)
-
-            if opts.enable_pnginfo and info is not None:
-                exif_bytes = piexif.dump({
-                    "Exif": {
-                        piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(info or "", encoding="unicode")
-                    },
-                })
-
-                piexif.insert(exif_bytes, temp_file_path)
-        else:
-            image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality)
-
-        # atomically rename the file with correct extension
         os.replace(temp_file_path, filename_without_extension + extension)
 
     fullfn_without_extension, extension = os.path.splitext(params.filename)
@@ -612,12 +653,18 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     oversize = image.width > opts.target_side_length or image.height > opts.target_side_length
     if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > opts.img_downscale_threshold * 1024 * 1024):
         ratio = image.width / image.height
-
+        resize_to = None
         if oversize and ratio > 1:
-            image = image.resize((round(opts.target_side_length), round(image.height * opts.target_side_length / image.width)), LANCZOS)
+            resize_to = round(opts.target_side_length), round(image.height * opts.target_side_length / image.width)
         elif oversize:
-            image = image.resize((round(image.width * opts.target_side_length / image.height), round(opts.target_side_length)), LANCZOS)
+            resize_to = round(image.width * opts.target_side_length / image.height), round(opts.target_side_length)
 
+        if resize_to is not None:
+            try:
+                # Resizing image with LANCZOS could throw an exception if e.g. image mode is I;16
+                image = image.resize(resize_to, LANCZOS)
+            except Exception:
+                image = image.resize(resize_to)
         try:
             _atomically_save_image(image, fullfn_without_extension, ".jpg")
         except Exception as e:
@@ -635,8 +682,15 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     return fullfn, txt_fullfn
 
 
-def read_info_from_image(image):
+IGNORED_INFO_KEYS = {
-    items = image.info or {}
+    'jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',
+    'loop', 'background', 'timestamp', 'duration', 'progressive', 'progression',
+    'icc_profile', 'chromaticity', 'photoshop',
+}
+
+
+def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]:
+    items = (image.info or {}).copy()
 
     geninfo = items.pop('parameters', None)
 
@@ -652,8 +706,7 @@ def read_info_from_image(image):
             items['exif comment'] = exif_comment
             geninfo = exif_comment
 
-        for field in ['jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',
+    for field in IGNORED_INFO_KEYS:
-                      'loop', 'background', 'timestamp', 'duration']:
         items.pop(field, None)
 
     if items.get("Software", None) == "NovelAI":
@@ -665,8 +718,7 @@ def read_info_from_image(image):
 Negative prompt: {json_info["uc"]}
 Steps: {json_info["steps"]}, Sampler: {sampler}, CFG scale: {json_info["scale"]}, Seed: {json_info["seed"]}, Size: {image.width}x{image.height}, Clip skip: 2, ENSD: 31337"""
         except Exception:
-            print("Error parsing NovelAI image generation parameters:", file=sys.stderr)
+            errors.report("Error parsing NovelAI image generation parameters", exc_info=True)
-            print(traceback.format_exc(), file=sys.stderr)
 
     return geninfo, items
 

modules/img2img.py

@@ -1,23 +1,21 @@
-import math
 import os
-import sys
+from pathlib import Path
-import traceback
 
 import numpy as np
 from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops, UnidentifiedImageError
+import gradio as gr
 
-from modules import devices, sd_samplers
+from modules import sd_samplers, images as imgutil
-from modules.generation_parameters_copypaste import create_override_settings_dict
+from modules.generation_parameters_copypaste import create_override_settings_dict, parse_generation_parameters
 from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
 from modules.shared import opts, state
 import modules.shared as shared
 import modules.processing as processing
 from modules.ui import plaintext_to_html
-import modules.images as images
 import modules.scripts
 
 
-def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args):
+def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
     processing.fix_seed(p)
 
     images = []
@@ -31,7 +29,8 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args):
     is_inpaint_batch = False
     if inpaint_mask_dir:
         inpaint_masks = shared.listfiles(inpaint_mask_dir)
-        is_inpaint_batch = len(inpaint_masks) > 0
+        is_inpaint_batch = bool(inpaint_masks)
+
         if is_inpaint_batch:
             print(f"\nInpaint batch is enabled. {len(inpaint_masks)} masks found.")
 
@@ -44,6 +43,14 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args):
 
     state.job_count = len(images) * p.n_iter
 
+    # extract "default" params to use in case getting png info fails
+    prompt = p.prompt
+    negative_prompt = p.negative_prompt
+    seed = p.seed
+    cfg_scale = p.cfg_scale
+    sampler_name = p.sampler_name
+    steps = p.steps
+
     for i, image in enumerate(images):
         state.job = f"{i+1} out of {len(images)}"
         if state.skipped:
@@ -59,23 +66,59 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args):
             continue
         # Use the EXIF orientation of photos taken by smartphones.
         img = ImageOps.exif_transpose(img)
+
+        if to_scale:
+            p.width = int(img.width * scale_by)
+            p.height = int(img.height * scale_by)
+
         p.init_images = [img] * p.batch_size
 
+        image_path = Path(image)
         if is_inpaint_batch:
             # try to find corresponding mask for an image using simple filename matching
-            mask_image_path = os.path.join(inpaint_mask_dir, os.path.basename(image))
+            if len(inpaint_masks) == 1:
-            # if not found use first one ("same mask for all images" use-case)
-            if not mask_image_path in inpaint_masks:
                 mask_image_path = inpaint_masks[0]
+            else:
+                # try to find corresponding mask for an image using simple filename matching
+                mask_image_dir = Path(inpaint_mask_dir)
+                masks_found = list(mask_image_dir.glob(f"{image_path.stem}.*"))
+
+                if len(masks_found) == 0:
+                    print(f"Warning: mask is not found for {image_path} in {mask_image_dir}. Skipping it.")
+                    continue
+
+                # it should contain only 1 matching mask
+                # otherwise user has many masks with the same name but different extensions
+                mask_image_path = masks_found[0]
+
             mask_image = Image.open(mask_image_path)
             p.image_mask = mask_image
 
+        if use_png_info:
+            try:
+                info_img = img
+                if png_info_dir:
+                    info_img_path = os.path.join(png_info_dir, os.path.basename(image))
+                    info_img = Image.open(info_img_path)
+                geninfo, _ = imgutil.read_info_from_image(info_img)
+                parsed_parameters = parse_generation_parameters(geninfo)
+                parsed_parameters = {k: v for k, v in parsed_parameters.items() if k in (png_info_props or {})}
+            except Exception:
+                parsed_parameters = {}
+
+            p.prompt = prompt + (" " + parsed_parameters["Prompt"] if "Prompt" in parsed_parameters else "")
+            p.negative_prompt = negative_prompt + (" " + parsed_parameters["Negative prompt"] if "Negative prompt" in parsed_parameters else "")
+            p.seed = int(parsed_parameters.get("Seed", seed))
+            p.cfg_scale = float(parsed_parameters.get("CFG scale", cfg_scale))
+            p.sampler_name = parsed_parameters.get("Sampler", sampler_name)
+            p.steps = int(parsed_parameters.get("Steps", steps))
+
         proc = modules.scripts.scripts_img2img.run(p, *args)
         if proc is None:
             proc = process_images(p)
 
         for n, processed_image in enumerate(proc.images):
-            filename = os.path.basename(image)
+            filename = image_path.name
             relpath = os.path.dirname(os.path.relpath(image, input_dir))
 
             if n > 0:
@@ -89,7 +132,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args):
                 processed_image.save(os.path.join(output_dir, relpath, filename))
 
 
-def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args):
+def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *args):
     override_settings = create_override_settings_dict(override_settings_texts)
 
     is_batch = mode == 5
@@ -103,7 +146,8 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     elif mode == 2:  # inpaint
         image, mask = init_img_with_mask["image"], init_img_with_mask["mask"]
         alpha_mask = ImageOps.invert(image.split()[-1]).convert('L').point(lambda x: 255 if x > 0 else 0, mode='1')
-        mask = ImageChops.lighter(alpha_mask, mask.convert('L')).convert('L')
+        mask = mask.convert('L').point(lambda x: 255 if x > 128 else 0, mode='1')
+        mask = ImageChops.lighter(alpha_mask, mask).convert('L')
         image = image.convert("RGB")
     elif mode == 3:  # inpaint sketch
         image = inpaint_color_sketch
@@ -125,7 +169,7 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     if image is not None:
         image = ImageOps.exif_transpose(image)
 
-    if selected_scale_tab == 1:
+    if selected_scale_tab == 1 and not is_batch:
         assert image, "Can't scale by because no image is selected"
 
         width = int(image.width * scale_by)
@@ -171,6 +215,8 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     p.scripts = modules.scripts.scripts_img2img
     p.script_args = args
 
+    p.user = request.username
+
     if shared.cmd_opts.enable_console_prompts:
         print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
 
@@ -180,7 +226,7 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     if is_batch:
         assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
 
-        process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args)
+        process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
 
         processed = Processed(p, [], p.seed, "")
     else:

modules/interrogate.py

@@ -1,6 +1,5 @@
 import os
 import sys
-import traceback
 from collections import namedtuple
 from pathlib import Path
 import re
@@ -11,7 +10,6 @@ import torch.hub
 from torchvision import transforms
 from torchvision.transforms.functional import InterpolationMode
 
-import modules.shared as shared
 from modules import devices, paths, shared, lowvram, modelloader, errors
 
 blip_image_eval_size = 384
@@ -160,7 +158,7 @@ class InterrogateModels:
             text_array = text_array[0:int(shared.opts.interrogate_clip_dict_limit)]
 
         top_count = min(top_count, len(text_array))
-        text_tokens = clip.tokenize([text for text in text_array], truncate=True).to(devices.device_interrogate)
+        text_tokens = clip.tokenize(list(text_array), truncate=True).to(devices.device_interrogate)
         text_features = self.clip_model.encode_text(text_tokens).type(self.dtype)
         text_features /= text_features.norm(dim=-1, keepdim=True)
 
