StableDiffusion/WebUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'release_candidate'

Browse Source
This commit is contained in:
AUTOMATIC 2023-05-27 20:13:26 +03:00
commit 50906bf78b
156 changed files with 5065 additions and 3665 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.eslintignore Normal file
View File

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

88
.eslintrc.js Normal file
View File

@ -0,0 +1,88 @@
/* 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",
onUiLoaded: "readonly",
onUiUpdate: "readonly",
onOptionsChanged: "readonly",
uiCurrentTab: "writable",
uiElementIsVisible: "readonly",
uiElementInSight: "readonly",
executeCallbacks: "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",
}
};

2
.git-blame-ignore-revs Normal file
View File

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

21
.github/ISSUE_TEMPLATE/bug_report.yml vendored
View File

@ -47,6 +47,15 @@ body:
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.)
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 +68,18 @@ 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: browsers
attributes:

33
.github/pull_request_template.md vendored
View File

@ -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.
**Additional notes and description of your changes**
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.
- [ ] 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
- [ ] 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)

49
.github/workflows/on_pull_request.yaml vendored
View File

@ -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
cache: pip
cache-dependency-path: |
**/requirements*txt
- name: Install PyLint
run: |
python -m pip install --upgrade pip
pip install pylint
# This lets PyLint check to see if it can resolve imports
- name: Install dependencies
run: |
export COMMANDLINE_ARGS="--skip-torch-cuda-test --exit"
python launch.py
- name: Analysing the code with pylint
run: |
pylint $(git ls-files '*.py')
python-version: 3.11
# NB: there's no cache: pip here since we're not installing anything
# from the requirements.txt file(s) in the repository; it's faster
# not to have GHA download an (at the time of writing) 4 GB cache
# of PyTorch and other dependencies.
- name: Install Ruff
run: pip install ruff==0.0.265
- name: Run Ruff
run: ruff .
lint-js:
runs-on: ubuntu-latest
steps:
- name: Checkout Code
uses: actions/checkout@v3
- name: Install Node.js
uses: actions/setup-node@v3
with:
node-version: 18
- run: npm i --ci
- run: npm run lint

53
.github/workflows/run_tests.yaml vendored
View File

@ -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
--add-stop-route
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
- name: Upload main app stdout-stderr
run: |
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/_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
path: |
test/stdout.txt
test/stderr.txt
name: output
path: output.txt
- name: Upload coverage HTML
uses: actions/upload-artifact@v3
if: always()
with:
name: htmlcov
path: htmlcov

3
.gitignore vendored
View File

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

138
CHANGELOG.md
View File

@ -1,56 +1,116 @@
## Upcoming 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
* add filename patterns: [denoising]
* 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: 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: add an option to use old method of applying loras (producing same results as with kohya-ss)
* do not wait for Stable Diffusion model to load at startup
* add filename patterns: `[denoising]`
* 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: 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: 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
* torch bumped to 2.0.1
* --subpath option for gradio for use with reverse proxy
* linux/OSX: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)
* possible frontend optimization: do not apply localizations if there are none
* Add extra `None` option for VAE in XYZ plot
* bump Gradio to 3.29.0
* bump PyTorch to 2.0.1
* `--subpath` option for gradio for use with reverse proxy
* Linux/macOS: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)
* do not apply localizations if there are none (possible frontend optimization)
* 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
* Add api method to get LoRA models with prompt
* tooltip localization support
* 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 +118,20 @@
## 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 +140,22 @@
* button to restore the progress from session lost / tab reload
### Minor:
* gradio bumped to 3.28.1
* in extra tab, change extras "scale to" to sliders
* bump Gradio to 3.28.1
* 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
* sort textual inversion embeddings by name (case insensitive)
* change Linux installation script to install into current directory rather than `/home/username`
* 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
* add disable_tls_verify arg for use with self-signed certs
* make the extra networks UI fixed height and scrollable
* add `disable_tls_verify` arg for use with self-signed certs
### Extensions:
* Add reload callback
* add is_hr_pass field for processing
* add reload callback
* add `is_hr_pass` field for processing
### Bug Fixes:
* fix broken batch image processing on 'Extras/Batch Process' tab
@ -111,10 +171,10 @@
* 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 --skip-install not working
* outpainting Mk2 & Poorman should use the SAMPLE file format to save images, not GRID file format
* do not fail all Loras if some have failed to load when making a picture
* fix `--realesrgan-models-path` and `--ldsr-models-path` not working
* fix `--skip-install` not working
* use SAMPLE file format in Outpainting Mk2 & Poorman
* do not fail all LoRAs if some have failed to load when making a picture
## 1.0.0
* everything