@@ -186,8 +184,7 @@ class InterrogateModels:
 
     def interrogate(self, pil_image):
         res = ""
-        shared.state.begin()
+        shared.state.begin(job="interrogate")
-        shared.state.job = 'interrogate'
         try:
             if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
                 lowvram.send_everything_to_cpu()
@@ -208,8 +205,8 @@ class InterrogateModels:
 
                 image_features /= image_features.norm(dim=-1, keepdim=True)
 
-                for name, topn, items in self.categories():
+                for cat in self.categories():
-                    matches = self.rank(image_features, items, top_count=topn)
+                    matches = self.rank(image_features, cat.items, top_count=cat.topn)
                     for match, score in matches:
                         if shared.opts.interrogate_return_ranks:
                             res += f", ({match}:{score/100:.3f})"
@@ -217,8 +214,7 @@ class InterrogateModels:
                             res += f", {match}"
 
         except Exception:
-            print("Error interrogating", file=sys.stderr)
+            errors.report("Error interrogating", exc_info=True)
-            print(traceback.format_exc(), file=sys.stderr)
             res += "<error>"
 
         self.unload()

modules/launch_utils.py

@@ -0,0 +1,344 @@
+# this scripts installs necessary requirements and launches main program in webui.py
+import subprocess
+import os
+import sys
+import importlib.util
+import platform
+import json
+from functools import lru_cache
+
+from modules import cmd_args, errors
+from modules.paths_internal import script_path, extensions_dir
+
+args, _ = cmd_args.parser.parse_known_args()
+
+python = sys.executable
+git = os.environ.get('GIT', "git")
+index_url = os.environ.get('INDEX_URL', "")
+dir_repos = "repositories"
+
+# Whether to default to printing command output
+default_command_live = (os.environ.get('WEBUI_LAUNCH_LIVE_OUTPUT') == "1")
+
+if 'GRADIO_ANALYTICS_ENABLED' not in os.environ:
+    os.environ['GRADIO_ANALYTICS_ENABLED'] = 'False'
+
+
+def check_python_version():
+    is_windows = platform.system() == "Windows"
+    major = sys.version_info.major
+    minor = sys.version_info.minor
+    micro = sys.version_info.micro
+
+    if is_windows:
+        supported_minors = [10]
+    else:
+        supported_minors = [7, 8, 9, 10, 11]
+
+    if not (major == 3 and minor in supported_minors):
+        import modules.errors
+
+        modules.errors.print_error_explanation(f"""
+INCOMPATIBLE PYTHON VERSION
+
+This program is tested with 3.10.6 Python, but you have {major}.{minor}.{micro}.
+If you encounter an error with "RuntimeError: Couldn't install torch." message,
+or any other error regarding unsuccessful package (library) installation,
+please downgrade (or upgrade) to the latest version of 3.10 Python
+and delete current Python and "venv" folder in WebUI's directory.
+
+You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
+
+{"Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases" if is_windows else ""}
+
+Use --skip-python-version-check to suppress this warning.
+""")
+
+
+@lru_cache()
+def commit_hash():
+    try:
+        return subprocess.check_output([git, "rev-parse", "HEAD"], shell=False, encoding='utf8').strip()
+    except Exception:
+        return "<none>"
+
+
+@lru_cache()
+def git_tag():
+    try:
+        return subprocess.check_output([git, "describe", "--tags"], shell=False, encoding='utf8').strip()
+    except Exception:
+        try:
+            from pathlib import Path
+            changelog_md = Path(__file__).parent.parent / "CHANGELOG.md"
+            with changelog_md.open(encoding="utf-8") as file:
+                return next((line.strip() for line in file if line.strip()), "<none>")
+        except Exception:
+            return "<none>"
+
+
+def run(command, desc=None, errdesc=None, custom_env=None, live: bool = default_command_live) -> str:
+    if desc is not None:
+        print(desc)
+
+    run_kwargs = {
+        "args": command,
+        "shell": True,
+        "env": os.environ if custom_env is None else custom_env,
+        "encoding": 'utf8',
+        "errors": 'ignore',
+    }
+
+    if not live:
+        run_kwargs["stdout"] = run_kwargs["stderr"] = subprocess.PIPE
+
+    result = subprocess.run(**run_kwargs)
+
+    if result.returncode != 0:
+        error_bits = [
+            f"{errdesc or 'Error running command'}.",
+            f"Command: {command}",
+            f"Error code: {result.returncode}",
+        ]
+        if result.stdout:
+            error_bits.append(f"stdout: {result.stdout}")
+        if result.stderr:
+            error_bits.append(f"stderr: {result.stderr}")
+        raise RuntimeError("\n".join(error_bits))
+
+    return (result.stdout or "")
+
+
+def is_installed(package):
+    try:
+        spec = importlib.util.find_spec(package)
+    except ModuleNotFoundError:
+        return False
+
+    return spec is not None
+
+
+def repo_dir(name):
+    return os.path.join(script_path, dir_repos, name)
+
+
+def run_pip(command, desc=None, live=default_command_live):
+    if args.skip_install:
+        return
+
+    index_url_line = f' --index-url {index_url}' if index_url != '' else ''
+    return run(f'"{python}" -m pip {command} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}", live=live)
+
+
+def check_run_python(code: str) -> bool:
+    result = subprocess.run([python, "-c", code], capture_output=True, shell=False)
+    return result.returncode == 0
+
+
+def git_clone(url, dir, name, commithash=None):
+    # TODO clone into temporary dir and move if successful
+
+    if os.path.exists(dir):
+        if commithash is None:
+            return
+
+        current_hash = run(f'"{git}" -C "{dir}" rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}", live=False).strip()
+        if current_hash == commithash:
+            return
+
+        run(f'"{git}" -C "{dir}" fetch', f"Fetching updates for {name}...", f"Couldn't fetch {name}")
+        run(f'"{git}" -C "{dir}" checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}", live=True)
+        return
+
+    run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
+
+    if commithash is not None:
+        run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
+
+
+def git_pull_recursive(dir):
+    for subdir, _, _ in os.walk(dir):
+        if os.path.exists(os.path.join(subdir, '.git')):
+            try:
+                output = subprocess.check_output([git, '-C', subdir, 'pull', '--autostash'])
+                print(f"Pulled changes for repository in '{subdir}':\n{output.decode('utf-8').strip()}\n")
+            except subprocess.CalledProcessError as e:
+                print(f"Couldn't perform 'git pull' on repository in '{subdir}':\n{e.output.decode('utf-8').strip()}\n")
+
+
+def version_check(commit):
+    try:
+        import requests
+        commits = requests.get('https://api.github.com/repos/AUTOMATIC1111/stable-diffusion-webui/branches/master').json()
+        if commit != "<none>" and commits['commit']['sha'] != commit:
+            print("--------------------------------------------------------")
+            print("| You are not up to date with the most recent release. |")
+            print("| Consider running `git pull` to update.               |")
+            print("--------------------------------------------------------")
+        elif commits['commit']['sha'] == commit:
+            print("You are up to date with the most recent release.")
+        else:
+            print("Not a git clone, can't perform version check.")
+    except Exception as e:
+        print("version check failed", e)
+
+
+def run_extension_installer(extension_dir):
+    path_installer = os.path.join(extension_dir, "install.py")
+    if not os.path.isfile(path_installer):
+        return
+
+    try:
+        env = os.environ.copy()
+        env['PYTHONPATH'] = os.path.abspath(".")
+
+        print(run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env))
+    except Exception as e:
+        errors.report(str(e))
+
+
+def list_extensions(settings_file):
+    settings = {}
+
+    try:
+        if os.path.isfile(settings_file):
+            with open(settings_file, "r", encoding="utf8") as file:
+                settings = json.load(file)
+    except Exception:
+        errors.report("Could not load settings", exc_info=True)
+
+    disabled_extensions = set(settings.get('disabled_extensions', []))
+    disable_all_extensions = settings.get('disable_all_extensions', 'none')
+
+    if disable_all_extensions != 'none':
+        return []
+
+    return [x for x in os.listdir(extensions_dir) if x not in disabled_extensions]
+
+
+def run_extensions_installers(settings_file):
+    if not os.path.isdir(extensions_dir):
+        return
+
+    for dirname_extension in list_extensions(settings_file):
+        run_extension_installer(os.path.join(extensions_dir, dirname_extension))
+
+
+def prepare_environment():
+    torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu118")
+    torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url {torch_index_url}")
+    requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
+
+    xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.20')
+    gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "https://github.com/TencentARC/GFPGAN/archive/8d2447a2d918f8eba5a4a01463fd48e45126a379.zip")
+    clip_package = os.environ.get('CLIP_PACKAGE', "https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip")
+    openclip_package = os.environ.get('OPENCLIP_PACKAGE', "https://github.com/mlfoundations/open_clip/archive/bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip")
+
+    stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/Stability-AI/stablediffusion.git")
+    k_diffusion_repo = os.environ.get('K_DIFFUSION_REPO', 'https://github.com/crowsonkb/k-diffusion.git')
+    codeformer_repo = os.environ.get('CODEFORMER_REPO', 'https://github.com/sczhou/CodeFormer.git')
+    blip_repo = os.environ.get('BLIP_REPO', 'https://github.com/salesforce/BLIP.git')
+
+    stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf")
+    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "c9fe758757e022f05ca5a53fa8fac28889e4f1cf")
+    codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
+    blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
+
+    try:
+        # the existance of this file is a signal to webui.sh/bat that webui needs to be restarted when it stops execution
+        os.remove(os.path.join(script_path, "tmp", "restart"))
+        os.environ.setdefault('SD_WEBUI_RESTARTING ', '1')
+    except OSError:
+        pass
+
+    if not args.skip_python_version_check:
+        check_python_version()
+
+    commit = commit_hash()
+    tag = git_tag()
+
+    print(f"Python {sys.version}")
+    print(f"Version: {tag}")
+    print(f"Commit hash: {commit}")
+
+    if args.reinstall_torch or not is_installed("torch") or not is_installed("torchvision"):
+        run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True)
+
+    if not args.skip_torch_cuda_test and not check_run_python("import torch; assert torch.cuda.is_available()"):
+        raise RuntimeError(
+            'Torch is not able to use GPU; '
+            'add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'
+        )
+
+    if not is_installed("gfpgan"):
+        run_pip(f"install {gfpgan_package}", "gfpgan")
+
+    if not is_installed("clip"):
+        run_pip(f"install {clip_package}", "clip")
+
+    if not is_installed("open_clip"):
+        run_pip(f"install {openclip_package}", "open_clip")
+
+    if (not is_installed("xformers") or args.reinstall_xformers) and args.xformers:
+        if platform.system() == "Windows":
+            if platform.python_version().startswith("3.10"):
+                run_pip(f"install -U -I --no-deps {xformers_package}", "xformers", live=True)
+            else:
+                print("Installation of xformers is not supported in this version of Python.")
+                print("You can also check this and build manually: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers#building-xformers-on-windows-by-duckness")
+                if not is_installed("xformers"):
+                    exit(0)
+        elif platform.system() == "Linux":
+            run_pip(f"install -U -I --no-deps {xformers_package}", "xformers")
+
+    if not is_installed("ngrok") and args.ngrok:
+        run_pip("install ngrok", "ngrok")
+
+    os.makedirs(os.path.join(script_path, dir_repos), exist_ok=True)
+
+    git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash)
+    git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
+    git_clone(codeformer_repo, repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
+    git_clone(blip_repo, repo_dir('BLIP'), "BLIP", blip_commit_hash)
+
+    if not is_installed("lpips"):
+        run_pip(f"install -r \"{os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}\"", "requirements for CodeFormer")
+
+    if not os.path.isfile(requirements_file):
+        requirements_file = os.path.join(script_path, requirements_file)
+    run_pip(f"install -r \"{requirements_file}\"", "requirements")
+
+    run_extensions_installers(settings_file=args.ui_settings_file)
+
+    if args.update_check:
+        version_check(commit)
+
+    if args.update_all_extensions:
+        git_pull_recursive(extensions_dir)
+
+    if "--exit" in sys.argv:
+        print("Exiting because of --exit argument")
+        exit(0)
+
+
+def configure_for_tests():
+    if "--api" not in sys.argv:
+        sys.argv.append("--api")
+    if "--ckpt" not in sys.argv:
+        sys.argv.append("--ckpt")
+        sys.argv.append(os.path.join(script_path, "test/test_files/empty.pt"))
+    if "--skip-torch-cuda-test" not in sys.argv:
+        sys.argv.append("--skip-torch-cuda-test")
+    if "--disable-nan-check" not in sys.argv:
+        sys.argv.append("--disable-nan-check")
+
+    os.environ['COMMANDLINE_ARGS'] = ""
+
+
+def start():
+    print(f"Launching {'API server' if '--nowebui' in sys.argv else 'Web UI'} with arguments: {' '.join(sys.argv[1:])}")
+    import webui
+    if '--nowebui' in sys.argv:
+        webui.api_only()
+    else:
+        webui.webui()

modules/localization.py

@@ -1,8 +1,7 @@
 import json
 import os
-import sys
-import traceback
 
+from modules import errors
 
 localizations = {}
 
@@ -31,7 +30,6 @@ def localization_js(current_localization_name: str) -> str:
             with open(fn, "r", encoding="utf8") as file:
                 data = json.load(file)
         except Exception:
-            print(f"Error loading localization from {fn}:", file=sys.stderr)
+            errors.report(f"Error loading localization from {fn}", exc_info=True)
-            print(traceback.format_exc(), file=sys.stderr)
 
     return f"window.localization = {json.dumps(data)}"

modules/lowvram.py

@@ -15,6 +15,8 @@ def send_everything_to_cpu():
 
 
 def setup_for_low_vram(sd_model, use_medvram):
+    sd_model.lowvram = True
+
     parents = {}
 
     def send_me_to_gpu(module, _):
@@ -96,3 +98,7 @@ def setup_for_low_vram(sd_model, use_medvram):
         diff_model.middle_block.register_forward_pre_hook(send_me_to_gpu)
         for block in diff_model.output_blocks:
             block.register_forward_pre_hook(send_me_to_gpu)
+
+
+def is_enabled(sd_model):
+    return getattr(sd_model, 'lowvram', False)

modules/mac_specific.py

@@ -1,13 +1,15 @@
 import torch
 import platform
-from modules import paths
 from modules.sd_hijack_utils import CondFunc
 from packaging import version
 
 
-# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
+# before torch version 1.13, has_mps is only available in nightly pytorch and macOS 12.3+,
-# check `getattr` and try it for compatibility
+# use check `getattr` and try it for compatibility.
+# in torch version 1.13, backends.mps.is_available() and backends.mps.is_built() are introduced in to check mps availabilty,
+# since torch 2.0.1+ nightly build, getattr(torch, 'has_mps', False) was deprecated, see https://github.com/pytorch/pytorch/pull/103279
 def check_for_mps() -> bool:
+    if version.parse(torch.__version__) <= version.parse("2.0.1"):
         if not getattr(torch, 'has_mps', False):
             return False
         try:
@@ -15,6 +17,8 @@ def check_for_mps() -> bool:
             return True
         except Exception:
             return False
+    else:
+        return torch.backends.mps.is_available() and torch.backends.mps.is_built()
 has_mps = check_for_mps()
 
 

modules/modelloader.py

@@ -1,4 +1,5 @@
-import glob
+from __future__ import annotations
+
 import os
 import shutil
 import importlib
@@ -9,6 +10,29 @@ from modules.upscaler import Upscaler, UpscalerLanczos, UpscalerNearest, Upscale
 from modules.paths import script_path, models_path
 
 
+def load_file_from_url(
+    url: str,
+    *,
+    model_dir: str,
+    progress: bool = True,
+    file_name: str | None = None,
+) -> str:
+    """Download a file from `url` into `model_dir`, using the file present if possible.
+
+    Returns the path to the downloaded file.
+    """
+    os.makedirs(model_dir, exist_ok=True)
+    if not file_name:
+        parts = urlparse(url)
+        file_name = os.path.basename(parts.path)
+    cached_file = os.path.abspath(os.path.join(model_dir, file_name))
+    if not os.path.exists(cached_file):
+        print(f'Downloading: "{url}" to {cached_file}\n')
+        from torch.hub import download_url_to_file
+        download_url_to_file(url, cached_file, progress=progress)
+    return cached_file
+
+
 def load_models(model_path: str, model_url: str = None, command_path: str = None, ext_filter=None, download_name=None, ext_blacklist=None) -> list:
     """
     A one-and done loader to try finding the desired models in specified directories.
@@ -40,16 +64,14 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None
                 if os.path.islink(full_path) and not os.path.exists(full_path):
                     print(f"Skipping broken symlink: {full_path}")
                     continue
-                if ext_blacklist is not None and any([full_path.endswith(x) for x in ext_blacklist]):
+                if ext_blacklist is not None and any(full_path.endswith(x) for x in ext_blacklist):
                     continue
                 if full_path not in output:
                     output.append(full_path)
 
         if model_url is not None and len(output) == 0:
             if download_name is not None:
-                from basicsr.utils.download_util import load_file_from_url
+                output.append(load_file_from_url(model_url, model_dir=places[0], file_name=download_name))
-                dl = load_file_from_url(model_url, model_path, True, download_name)
-                output.append(dl)
             else:
                 output.append(model_url)
 
@@ -60,7 +82,7 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None
 
 
 def friendly_name(file: str):
-    if "http" in file:
+    if file.startswith("http"):
         file = urlparse(file).path
 
     file = os.path.basename(file)
@@ -96,8 +118,7 @@ def cleanup_models():
 
 def move_files(src_path: str, dest_path: str, ext_filter: str = None):
     try:
-        if not os.path.exists(dest_path):
+        os.makedirs(dest_path, exist_ok=True)
-            os.makedirs(dest_path)
         if os.path.exists(src_path):
             for file in os.listdir(src_path):
                 fullpath = os.path.join(src_path, file)
@@ -108,12 +129,12 @@ def move_files(src_path: str, dest_path: str, ext_filter: str = None):
                     print(f"Moving {file} from {src_path} to {dest_path}.")
                     try:
                         shutil.move(fullpath, dest_path)
-                    except:
+                    except Exception:
                         pass
             if len(os.listdir(src_path)) == 0:
                 print(f"Removing empty folder: {src_path}")
                 shutil.rmtree(src_path, True)
-    except:
+    except Exception:
         pass
 
 
@@ -127,7 +148,7 @@ def load_upscalers():
             full_model = f"modules.{model_name}_model"
             try:
                 importlib.import_module(full_model)
-            except:
+            except Exception:
                 pass
 
     datas = []
@@ -145,7 +166,10 @@ def load_upscalers():
     for cls in reversed(used_classes.values()):
         name = cls.__name__
         cmd_name = f"{name.lower().replace('upscaler', '')}_models_path"
-        scaler = cls(commandline_options.get(cmd_name, None))
+        commandline_model_path = commandline_options.get(cmd_name, None)
+        scaler = cls(commandline_model_path)
+        scaler.user_path = commandline_model_path
+        scaler.model_download_path = commandline_model_path or scaler.model_path
         datas += scaler.scalers
 
     shared.sd_upscalers = sorted(

modules/models/diffusion/ddpm_edit.py

@@ -52,7 +52,7 @@ class DDPM(pl.LightningModule):
                  beta_schedule="linear",
                  loss_type="l2",
                  ckpt_path=None,
-                 ignore_keys=[],
+                 ignore_keys=None,
                  load_only_unet=False,
                  monitor="val/loss",
                  use_ema=True,
@@ -107,7 +107,7 @@ class DDPM(pl.LightningModule):
             print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
 
         if ckpt_path is not None:
-            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [], only_model=load_only_unet)
 