9
README.md
View File

@ -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)

13
extensions-builtin/LDSR/ldsr_model_arch.py
View File

@ -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:
@ -131,11 +130,11 @@ class LDSR:
im_og = im_og.resize((width_downsampled_pre, height_downsampled_pre), Image.LANCZOS)
else:
print(f"Down sample rate is 1 from {target_scale} / 4 (Not downsampling)")
# pad width and height to multiples of 64, pads with the edge values of image to avoid artifacts
pad_w, pad_h = np.max(((2, 2), np.ceil(np.array(im_og.size) / 64).astype(int)), axis=0) * 64 - im_og.size
im_padded = Image.fromarray(np.pad(np.array(im_og), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge'))
logs = self.run(model["model"], im_padded, diffusion_steps, eta)
sample = logs["sample"]
@ -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

7
extensions-builtin/LDSR/scripts/ldsr_model.py
View File

@ -7,7 +7,8 @@ from basicsr.utils.download_util import load_file_from_url
from modules.upscaler import Upscaler, UpscalerData
from ldsr_model_arch import LDSR
from modules import shared, script_callbacks
import sd_hijack_autoencoder, sd_hijack_ddpm_v1
import sd_hijack_autoencoder # noqa: F401
import sd_hijack_ddpm_v1 # noqa: F401
class UpscalerLDSR(Upscaler):
@ -44,9 +45,9 @@ 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 if local_ckpt_path is not None else load_file_from_url(url=self.model_url, model_dir=self.model_download_path, file_name="model.ckpt", progress=True)
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 if local_yaml_path is not None else load_file_from_url(url=self.yaml_url, model_dir=self.model_download_path, file_name="project.yaml", progress=True)
try:
return LDSR(model, yaml)

28
extensions-builtin/LDSR/sd_hijack_autoencoder.py
View File

@ -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 torch.optim.lr_scheduler import LambdaLR
from ldm.modules.ema import LitEma
from taming.modules.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
@ -76,11 +81,11 @@ 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]
@ -165,7 +170,7 @@ 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 +237,7 @@ 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 +254,8 @@ 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 +270,7 @@ 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 +288,5 @@ class VQModelInterface(VQModel):
dec = self.decoder(quant)
return dec
setattr(ldm.models.autoencoder, "VQModel", VQModel)
setattr(ldm.models.autoencoder, "VQModelInterface", VQModelInterface)
ldm.models.autoencoder.VQModel = VQModel
ldm.models.autoencoder.VQModelInterface = VQModelInterface

66
extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
View File

@ -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)
@ -182,13 +182,13 @@ 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]
@ -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
@ -460,7 +460,7 @@ class LatentDiffusionV1(DDPMV1):
self.instantiate_cond_stage(cond_stage_config)
self.cond_stage_forward = cond_stage_forward
self.clip_denoised = False
self.bbox_tokenizer = None
self.bbox_tokenizer = None
self.restarted_from_ckpt = False
if ckpt_path is not None:
@ -792,7 +792,7 @@ class LatentDiffusionV1(DDPMV1):
z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
# 2. apply model loop over last dim
if isinstance(self.first_stage_model, VQModelInterface):
if isinstance(self.first_stage_model, VQModelInterface):
output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
force_not_quantize=predict_cids or force_not_quantize)
for i in range(z.shape[-1])]
@ -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):
@ -900,7 +890,7 @@ class LatentDiffusionV1(DDPMV1):
if hasattr(self, "split_input_params"):
assert len(cond) == 1 # todo can only deal with one conditioning atm
assert not return_ids
assert not return_ids
ks = self.split_input_params["ks"] # eg. (128, 128)
stride = self.split_input_params["stride"] # eg. (64, 64)
@ -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 img_callback: img_callback(img, i)
if callback:
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 img_callback: img_callback(img, i)
if callback:
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)
setattr(ldm.models.diffusion.ddpm, "LatentDiffusionV1", LatentDiffusionV1)
setattr(ldm.models.diffusion.ddpm, "DiffusionWrapperV1", DiffusionWrapperV1)
setattr(ldm.models.diffusion.ddpm, "Layout2ImgDiffusionV1", Layout2ImgDiffusionV1)
ldm.models.diffusion.ddpm.DDPMV1 = DDPMV1
ldm.models.diffusion.ddpm.LatentDiffusionV1 = LatentDiffusionV1
ldm.models.diffusion.ddpm.DiffusionWrapperV1 = DiffusionWrapperV1
ldm.models.diffusion.ddpm.Layout2ImgDiffusionV1 = Layout2ImgDiffusionV1