             # If initialing from EMA-only checkpoint, create EMA model after loading.
             if self.use_ema and not load_ema:
@@ -194,7 +194,9 @@ class DDPM(pl.LightningModule):
                 if context is not None:
                     print(f"{context}: Restored training weights")
 
-    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+    def init_from_ckpt(self, path, ignore_keys=None, only_model=False):
+        ignore_keys = ignore_keys or []
+
         sd = torch.load(path, map_location="cpu")
         if "state_dict" in list(sd.keys()):
             sd = sd["state_dict"]
@@ -228,9 +230,9 @@ class DDPM(pl.LightningModule):
         missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
             sd, strict=False)
         print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
-        if len(missing) > 0:
+        if missing:
             print(f"Missing Keys: {missing}")
-        if len(unexpected) > 0:
+        if unexpected:
             print(f"Unexpected Keys: {unexpected}")
 
     def q_mean_variance(self, x_start, t):
@@ -403,7 +405,7 @@ class DDPM(pl.LightningModule):
 
     @torch.no_grad()
     def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
-        log = dict()
+        log = {}
         x = self.get_input(batch, self.first_stage_key)
         N = min(x.shape[0], N)
         n_row = min(x.shape[0], n_row)
@@ -411,7 +413,7 @@ class DDPM(pl.LightningModule):
         log["inputs"] = x
 
         # get diffusion row
-        diffusion_row = list()
+        diffusion_row = []
         x_start = x[:n_row]
 
         for t in range(self.num_timesteps):
@@ -473,13 +475,13 @@ class LatentDiffusion(DDPM):
             conditioning_key = None
         ckpt_path = kwargs.pop("ckpt_path", None)
         ignore_keys = kwargs.pop("ignore_keys", [])
-        super().__init__(conditioning_key=conditioning_key, *args, load_ema=load_ema, **kwargs)
+        super().__init__(*args, conditioning_key=conditioning_key, load_ema=load_ema, **kwargs)
         self.concat_mode = concat_mode
         self.cond_stage_trainable = cond_stage_trainable
         self.cond_stage_key = cond_stage_key
         try:
             self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
-        except:
+        except Exception:
             self.num_downs = 0
         if not scale_by_std:
             self.scale_factor = scale_factor
@@ -891,16 +893,6 @@ class LatentDiffusion(DDPM):
                 c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
         return self.p_losses(x, c, t, *args, **kwargs)
 
-    def _rescale_annotations(self, bboxes, crop_coordinates):  # TODO: move to dataset
-        def rescale_bbox(bbox):
-            x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
-            y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
-            w = min(bbox[2] / crop_coordinates[2], 1 - x0)
-            h = min(bbox[3] / crop_coordinates[3], 1 - y0)
-            return x0, y0, w, h
-
-        return [rescale_bbox(b) for b in bboxes]
-
     def apply_model(self, x_noisy, t, cond, return_ids=False):
 
         if isinstance(cond, dict):
@@ -1140,7 +1132,7 @@ class LatentDiffusion(DDPM):
         if cond is not None:
             if isinstance(cond, dict):
                 cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
-                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+                [x[:batch_size] for x in cond[key]] for key in cond}
             else:
                 cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
 
@@ -1171,8 +1163,10 @@ class LatentDiffusion(DDPM):
 
             if i % log_every_t == 0 or i == timesteps - 1:
                 intermediates.append(x0_partial)
-            if callback: callback(i)
+            if callback:
-            if img_callback: img_callback(img, i)
+                callback(i)
+            if img_callback:
+                img_callback(img, i)
         return img, intermediates
 
     @torch.no_grad()
@@ -1219,8 +1213,10 @@ class LatentDiffusion(DDPM):
 
             if i % log_every_t == 0 or i == timesteps - 1:
                 intermediates.append(img)
-            if callback: callback(i)
+            if callback:
-            if img_callback: img_callback(img, i)
+                callback(i)
+            if img_callback:
+                img_callback(img, i)
 
         if return_intermediates:
             return img, intermediates
@@ -1235,7 +1231,7 @@ class LatentDiffusion(DDPM):
         if cond is not None:
             if isinstance(cond, dict):
                 cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
-                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+                [x[:batch_size] for x in cond[key]] for key in cond}
             else:
                 cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
         return self.p_sample_loop(cond,
@@ -1267,7 +1263,7 @@ class LatentDiffusion(DDPM):
 
         use_ddim = False
 
-        log = dict()
+        log = {}
         z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
                                            return_first_stage_outputs=True,
                                            force_c_encode=True,
@@ -1295,7 +1291,7 @@ class LatentDiffusion(DDPM):
 
         if plot_diffusion_rows:
             # get diffusion row
-            diffusion_row = list()
+            diffusion_row = []
             z_start = z[:n_row]
             for t in range(self.num_timesteps):
                 if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
@@ -1337,7 +1333,7 @@ class LatentDiffusion(DDPM):
 
             if inpaint:
                 # make a simple center square
-                b, h, w = z.shape[0], z.shape[2], z.shape[3]
+                h, w = z.shape[2], z.shape[3]
                 mask = torch.ones(N, h, w).to(self.device)
                 # zeros will be filled in
                 mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
@@ -1439,10 +1435,10 @@ class Layout2ImgDiffusion(LatentDiffusion):
     # TODO: move all layout-specific hacks to this class
     def __init__(self, cond_stage_key, *args, **kwargs):
         assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
-        super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+        super().__init__(*args, cond_stage_key=cond_stage_key, **kwargs)
 
     def log_images(self, batch, N=8, *args, **kwargs):
-        logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+        logs = super().log_images(*args, batch=batch, N=N, **kwargs)
 
         key = 'train' if self.training else 'validation'
         dset = self.trainer.datamodule.datasets[key]

modules/models/diffusion/uni_pc/__init__.py

@@ -1 +1 @@
-from .sampler import UniPCSampler
+from .sampler import UniPCSampler  # noqa: F401

modules/models/diffusion/uni_pc/sampler.py

@@ -54,7 +54,8 @@ class UniPCSampler(object):
         if conditioning is not None:
             if isinstance(conditioning, dict):
                 ctmp = conditioning[list(conditioning.keys())[0]]
-                while isinstance(ctmp, list): ctmp = ctmp[0]
+                while isinstance(ctmp, list):
+                    ctmp = ctmp[0]
                 cbs = ctmp.shape[0]
                 if cbs != batch_size:
                     print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")

modules/models/diffusion/uni_pc/uni_pc.py

@@ -1,7 +1,6 @@
 import torch
-import torch.nn.functional as F
 import math
-from tqdm.auto import trange
+import tqdm
 
 
 class NoiseScheduleVP:
@@ -179,13 +178,13 @@ def model_wrapper(
     model,
     noise_schedule,
     model_type="noise",
-    model_kwargs={},
+    model_kwargs=None,
     guidance_type="uncond",
     #condition=None,
     #unconditional_condition=None,
     guidance_scale=1.,
     classifier_fn=None,
-    classifier_kwargs={},
+    classifier_kwargs=None,
 ):
     """Create a wrapper function for the noise prediction model.
 
@@ -276,6 +275,9 @@ def model_wrapper(
         A noise prediction model that accepts the noised data and the continuous time as the inputs.
     """
 
+    model_kwargs = model_kwargs or {}
+    classifier_kwargs = classifier_kwargs or {}
+
     def get_model_input_time(t_continuous):
         """
         Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time.
@@ -342,7 +344,7 @@ def model_wrapper(
                 t_in = torch.cat([t_continuous] * 2)
                 if isinstance(condition, dict):
                     assert isinstance(unconditional_condition, dict)
-                    c_in = dict()
+                    c_in = {}
                     for k in condition:
                         if isinstance(condition[k], list):
                             c_in[k] = [torch.cat([
@@ -353,7 +355,7 @@ def model_wrapper(
                                 unconditional_condition[k],
                                 condition[k]])
                 elif isinstance(condition, list):
-                    c_in = list()
+                    c_in = []
                     assert isinstance(unconditional_condition, list)
                     for i in range(len(condition)):
                         c_in.append(torch.cat([unconditional_condition[i], condition[i]]))
@@ -757,6 +759,7 @@ class UniPC:
                 vec_t = timesteps[0].expand((x.shape[0]))
                 model_prev_list = [self.model_fn(x, vec_t)]
                 t_prev_list = [vec_t]
+                with tqdm.tqdm(total=steps) as pbar:
                     # Init the first `order` values by lower order multistep DPM-Solver.
                     for init_order in range(1, order):
                         vec_t = timesteps[init_order].expand(x.shape[0])
@@ -767,7 +770,9 @@ class UniPC:
                             self.after_update(x, model_x)
                         model_prev_list.append(model_x)
                         t_prev_list.append(vec_t)
-                for step in trange(order, steps + 1):
+                        pbar.update()
+
+                    for step in range(order, steps + 1):
                         vec_t = timesteps[step].expand(x.shape[0])
                         if lower_order_final:
                             step_order = min(order, steps + 1 - step)
@@ -791,6 +796,7 @@ class UniPC:
                             if model_x is None:
                                 model_x = self.model_fn(x, vec_t)
                             model_prev_list[-1] = model_x
+                        pbar.update()
         else:
             raise NotImplementedError()
         if denoise_to_zero:

modules/ngrok.py

@@ -1,6 +1,7 @@
-from pyngrok import ngrok, conf, exception
+import ngrok
 
-def connect(token, port, region):
+# Connect to ngrok for ingress
+def connect(token, port, options):
     account = None
     if token is None:
         token = 'None'
@@ -10,28 +11,19 @@ def connect(token, port, region):
             token, username, password = token.split(':', 2)
             account = f"{username}:{password}"
 
-    config = conf.PyngrokConfig(
+    # For all options see: https://github.com/ngrok/ngrok-py/blob/main/examples/ngrok-connect-full.py
-        auth_token=token, region=region
+    if not options.get('authtoken_from_env'):
-    )
+        options['authtoken'] = token
+    if account:
+        options['basic_auth'] = account
+    if not options.get('session_metadata'):
+        options['session_metadata'] = 'stable-diffusion-webui'
 
-    # Guard for existing tunnels
-    existing = ngrok.get_tunnels(pyngrok_config=config)
-    if existing:
-        for established in existing:
-            # Extra configuration in the case that the user is also using ngrok for other tunnels
-            if established.config['addr'][-4:] == str(port):
-                public_url = existing[0].public_url
-                print(f'ngrok has already been connected to localhost:{port}! URL: {public_url}\n'
-                    'You can use this link after the launch is complete.')
-                return
 
     try:
-        if account is None:
+        public_url = ngrok.connect(f"127.0.0.1:{port}", **options).url()
-            public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True).public_url
+    except Exception as e:
-        else:
+        print(f'Invalid ngrok authtoken? ngrok connection aborted due to: {e}\n'
-            public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True, auth=account).public_url
-    except exception.PyngrokNgrokError:
-        print(f'Invalid ngrok authtoken, ngrok connection aborted.\n'
               f'Your token: {token}, get the right one on https://dashboard.ngrok.com/get-started/your-authtoken')
     else:
         print(f'ngrok connected to localhost:{port}! URL: {public_url}\n'

modules/paths.py

@@ -1,8 +1,8 @@
 import os
 import sys
-from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir
+from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir  # noqa: F401
 
-import modules.safe
+import modules.safe  # noqa: F401
 
 
 # data_path = cmd_opts_pre.data
@@ -20,7 +20,6 @@ assert sd_path is not None, f"Couldn't find Stable Diffusion in any of: {possibl
 
 path_dirs = [
     (sd_path, 'ldm', 'Stable Diffusion', []),
-    (os.path.join(sd_path, '../taming-transformers'), 'taming', 'Taming Transformers', []),
     (os.path.join(sd_path, '../CodeFormer'), 'inference_codeformer.py', 'CodeFormer', []),
     (os.path.join(sd_path, '../BLIP'), 'models/blip.py', 'BLIP', []),
     (os.path.join(sd_path, '../k-diffusion'), 'k_diffusion/sampling.py', 'k_diffusion', ["atstart"]),
@@ -39,17 +38,3 @@ for d, must_exist, what, options in path_dirs:
         else:
             sys.path.append(d)
         paths[what] = d
-
-
-class Prioritize:
-    def __init__(self, name):
-        self.name = name
-        self.path = None
-
-    def __enter__(self):
-        self.path = sys.path.copy()
-        sys.path = [paths[self.name]] + sys.path
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        sys.path = self.path
-        self.path = None

modules/paths_internal.py

@@ -2,8 +2,14 @@
 
 import argparse
 import os
+import sys
+import shlex
 
-script_path = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
+commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
+sys.argv += shlex.split(commandline_args)
+
+modules_path = os.path.dirname(os.path.realpath(__file__))
+script_path = os.path.dirname(modules_path)
 
 sd_configs_path = os.path.join(script_path, "configs")
 sd_default_config = os.path.join(sd_configs_path, "v1-inference.yaml")
@@ -12,7 +18,7 @@ default_sd_model_file = sd_model_file
 
 # Parse the --data-dir flag first so we can use it as a base for our other argument default values
 parser_pre = argparse.ArgumentParser(add_help=False)
-parser_pre.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored",)
+parser_pre.add_argument("--data-dir", type=str, default=os.path.dirname(modules_path), help="base path where all user data is stored", )
 cmd_opts_pre = parser_pre.parse_known_args()[0]
 
 data_path = cmd_opts_pre.data_dir
@@ -21,3 +27,5 @@ models_path = os.path.join(data_path, "models")
 extensions_dir = os.path.join(data_path, "extensions")
 extensions_builtin_dir = os.path.join(script_path, "extensions-builtin")
 config_states_dir = os.path.join(script_path, "config_states")
+
+roboto_ttf_file = os.path.join(modules_path, 'Roboto-Regular.ttf')

modules/postprocessing.py

@@ -9,8 +9,7 @@ from modules.shared import opts
 def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, show_extras_results, *args, save_output: bool = True):
     devices.torch_gc()
 
-    shared.state.begin()
+    shared.state.begin(job="extras")
-    shared.state.job = 'extras'
 
     image_data = []
     image_names = []
@@ -54,7 +53,9 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
     for image, name in zip(image_data, image_names):
         shared.state.textinfo = name
 
-        existing_pnginfo = image.info or {}
+        parameters, existing_pnginfo = images.read_info_from_image(image)
+        if parameters:
+            existing_pnginfo["parameters"] = parameters
 
         pp = scripts_postprocessing.PostprocessedImage(image.convert("RGB"))
 

modules/processing.py

@@ -1,20 +1,20 @@
 import json
+import logging
 import math
 import os
 import sys
-import warnings
 import hashlib
 
 import torch
 import numpy as np
-from PIL import Image, ImageFilter, ImageOps
+from PIL import Image, ImageOps
 import random
 import cv2
 from skimage import exposure
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List
 
 import modules.sd_hijack
-from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, script_callbacks, extra_networks, sd_vae_approx, scripts
+from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common, sd_unet
 from modules.sd_hijack import model_hijack
 from modules.shared import opts, cmd_opts, state
 import modules.shared as shared
@@ -24,13 +24,13 @@ import modules.images as images
 import modules.styles
 import modules.sd_models as sd_models
 import modules.sd_vae as sd_vae
-import logging
 from ldm.data.util import AddMiDaS
 from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion
 
 from einops import repeat, rearrange
 from blendmodes.blend import blendLayers, BlendType
 
+
 # some of those options should not be changed at all because they would break the model, so I removed them from options.
 opt_C = 4
 opt_f = 8
@@ -106,6 +106,9 @@ class StableDiffusionProcessing:
     """
     The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
     """
+    cached_uc = [None, None]
+    cached_c = [None, None]
+
     def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_min_uncond: float = 0.0, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None):
         if sampler_index is not None:
             print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
@@ -150,6 +153,8 @@ class StableDiffusionProcessing:
         self.override_settings_restore_afterwards = override_settings_restore_afterwards
         self.is_using_inpainting_conditioning = False
         self.disable_extra_networks = False
+        self.token_merging_ratio = 0
+        self.token_merging_ratio_hr = 0
 
         if not seed_enable_extras:
             self.subseed = -1
@@ -165,7 +170,21 @@ class StableDiffusionProcessing:
         self.all_subseeds = None
         self.iteration = 0
         self.is_hr_pass = False
+        self.sampler = None
 
+        self.prompts = None
+        self.negative_prompts = None
+        self.extra_network_data = None
+        self.seeds = None
+        self.subseeds = None
+
+        self.step_multiplier = 1
+        self.cached_uc = StableDiffusionProcessing.cached_uc
+        self.cached_c = StableDiffusionProcessing.cached_c
+        self.uc = None
+        self.c = None
+
+        self.user = None
 
     @property
     def sd_model(self):
@@ -273,6 +292,64 @@ class StableDiffusionProcessing:
 
     def close(self):
         self.sampler = None
+        self.c = None
+        self.uc = None
+        if not opts.experimental_persistent_cond_cache:
+            StableDiffusionProcessing.cached_c = [None, None]
+            StableDiffusionProcessing.cached_uc = [None, None]
+
+    def get_token_merging_ratio(self, for_hr=False):
+        if for_hr:
+            return self.token_merging_ratio_hr or opts.token_merging_ratio_hr or self.token_merging_ratio or opts.token_merging_ratio
+
+        return self.token_merging_ratio or opts.token_merging_ratio
+
+    def setup_prompts(self):
+        if type(self.prompt) == list:
+            self.all_prompts = self.prompt
+        else:
+            self.all_prompts = self.batch_size * self.n_iter * [self.prompt]
+
+        if type(self.negative_prompt) == list:
+            self.all_negative_prompts = self.negative_prompt
+        else:
+            self.all_negative_prompts = self.batch_size * self.n_iter * [self.negative_prompt]
+
+        self.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, self.styles) for x in self.all_prompts]
+        self.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, self.styles) for x in self.all_negative_prompts]
+
+    def get_conds_with_caching(self, function, required_prompts, steps, caches, extra_network_data):
+        """
+        Returns the result of calling function(shared.sd_model, required_prompts, steps)
+        using a cache to store the result if the same arguments have been used before.
+
+        cache is an array containing two elements. The first element is a tuple
+        representing the previously used arguments, or None if no arguments
+        have been used before. The second element is where the previously
+        computed result is stored.
+
+        caches is a list with items described above.
+        """
+        for cache in caches:
+            if cache[0] is not None and (required_prompts, steps, opts.CLIP_stop_at_last_layers, shared.sd_model.sd_checkpoint_info, extra_network_data) == cache[0]:
+                return cache[1]
+
+        cache = caches[0]
+
+        with devices.autocast():
+            cache[1] = function(shared.sd_model, required_prompts, steps)
+
+        cache[0] = (required_prompts, steps, opts.CLIP_stop_at_last_layers, shared.sd_model.sd_checkpoint_info, extra_network_data)
+        return cache[1]
+
+    def setup_conds(self):
+        sampler_config = sd_samplers.find_sampler_config(self.sampler_name)
+        self.step_multiplier = 2 if sampler_config and sampler_config.options.get("second_order", False) else 1
+        self.uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, self.negative_prompts, self.steps * self.step_multiplier, [self.cached_uc], self.extra_network_data)
+        self.c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, self.prompts, self.steps * self.step_multiplier, [self.cached_c], self.extra_network_data)
+
+    def parse_extra_network_prompts(self):
+        self.prompts, self.extra_network_data = extra_networks.parse_prompts(self.prompts)
 
 
 class Processed:
@@ -303,6 +380,8 @@ class Processed:
         self.styles = p.styles
         self.job_timestamp = state.job_timestamp
         self.clip_skip = opts.CLIP_stop_at_last_layers
+        self.token_merging_ratio = p.token_merging_ratio
+        self.token_merging_ratio_hr = p.token_merging_ratio_hr
 
         self.eta = p.eta
         self.ddim_discretize = p.ddim_discretize
@@ -310,6 +389,7 @@ class Processed:
         self.s_tmin = p.s_tmin
         self.s_tmax = p.s_tmax
         self.s_noise = p.s_noise
+        self.s_min_uncond = p.s_min_uncond
         self.sampler_noise_scheduler_override = p.sampler_noise_scheduler_override
         self.prompt = self.prompt if type(self.prompt) != list else self.prompt[0]
         self.negative_prompt = self.negative_prompt if type(self.negative_prompt) != list else self.negative_prompt[0]
@@ -360,6 +440,9 @@ class Processed:
     def infotext(self, p: StableDiffusionProcessing, index):
         return create_infotext(p, self.all_prompts, self.all_seeds, self.all_subseeds, comments=[], position_in_batch=index % self.batch_size, iteration=index // self.batch_size)
 