18
extensions-builtin/Lora/extra_networks_lora.py
View File

@ -23,5 +23,23 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
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

80
extensions-builtin/Lora/lora.py
View File

@ -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 ext.lower() == ".safetensors":
if self.is_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):
lora = LoraModule(name)
lora.mtime = os.path.getmtime(filename)
def load_lora(name, lora_on_disk):
lora = LoraModule(name, lora_on_disk)
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:
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 len(failed_to_load_loras) > 0:
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", ())
setattr(self, "lora_weights_backup", None)
self.lora_current_names = ()
self.lora_weights_backup = None
def lora_Linear_forward(self, input):
@ -398,7 +437,8 @@ 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)
@ -428,7 +468,7 @@ 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 +492,10 @@ 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 = []

38
extensions-builtin/Lora/scripts/lora_script.py
View File

@ -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),
"lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}),
"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_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)

5
extensions-builtin/Lora/ui_extra_networks_lora.py
View File

@ -16,10 +16,7 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
for name, lora_on_disk in 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 = name
else:
alias = lora_on_disk.alias
alias = lora_on_disk.get_alias()
yield {
"name": name,

19
extensions-builtin/ScuNET/scripts/scunet_model.py
View File

@ -10,10 +10,9 @@ 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
from scunet_model_arch import SCUNet as net
from modules.shared import opts
from modules import images
class UpscalerScuNET(modules.upscaler.Upscaler):
@ -122,8 +121,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
def load_model(self, path: str):
device = devices.get_device_for('scunet')
if "http" in path:
filename = load_file_from_url(url=self.model_url, model_dir=self.model_path, file_name="%s.pth" % self.name,
progress=True)
filename = load_file_from_url(url=self.model_url, model_dir=self.model_download_path, file_name="%s.pth" % self.name, progress=True)
else:
filename = path
if not os.path.exists(os.path.join(self.model_path, filename)) or filename is None:
@ -133,8 +131,19 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
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)

11
extensions-builtin/ScuNET/scunet_model_arch.py
View File

@ -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),
dims=(1, 2))
if self.type != 'W':
output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), dims=(1, 2))
return output
def relative_embedding(self):
@ -262,4 +265,4 @@ class SCUNet(nn.Module):
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.LayerNorm):
nn.init.constant_(m.bias, 0)
nn.init.constant_(m.weight, 1.0)
nn.init.constant_(m.weight, 1.0)

9
extensions-builtin/SwinIR/scripts/swinir_model.py
View File

@ -1,4 +1,3 @@
import contextlib
import os
import numpy as np
@ -8,7 +7,7 @@ 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_v2 import Swin2SR as net2
from modules.upscaler import Upscaler, UpscalerData
@ -45,14 +44,14 @@ class UpscalerSwinIR(Upscaler):
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:
dl_name = "%s%s" % (self.model_name.replace(" ", "_"), ".pth")
filename = load_file_from_url(url=path, model_dir=self.model_path, file_name=dl_name, progress=True)
filename = load_file_from_url(url=path, model_dir=self.model_download_path, file_name=dl_name, progress=True)
else:
filename = path
if filename is None or not os.path.exists(filename):
@ -151,7 +150,7 @@ def inference(img, model, tile, tile_overlap, window_size, scale):
for w_idx in w_idx_list:
if state.interrupted or state.skipped:
break
in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
out_patch = model(in_patch)
out_patch_mask = torch.ones_like(out_patch)

6
extensions-builtin/SwinIR/swinir_model_arch.py
View File

@ -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,
@ -805,7 +805,7 @@ class SwinIR(nn.Module):
def forward(self, x):
H, W = x.shape[2:]
x = self.check_image_size(x)
self.mean = self.mean.type_as(x)
x = (x - self.mean) * self.img_range
@ -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()