+    def get_token_merging_ratio(self, for_hr=False):
+        return self.token_merging_ratio_hr if for_hr else self.token_merging_ratio
+
 
 # from https://discuss.pytorch.org/t/help-regarding-slerp-function-for-generative-model-sampling/32475/3
 def slerp(val, low, high):
@@ -468,10 +551,17 @@ def program_version():
     return res
 
 
-def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0):
+def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0, use_main_prompt=False):
     index = position_in_batch + iteration * p.batch_size
 
     clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers)
+    enable_hr = getattr(p, 'enable_hr', False)
+    token_merging_ratio = p.get_token_merging_ratio()
+    token_merging_ratio_hr = p.get_token_merging_ratio(for_hr=True)
+
+    uses_ensd = opts.eta_noise_seed_delta != 0
+    if uses_ensd:
+        uses_ensd = sd_samplers_common.is_sampler_using_eta_noise_seed_delta(p)
 
     generation_params = {
         "Steps": p.steps,
@@ -485,27 +575,33 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
         "Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
         "Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),
         "Variation seed strength": (None if p.subseed_strength == 0 else p.subseed_strength),
-        "Seed resize from": (None if p.seed_resize_from_w == 0 or p.seed_resize_from_h == 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
+        "Seed resize from": (None if p.seed_resize_from_w <= 0 or p.seed_resize_from_h <= 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
         "Denoising strength": getattr(p, 'denoising_strength', None),
         "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None,
         "Clip skip": None if clip_skip <= 1 else clip_skip,
-        "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta,
+        "ENSD": opts.eta_noise_seed_delta if uses_ensd else None,
+        "Token merging ratio": None if token_merging_ratio == 0 else token_merging_ratio,
+        "Token merging ratio hr": None if not enable_hr or token_merging_ratio_hr == 0 else token_merging_ratio_hr,
         "Init image hash": getattr(p, 'init_img_hash', None),
         "RNG": opts.randn_source if opts.randn_source != "GPU" else None,
         "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond,
+        **p.extra_generation_params,
         "Version": program_version() if opts.add_version_to_infotext else None,
+        "User": p.user if opts.add_user_name_to_info else None,
     }
 
-    generation_params.update(p.extra_generation_params)
-
     generation_params_text = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in generation_params.items() if v is not None])
 
+    prompt_text = p.prompt if use_main_prompt else all_prompts[index]
     negative_prompt_text = f"\nNegative prompt: {p.all_negative_prompts[index]}" if p.all_negative_prompts[index] else ""
 
-    return f"{all_prompts[index]}{negative_prompt_text}\n{generation_params_text}".strip()
+    return f"{prompt_text}{negative_prompt_text}\n{generation_params_text}".strip()
 
 
 def process_images(p: StableDiffusionProcessing) -> Processed:
+    if p.scripts is not None:
+        p.scripts.before_process(p)
+
     stored_opts = {k: opts.data[k] for k in p.override_settings.keys()}
 
     try:
@@ -523,9 +619,13 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             if k == 'sd_vae':
                 sd_vae.reload_vae_weights()
 
+        sd_models.apply_token_merging(p.sd_model, p.get_token_merging_ratio())
+
         res = process_images_inner(p)
 
     finally:
+        sd_models.apply_token_merging(p.sd_model, 0)
+
         # restore opts to original state
         if p.override_settings_restore_afterwards:
             for k, v in stored_opts.items():
@@ -555,15 +655,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
     comments = {}
 
-    if type(p.prompt) == list:
+    p.setup_prompts()
-        p.all_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, p.styles) for x in p.prompt]
-    else:
-        p.all_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_styles_to_prompt(p.prompt, p.styles)]
-
-    if type(p.negative_prompt) == list:
-        p.all_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, p.styles) for x in p.negative_prompt]
-    else:
-        p.all_negative_prompts = p.batch_size * p.n_iter * [shared.prompt_styles.apply_negative_styles_to_prompt(p.negative_prompt, p.styles)]
 
     if type(seed) == list:
         p.all_seeds = seed
@@ -575,8 +667,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
     else:
         p.all_subseeds = [int(subseed) + x for x in range(len(p.all_prompts))]
 
-    def infotext(iteration=0, position_in_batch=0):
+    def infotext(iteration=0, position_in_batch=0, use_main_prompt=False):
-        return create_infotext(p, p.all_prompts, p.all_seeds, p.all_subseeds, comments, iteration, position_in_batch)
+        return create_infotext(p, p.all_prompts, p.all_seeds, p.all_subseeds, comments, iteration, position_in_batch, use_main_prompt)
 
     if os.path.exists(cmd_opts.embeddings_dir) and not p.do_not_reload_embeddings:
         model_hijack.embedding_db.load_textual_inversion_embeddings()
@@ -587,29 +679,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
     infotexts = []
     output_images = []
 
-    cached_uc = [None, None]
-    cached_c = [None, None]
-
-    def get_conds_with_caching(function, required_prompts, steps, cache):
-        """
-        Returns the result of calling function(shared.sd_model, required_prompts, steps)
-        using a cache to store the result if the same arguments have been used before.
-
-        cache is an array containing two elements. The first element is a tuple
-        representing the previously used arguments, or None if no arguments
-        have been used before. The second element is where the previously
-        computed result is stored.
-        """
-
-        if cache[0] is not None and (required_prompts, steps) == cache[0]:
-            return cache[1]
-
-        with devices.autocast():
-            cache[1] = function(shared.sd_model, required_prompts, steps)
-
-        cache[0] = (required_prompts, steps)
-        return cache[1]
-
     with torch.no_grad(), p.sd_model.ema_scope():
         with devices.autocast():
             p.init(p.all_prompts, p.all_seeds, p.all_subseeds)
@@ -618,10 +687,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             if shared.opts.live_previews_enable and opts.show_progress_type == "Approx NN":
                 sd_vae_approx.model()
 
+            sd_unet.apply_unet()
+
         if state.job_count == -1:
             state.job_count = p.n_iter
 
-        extra_network_data = None
         for n in range(p.n_iter):
             p.iteration = n
 
@@ -631,25 +701,25 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             if state.interrupted:
                 break
 
-            prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
+            p.prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
-            negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size]
+            p.negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size]
-            seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
+            p.seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
-            subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size]
+            p.subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size]
 
             if p.scripts is not None:
-                p.scripts.before_process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)
+                p.scripts.before_process_batch(p, batch_number=n, prompts=p.prompts, seeds=p.seeds, subseeds=p.subseeds)
 
-            if len(prompts) == 0:
+            if len(p.prompts) == 0:
                 break
 
-            prompts, extra_network_data = extra_networks.parse_prompts(prompts)
+            p.parse_extra_network_prompts()
 
             if not p.disable_extra_networks:
                 with devices.autocast():
-                    extra_networks.activate(p, extra_network_data)
+                    extra_networks.activate(p, p.extra_network_data)
 
             if p.scripts is not None:
-                p.scripts.process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)
+                p.scripts.process_batch(p, batch_number=n, prompts=p.prompts, seeds=p.seeds, subseeds=p.subseeds)
 
             # params.txt should be saved after scripts.process_batch, since the
             # infotext could be modified by that callback
@@ -660,14 +730,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                     processed = Processed(p, [], p.seed, "")
                     file.write(processed.infotext(p, 0))
 
-            step_multiplier = 1
+            p.setup_conds()
-            if not shared.opts.dont_fix_second_order_samplers_schedule:
-                try:
-                    step_multiplier = 2 if sd_samplers.all_samplers_map.get(p.sampler_name).aliases[0] in ['k_dpmpp_2s_a', 'k_dpmpp_2s_a_ka', 'k_dpmpp_sde', 'k_dpmpp_sde_ka', 'k_dpm_2', 'k_dpm_2_a', 'k_heun'] else 1
-                except:
-                    pass
-            uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps * step_multiplier, cached_uc)
-            c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps * step_multiplier, cached_c)
 
             if len(model_hijack.comments) > 0:
                 for comment in model_hijack.comments:
@@ -677,7 +740,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 shared.state.job = f"Batch {n+1} out of {p.n_iter}"
 
             with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast():
-                samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
+                samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
 
             x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
             for x in x_samples_ddim:
@@ -688,7 +751,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
             del samples_ddim
 
-            if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
+            if lowvram.is_enabled(shared.sd_model):
                 lowvram.send_everything_to_cpu()
 
             devices.torch_gc()
@@ -704,7 +767,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
                 if p.restore_faces:
                     if opts.save and not p.do_not_save_samples and opts.save_images_before_face_restoration:
-                        images.save_image(Image.fromarray(x_sample), p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-face-restoration")
+                        images.save_image(Image.fromarray(x_sample), p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-face-restoration")
 
                     devices.torch_gc()
 
@@ -721,13 +784,13 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 if p.color_corrections is not None and i < len(p.color_corrections):
                     if opts.save and not p.do_not_save_samples and opts.save_images_before_color_correction:
                         image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images)
-                        images.save_image(image_without_cc, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-color-correction")
+                        images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-color-correction")
                     image = apply_color_correction(p.color_corrections[i], image)
 
                 image = apply_overlay(image, p.paste_to, i, p.overlay_images)
 
                 if opts.samples_save and not p.do_not_save_samples:
-                    images.save_image(image, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p)
+                    images.save_image(image, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p)
 
                 text = infotext(n, i)
                 infotexts.append(text)
@@ -740,10 +803,10 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                     image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, p.mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
 
                     if opts.save_mask:
-                        images.save_image(image_mask, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask")
+                        images.save_image(image_mask, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask")
 
                     if opts.save_mask_composite:
-                        images.save_image(image_mask_composite, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask-composite")
+                        images.save_image(image_mask_composite, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask-composite")
 
                     if opts.return_mask:
                         output_images.append(image_mask)
@@ -765,7 +828,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             grid = images.image_grid(output_images, p.batch_size)
 
             if opts.return_grid:
-                text = infotext()
+                text = infotext(use_main_prompt=True)
                 infotexts.insert(0, text)
                 if opts.enable_pnginfo:
                     grid.info["parameters"] = text
@@ -773,10 +836,10 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 index_of_first_image = 1
 
             if opts.grid_save:
-                images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p, grid=True)
+                images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], opts.grid_format, info=infotext(use_main_prompt=True), short_filename=not opts.grid_extended_filename, p=p, grid=True)
 
-    if not p.disable_extra_networks and extra_network_data:
+    if not p.disable_extra_networks and p.extra_network_data:
-        extra_networks.deactivate(p, extra_network_data)
+        extra_networks.deactivate(p, p.extra_network_data)
 
     devices.torch_gc()
 
@@ -785,7 +848,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
         images_list=output_images,
         seed=p.all_seeds[0],
         info=infotext(),
-        comments="".join(f"\n\n{comment}" for comment in comments),
+        comments="".join(f"{comment}\n" for comment in comments),
         subseed=p.all_subseeds[0],
         index_of_first_image=index_of_first_image,
         infotexts=infotexts,
@@ -811,8 +874,10 @@ def old_hires_fix_first_pass_dimensions(width, height):
 
 class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
     sampler = None
+    cached_hr_uc = [None, None]
+    cached_hr_c = [None, None]
 
-    def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, **kwargs):
+    def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler_name: str = None, hr_prompt: str = '', hr_negative_prompt: str = '', **kwargs):
         super().__init__(**kwargs)
         self.enable_hr = enable_hr
         self.denoising_strength = denoising_strength
@@ -823,6 +888,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         self.hr_resize_y = hr_resize_y
         self.hr_upscale_to_x = hr_resize_x
         self.hr_upscale_to_y = hr_resize_y
+        self.hr_sampler_name = hr_sampler_name
+        self.hr_prompt = hr_prompt
+        self.hr_negative_prompt = hr_negative_prompt
+        self.all_hr_prompts = None
+        self.all_hr_negative_prompts = None
 
         if firstphase_width != 0 or firstphase_height != 0:
             self.hr_upscale_to_x = self.width
@@ -834,8 +904,26 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         self.truncate_y = 0
         self.applied_old_hires_behavior_to = None
 
+        self.hr_prompts = None
+        self.hr_negative_prompts = None
+        self.hr_extra_network_data = None
+
+        self.cached_hr_uc = StableDiffusionProcessingTxt2Img.cached_hr_uc
+        self.cached_hr_c = StableDiffusionProcessingTxt2Img.cached_hr_c
+        self.hr_c = None
+        self.hr_uc = None
+
     def init(self, all_prompts, all_seeds, all_subseeds):
         if self.enable_hr:
+            if self.hr_sampler_name is not None and self.hr_sampler_name != self.sampler_name:
+                self.extra_generation_params["Hires sampler"] = self.hr_sampler_name
+
+            if tuple(self.hr_prompt) != tuple(self.prompt):
+                self.extra_generation_params["Hires prompt"] = self.hr_prompt
+
+            if tuple(self.hr_negative_prompt) != tuple(self.negative_prompt):
+                self.extra_generation_params["Hires negative prompt"] = self.hr_negative_prompt
+
             if opts.use_old_hires_fix_width_height and self.applied_old_hires_behavior_to != (self.width, self.height):
                 self.hr_resize_x = self.width
                 self.hr_resize_y = self.height
@@ -901,7 +989,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest")
         if self.enable_hr and latent_scale_mode is None:
-            assert len([x for x in shared.sd_upscalers if x.name == self.hr_upscaler]) > 0, f"could not find upscaler named {self.hr_upscaler}"
+            if not any(x.name == self.hr_upscaler for x in shared.sd_upscalers):
+                raise Exception(f"could not find upscaler named {self.hr_upscaler}")
 
         x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
         samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
@@ -965,9 +1054,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         shared.state.nextjob()
 
-        img2img_sampler_name = self.sampler_name
+        img2img_sampler_name = self.hr_sampler_name or self.sampler_name
+
         if self.sampler_name in ['PLMS', 'UniPC']:  # PLMS/UniPC do not support img2img so we just silently switch to DDIM
             img2img_sampler_name = 'DDIM'
+
         self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model)
 
         samples = samples[:, :, self.truncate_y//2:samples.shape[2]-(self.truncate_y+1)//2, self.truncate_x//2:samples.shape[3]-(self.truncate_x+1)//2]
@@ -978,17 +1069,101 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         x = None
         devices.torch_gc()
 
-        samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
+        if not self.disable_extra_networks:
+            with devices.autocast():
+                extra_networks.activate(self, self.hr_extra_network_data)
+
+        with devices.autocast():
+            self.calculate_hr_conds()
+
+        sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio(for_hr=True))
+
+        if self.scripts is not None:
+            self.scripts.before_hr(self)
+
+        samples = self.sampler.sample_img2img(self, samples, noise, self.hr_c, self.hr_uc, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
+
+        sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio())
 
         self.is_hr_pass = False
 
         return samples
 
+    def close(self):
+        super().close()
+        self.hr_c = None
+        self.hr_uc = None
+        if not opts.experimental_persistent_cond_cache:
+            StableDiffusionProcessingTxt2Img.cached_hr_uc = [None, None]
+            StableDiffusionProcessingTxt2Img.cached_hr_c = [None, None]
+
+    def setup_prompts(self):
+        super().setup_prompts()
+
+        if not self.enable_hr:
+            return
+
+        if self.hr_prompt == '':
+            self.hr_prompt = self.prompt
+
+        if self.hr_negative_prompt == '':
+            self.hr_negative_prompt = self.negative_prompt
+
+        if type(self.hr_prompt) == list:
+            self.all_hr_prompts = self.hr_prompt
+        else:
+            self.all_hr_prompts = self.batch_size * self.n_iter * [self.hr_prompt]
+
+        if type(self.hr_negative_prompt) == list:
+            self.all_hr_negative_prompts = self.hr_negative_prompt
+        else:
+            self.all_hr_negative_prompts = self.batch_size * self.n_iter * [self.hr_negative_prompt]
+
+        self.all_hr_prompts = [shared.prompt_styles.apply_styles_to_prompt(x, self.styles) for x in self.all_hr_prompts]
+        self.all_hr_negative_prompts = [shared.prompt_styles.apply_negative_styles_to_prompt(x, self.styles) for x in self.all_hr_negative_prompts]
+
+    def calculate_hr_conds(self):
+        if self.hr_c is not None:
+            return
+
+        self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, self.hr_negative_prompts, self.steps * self.step_multiplier, [self.cached_hr_uc, self.cached_uc], self.hr_extra_network_data)
+        self.hr_c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, self.hr_prompts, self.steps * self.step_multiplier, [self.cached_hr_c, self.cached_c], self.hr_extra_network_data)
+
+    def setup_conds(self):
+        super().setup_conds()
+
+        self.hr_uc = None
+        self.hr_c = None
+
+        if self.enable_hr:
+            if shared.opts.hires_fix_use_firstpass_conds:
+                self.calculate_hr_conds()
+
+            elif lowvram.is_enabled(shared.sd_model):  # if in lowvram mode, we need to calculate conds right away, before the cond NN is unloaded
+                with devices.autocast():
+                    extra_networks.activate(self, self.hr_extra_network_data)
+
+                self.calculate_hr_conds()
+
+                with devices.autocast():
+                    extra_networks.activate(self, self.extra_network_data)
+
+    def parse_extra_network_prompts(self):
+        res = super().parse_extra_network_prompts()
+
+        if self.enable_hr:
+            self.hr_prompts = self.all_hr_prompts[self.iteration * self.batch_size:(self.iteration + 1) * self.batch_size]
+            self.hr_negative_prompts = self.all_hr_negative_prompts[self.iteration * self.batch_size:(self.iteration + 1) * self.batch_size]
+
+            self.hr_prompts, self.hr_extra_network_data = extra_networks.parse_prompts(self.hr_prompts)
+
+        return res
+
 
 class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
     sampler = None
 
-    def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, image_cfg_scale: float = None, mask: Any = None, mask_blur: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, **kwargs):
+    def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, image_cfg_scale: float = None, mask: Any = None, mask_blur: int = None, mask_blur_x: int = 4, mask_blur_y: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, **kwargs):
         super().__init__(**kwargs)
 
         self.init_images = init_images
@@ -999,7 +1174,11 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
         self.image_mask = mask
         self.latent_mask = None
         self.mask_for_overlay = None
-        self.mask_blur = mask_blur
+        if mask_blur is not None:
+            mask_blur_x = mask_blur
+            mask_blur_y = mask_blur
+        self.mask_blur_x = mask_blur_x
+        self.mask_blur_y = mask_blur_y
         self.inpainting_fill = inpainting_fill
         self.inpaint_full_res = inpaint_full_res
         self.inpaint_full_res_padding = inpaint_full_res_padding
@@ -1021,8 +1200,17 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             if self.inpainting_mask_invert:
                 image_mask = ImageOps.invert(image_mask)
 