58
extensions-builtin/SwinIR/swinir_model_arch_v2.py
View File

@ -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
@ -241,7 +241,7 @@ class SwinTransformerBlock(nn.Module):
attn_mask = None
self.register_buffer("attn_mask", attn_mask)
def calculate_mask(self, x_size):
# calculate attention mask for SW-MSA
H, W = x_size
@ -263,7 +263,7 @@ class SwinTransformerBlock(nn.Module):
attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
return attn_mask
return attn_mask
def forward(self, x, x_size):
H, W = x_size
@ -288,7 +288,7 @@ class SwinTransformerBlock(nn.Module):
attn_windows = self.attn(x_windows, mask=self.attn_mask) # nW*B, window_size*window_size, C
else:
attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device))
# merge windows
attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
shifted_x = window_reverse(attn_windows, self.window_size, H, W) # B H' W' C
@ -369,7 +369,7 @@ class PatchMerging(nn.Module):
H, W = self.input_resolution
flops = (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim
flops += H * W * self.dim // 2
return flops
return flops
class BasicLayer(nn.Module):
""" A basic Swin Transformer layer for one stage.
@ -447,7 +447,7 @@ class BasicLayer(nn.Module):
nn.init.constant_(blk.norm1.weight, 0)
nn.init.constant_(blk.norm2.bias, 0)
nn.init.constant_(blk.norm2.weight, 0)
class PatchEmbed(nn.Module):
r""" Image to Patch Embedding
Args:
@ -492,7 +492,7 @@ class PatchEmbed(nn.Module):
flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1])
if self.norm is not None:
flops += Ho * Wo * self.embed_dim
return flops
return flops
class RSTB(nn.Module):
"""Residual Swin Transformer Block (RSTB).
@ -531,7 +531,7 @@ class RSTB(nn.Module):
num_heads=num_heads,
window_size=window_size,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qkv_bias=qkv_bias,
drop=drop, attn_drop=attn_drop,
drop_path=drop_path,
norm_layer=norm_layer,
@ -622,7 +622,7 @@ class Upsample(nn.Sequential):
else:
raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.')
super(Upsample, self).__init__(*m)
class Upsample_hf(nn.Sequential):
"""Upsample module.
@ -642,7 +642,7 @@ class Upsample_hf(nn.Sequential):
m.append(nn.PixelShuffle(3))
else:
raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.')
super(Upsample_hf, self).__init__(*m)
super(Upsample_hf, self).__init__(*m)
class UpsampleOneStep(nn.Sequential):
@ -667,8 +667,8 @@ class UpsampleOneStep(nn.Sequential):
H, W = self.input_resolution
flops = H * W * self.num_feat * 3 * 9
return flops
class Swin2SR(nn.Module):
r""" Swin2SR
@ -698,8 +698,8 @@ 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],
window_size=7, mlp_ratio=4., qkv_bias=True,
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,
use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv',
@ -764,7 +764,7 @@ class Swin2SR(nn.Module):
num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=self.mlp_ratio,
qkv_bias=qkv_bias,
qkv_bias=qkv_bias,
drop=drop_rate, attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results
norm_layer=norm_layer,
@ -776,7 +776,7 @@ class Swin2SR(nn.Module):
)
self.layers.append(layer)
if self.upsampler == 'pixelshuffle_hf':
self.layers_hf = nn.ModuleList()
for i_layer in range(self.num_layers):
@ -787,7 +787,7 @@ class Swin2SR(nn.Module):
num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=self.mlp_ratio,
qkv_bias=qkv_bias,
qkv_bias=qkv_bias,
drop=drop_rate, attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results
norm_layer=norm_layer,
@ -799,7 +799,7 @@ class Swin2SR(nn.Module):
)
self.layers_hf.append(layer)
self.norm = norm_layer(self.num_features)
# build the last conv layer in deep feature extraction
@ -829,10 +829,10 @@ class Swin2SR(nn.Module):
self.conv_aux = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
self.conv_after_aux = nn.Sequential(
nn.Conv2d(3, num_feat, 3, 1, 1),
nn.LeakyReLU(inplace=True))
nn.LeakyReLU(inplace=True))
self.upsample = Upsample(upscale, num_feat)
self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
elif self.upsampler == 'pixelshuffle_hf':
self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1),
nn.LeakyReLU(inplace=True))
@ -846,7 +846,7 @@ class Swin2SR(nn.Module):
nn.Conv2d(embed_dim, num_feat, 3, 1, 1),
nn.LeakyReLU(inplace=True))
self.conv_last_hf = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
elif self.upsampler == 'pixelshuffledirect':
# for lightweight SR (to save parameters)
self.upsample = UpsampleOneStep(upscale, embed_dim, num_out_ch,
@ -905,7 +905,7 @@ class Swin2SR(nn.Module):
x = self.patch_unembed(x, x_size)
return x
def forward_features_hf(self, x):
x_size = (x.shape[2], x.shape[3])
x = self.patch_embed(x)
@ -919,7 +919,7 @@ class Swin2SR(nn.Module):
x = self.norm(x) # B L C
x = self.patch_unembed(x, x_size)
return x
return x
def forward(self, x):
H, W = x.shape[2:]
@ -951,7 +951,7 @@ class Swin2SR(nn.Module):
x = self.conv_after_body(self.forward_features(x)) + x
x_before = self.conv_before_upsample(x)
x_out = self.conv_last(self.upsample(x_before))
x_hf = self.conv_first_hf(x_before)
x_hf = self.conv_after_body_hf(self.forward_features_hf(x_hf)) + x_hf
x_hf = self.conv_before_upsample_hf(x_hf)
@ -977,15 +977,15 @@ class Swin2SR(nn.Module):
x_first = self.conv_first(x)
res = self.conv_after_body(self.forward_features(x_first)) + x_first
x = x + self.conv_last(res)
x = x / self.img_range + self.mean
if self.upsampler == "pixelshuffle_aux":
return x[:, :, :H*self.upscale, :W*self.upscale], aux
elif self.upsampler == "pixelshuffle_hf":
x_out = x_out / self.img_range + self.mean
return x_out[:, :, :H*self.upscale, :W*self.upscale], x[:, :, :H*self.upscale, :W*self.upscale], x_hf[:, :, :H*self.upscale, :W*self.upscale]
else:
return x[:, :, :H*self.upscale, :W*self.upscale]
@ -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()
@ -1014,4 +1014,4 @@ if __name__ == '__main__':
x = torch.randn((1, 3, height, width))
x = model(x)
print(x.shape)
print(x.shape)