-            if self.mask_blur > 0:
+            if self.mask_blur_x > 0:
-                image_mask = image_mask.filter(ImageFilter.GaussianBlur(self.mask_blur))
+                np_mask = np.array(image_mask)
+                kernel_size = 2 * int(4 * self.mask_blur_x + 0.5) + 1
+                np_mask = cv2.GaussianBlur(np_mask, (kernel_size, 1), self.mask_blur_x)
+                image_mask = Image.fromarray(np_mask)
+
+            if self.mask_blur_y > 0:
+                np_mask = np.array(image_mask)
+                kernel_size = 2 * int(4 * self.mask_blur_y + 0.5) + 1
+                np_mask = cv2.GaussianBlur(np_mask, (1, kernel_size), self.mask_blur_y)
+                image_mask = Image.fromarray(np_mask)
 
             if self.inpaint_full_res:
                 self.mask_for_overlay = image_mask
@@ -1141,3 +1329,6 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
         devices.torch_gc()
 
         return samples
+
+    def get_token_merging_ratio(self, for_hr=False):
+        return self.token_merging_ratio or ("token_merging_ratio" in self.override_settings and opts.token_merging_ratio) or opts.token_merging_ratio_img2img or opts.token_merging_ratio

modules/progress.py

@@ -95,9 +95,20 @@ def progressapi(req: ProgressRequest):
         image = shared.state.current_image
         if image is not None:
             buffered = io.BytesIO()
-            image.save(buffered, format="png")
+
+            if opts.live_previews_image_format == "png":
+                # using optimize for large images takes an enormous amount of time
+                if max(*image.size) <= 256:
+                    save_kwargs = {"optimize": True}
+                else:
+                    save_kwargs = {"optimize": False, "compress_level": 1}
+
+            else:
+                save_kwargs = {}
+
+            image.save(buffered, format=opts.live_previews_image_format, **save_kwargs)
             base64_image = base64.b64encode(buffered.getvalue()).decode('ascii')
-            live_preview = f"data:image/png;base64,{base64_image}"
+            live_preview = f"data:image/{opts.live_previews_image_format};base64,{base64_image}"
             id_live_preview = shared.state.id_live_preview
         else:
             live_preview = None

modules/prompt_parser.py

@@ -54,18 +54,21 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
     """
 
     def collect_steps(steps, tree):
-        l = [steps]
+        res = [steps]
+
         class CollectSteps(lark.Visitor):
             def scheduled(self, tree):
                 tree.children[-1] = float(tree.children[-1])
                 if tree.children[-1] < 1:
                     tree.children[-1] *= steps
                 tree.children[-1] = min(steps, int(tree.children[-1]))
-                l.append(tree.children[-1])
+                res.append(tree.children[-1])
+
             def alternate(self, tree):
-                l.extend(range(1, steps+1))
+                res.extend(range(1, steps+1))
+
         CollectSteps().visit(tree)
-        return sorted(set(l))
+        return sorted(set(res))
 
     def at_step(step, tree):
         class AtStep(lark.Transformer):
@@ -92,7 +95,7 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
     def get_schedule(prompt):
         try:
             tree = schedule_parser.parse(prompt)
-        except lark.exceptions.LarkError as e:
+        except lark.exceptions.LarkError:
             if 0:
                 import traceback
                 traceback.print_exc()
@@ -140,7 +143,7 @@ def get_learned_conditioning(model, prompts, steps):
         conds = model.get_learned_conditioning(texts)
 
         cond_schedule = []
-        for i, (end_at_step, text) in enumerate(prompt_schedule):
+        for i, (end_at_step, _) in enumerate(prompt_schedule):
             cond_schedule.append(ScheduledPromptConditioning(end_at_step, conds[i]))
 
         cache[prompt] = cond_schedule
@@ -216,8 +219,8 @@ def reconstruct_cond_batch(c: List[List[ScheduledPromptConditioning]], current_s
     res = torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype)
     for i, cond_schedule in enumerate(c):
         target_index = 0
-        for current, (end_at, cond) in enumerate(cond_schedule):
+        for current, entry in enumerate(cond_schedule):
-            if current_step <= end_at:
+            if current_step <= entry.end_at_step:
                 target_index = current
                 break
         res[i] = cond_schedule[target_index].cond
@@ -231,13 +234,13 @@ def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step):
     tensors = []
     conds_list = []
 
-    for batch_no, composable_prompts in enumerate(c.batch):
+    for composable_prompts in c.batch:
         conds_for_batch = []
 
-        for cond_index, composable_prompt in enumerate(composable_prompts):
+        for composable_prompt in composable_prompts:
             target_index = 0
-            for current, (end_at, cond) in enumerate(composable_prompt.schedules):
+            for current, entry in enumerate(composable_prompt.schedules):
-                if current_step <= end_at:
+                if current_step <= entry.end_at_step:
                     target_index = current
                     break
 
@@ -333,11 +336,11 @@ def parse_prompt_attention(text):
             round_brackets.append(len(res))
         elif text == '[':
             square_brackets.append(len(res))
-        elif weight is not None and len(round_brackets) > 0:
+        elif weight is not None and round_brackets:
             multiply_range(round_brackets.pop(), float(weight))
-        elif text == ')' and len(round_brackets) > 0:
+        elif text == ')' and round_brackets:
             multiply_range(round_brackets.pop(), round_bracket_multiplier)
-        elif text == ']' and len(square_brackets) > 0:
+        elif text == ']' and square_brackets:
             multiply_range(square_brackets.pop(), square_bracket_multiplier)
         else:
             parts = re.split(re_break, text)

modules/realesrgan_model.py

@@ -1,15 +1,13 @@
 import os
-import sys
-import traceback
 
 import numpy as np
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 from realesrgan import RealESRGANer
 
 from modules.upscaler import Upscaler, UpscalerData
 from modules.shared import cmd_opts, opts
-from modules import modelloader
+from modules import modelloader, errors
+
 
 class UpscalerRealESRGAN(Upscaler):
     def __init__(self, path):
@@ -17,9 +15,9 @@ class UpscalerRealESRGAN(Upscaler):
         self.user_path = path
         super().__init__()
         try:
-            from basicsr.archs.rrdbnet_arch import RRDBNet
+            from basicsr.archs.rrdbnet_arch import RRDBNet  # noqa: F401
-            from realesrgan import RealESRGANer
+            from realesrgan import RealESRGANer  # noqa: F401
-            from realesrgan.archs.srvgg_arch import SRVGGNetCompact
+            from realesrgan.archs.srvgg_arch import SRVGGNetCompact  # noqa: F401
             self.enable = True
             self.scalers = []
             scalers = self.load_models(path)
@@ -36,8 +34,7 @@ class UpscalerRealESRGAN(Upscaler):
                     self.scalers.append(scaler)
 
         except Exception:
-            print("Error importing Real-ESRGAN:", file=sys.stderr)
+            errors.report("Error importing Real-ESRGAN", exc_info=True)
-            print(traceback.format_exc(), file=sys.stderr)
             self.enable = False
             self.scalers = []
 
@@ -45,9 +42,10 @@ class UpscalerRealESRGAN(Upscaler):
         if not self.enable:
             return img
 
+        try:
             info = self.load_model(path)
-        if not os.path.exists(info.local_data_path):
+        except Exception:
-            print(f"Unable to load RealESRGAN model: {info.name}")
+            errors.report(f"Unable to load RealESRGAN model {path}", exc_info=True)
             return img
 
         upsampler = RealESRGANer(
@@ -65,21 +63,17 @@ class UpscalerRealESRGAN(Upscaler):
         return image
 
     def load_model(self, path):
-        try:
+        for scaler in self.scalers:
-            info = next(iter([scaler for scaler in self.scalers if scaler.data_path == path]), None)
+            if scaler.data_path == path:
-
+                if scaler.local_data_path.startswith("http"):
-            if info is None:
+                    scaler.local_data_path = modelloader.load_file_from_url(
-                print(f"Unable to find model info: {path}")
+                        scaler.data_path,
-                return None
+                        model_dir=self.model_download_path,
-
+                    )
-            if info.local_data_path.startswith("http"):
+                if not os.path.exists(scaler.local_data_path):
-                info.local_data_path = load_file_from_url(url=info.data_path, model_dir=self.model_path, progress=True)
+                    raise FileNotFoundError(f"RealESRGAN data missing: {scaler.local_data_path}")
-
+                return scaler
-            return info
+        raise ValueError(f"Unable to find model info: {path}")
-        except Exception as e:
-            print(f"Error making Real-ESRGAN models list: {e}", file=sys.stderr)
-            print(traceback.format_exc(), file=sys.stderr)
-        return None
 
     def load_models(self, _):
         return get_realesrgan_models(self)
@@ -134,6 +128,5 @@ def get_realesrgan_models(scaler):
             ),
         ]
         return models
-    except Exception as e:
+    except Exception:
-        print("Error making Real-ESRGAN models list:", file=sys.stderr)
+        errors.report("Error making Real-ESRGAN models list", exc_info=True)
-        print(traceback.format_exc(), file=sys.stderr)

modules/restart.py

@@ -0,0 +1,23 @@
+import os
+from pathlib import Path
+
+from modules.paths_internal import script_path
+
+
+def is_restartable() -> bool:
+    """
+    Return True if the webui is restartable (i.e. there is something watching to restart it with)
+    """
+    return bool(os.environ.get('SD_WEBUI_RESTART'))
+
+
+def restart_program() -> None:
+    """creates file tmp/restart and immediately stops the process, which webui.bat/webui.sh interpret as a command to start webui again"""
+
+    (Path(script_path) / "tmp" / "restart").touch()
+
+    stop_program()
+
+
+def stop_program() -> None:
+    os._exit(0)