52
extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js
View File

@ -4,39 +4,39 @@
// If there's a mismatch, the keyword counter turns red and if you hover on it, a tooltip tells you what's wrong.
function checkBrackets(textArea, counterElt) {
var counts = {};
(textArea.value.match(/[(){}\[\]]/g) || []).forEach(bracket => {
counts[bracket] = (counts[bracket] || 0) + 1;
});
var errors = [];
var counts = {};
(textArea.value.match(/[(){}[\]]/g) || []).forEach(bracket => {
counts[bracket] = (counts[bracket] || 0) + 1;
});
var errors = [];
function checkPair(open, close, kind) {
if (counts[open] !== counts[close]) {
errors.push(
`${open}...${close} - Detected ${counts[open] || 0} opening and ${counts[close] || 0} closing ${kind}.`
);
function checkPair(open, close, kind) {
if (counts[open] !== counts[close]) {
errors.push(
`${open}...${close} - Detected ${counts[open] || 0} opening and ${counts[close] || 0} closing ${kind}.`
);
}
}
}
checkPair('(', ')', 'round brackets');
checkPair('[', ']', 'square brackets');
checkPair('{', '}', 'curly brackets');
counterElt.title = errors.join('\n');
counterElt.classList.toggle('error', errors.length !== 0);
checkPair('(', ')', 'round brackets');
checkPair('[', ']', 'square brackets');
checkPair('{', '}', 'curly brackets');
counterElt.title = errors.join('\n');
counterElt.classList.toggle('error', errors.length !== 0);
}
function setupBracketChecking(id_prompt, id_counter) {
var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea");
var counter = gradioApp().getElementById(id_counter)
var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea");
var counter = gradioApp().getElementById(id_counter);
if (textarea && counter) {
textarea.addEventListener("input", () => checkBrackets(textarea, counter));
}
if (textarea && counter) {
textarea.addEventListener("input", () => checkBrackets(textarea, counter));
}
}
onUiLoaded(function () {
setupBracketChecking('txt2img_prompt', 'txt2img_token_counter');
setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter');
setupBracketChecking('img2img_prompt', 'img2img_token_counter');
setupBracketChecking('img2img_neg_prompt', 'img2img_negative_token_counter');
onUiLoaded(function() {
setupBracketChecking('txt2img_prompt', 'txt2img_token_counter');
setupBracketChecking('txt2img_neg_prompt', 'txt2img_negative_token_counter');
setupBracketChecking('img2img_prompt', 'img2img_token_counter');
setupBracketChecking('img2img_neg_prompt', 'img2img_negative_token_counter');
});

5
html/extra-networks-card.html
View File

@ -1,15 +1,14 @@
<div class='card' style={style} onclick={card_clicked}>
{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>

26
html/licenses.html
View File

@ -661,4 +661,30 @@ 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>
<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>

224
javascript/aspectRatioOverlay.js
View File

@ -1,111 +1,113 @@
let currentWidth = null;
let currentHeight = null;
let arFrameTimeout = setTimeout(function(){},0);
function dimensionChange(e, is_width, is_height){
if(is_width){
currentWidth = e.target.value*1.0
}
if(is_height){
currentHeight = e.target.value*1.0
}
var inImg2img = gradioApp().querySelector("#tab_img2img").style.display == "block";
if(!inImg2img){
return;
}
var targetElement = null;
var tabIndex = get_tab_index('mode_img2img')
if(tabIndex == 0){ // img2img
targetElement = gradioApp().querySelector('#img2img_image div[data-testid=image] img');
} else if(tabIndex == 1){ //Sketch
targetElement = gradioApp().querySelector('#img2img_sketch div[data-testid=image] img');
} else if(tabIndex == 2){ // Inpaint
targetElement = gradioApp().querySelector('#img2maskimg div[data-testid=image] img');
} else if(tabIndex == 3){ // Inpaint sketch
targetElement = gradioApp().querySelector('#inpaint_sketch div[data-testid=image] img');
}
if(targetElement){
var arPreviewRect = gradioApp().querySelector('#imageARPreview');
if(!arPreviewRect){
arPreviewRect = document.createElement('div')
arPreviewRect.id = "imageARPreview";
gradioApp().appendChild(arPreviewRect)
}
var viewportOffset = targetElement.getBoundingClientRect();
var viewportscale = Math.min( targetElement.clientWidth/targetElement.naturalWidth, targetElement.clientHeight/targetElement.naturalHeight )
var scaledx = targetElement.naturalWidth*viewportscale
var scaledy = targetElement.naturalHeight*viewportscale
var cleintRectTop = (viewportOffset.top+window.scrollY)
var cleintRectLeft = (viewportOffset.left+window.scrollX)
var cleintRectCentreY = cleintRectTop + (targetElement.clientHeight/2)
var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth/2)
var arscale = Math.min( scaledx/currentWidth, scaledy/currentHeight )
var arscaledx = currentWidth*arscale
var arscaledy = currentHeight*arscale
var arRectTop = cleintRectCentreY-(arscaledy/2)
var arRectLeft = cleintRectCentreX-(arscaledx/2)
var arRectWidth = arscaledx
var arRectHeight = arscaledy
arPreviewRect.style.top = arRectTop+'px';
arPreviewRect.style.left = arRectLeft+'px';
arPreviewRect.style.width = arRectWidth+'px';
arPreviewRect.style.height = arRectHeight+'px';
clearTimeout(arFrameTimeout);
arFrameTimeout = setTimeout(function(){
arPreviewRect.style.display = 'none';
},2000);
arPreviewRect.style.display = 'block';
}
}
onUiUpdate(function(){
var arPreviewRect = gradioApp().querySelector('#imageARPreview');
if(arPreviewRect){
arPreviewRect.style.display = 'none';
}
var tabImg2img = gradioApp().querySelector("#tab_img2img");
if (tabImg2img) {
var inImg2img = tabImg2img.style.display == "block";
if(inImg2img){
let inputs = gradioApp().querySelectorAll('input');
inputs.forEach(function(e){
var is_width = e.parentElement.id == "img2img_width"
var is_height = e.parentElement.id == "img2img_height"
if((is_width || is_height) && !e.classList.contains('scrollwatch')){
e.addEventListener('input', function(e){dimensionChange(e, is_width, is_height)} )
e.classList.add('scrollwatch')
}
if(is_width){
currentWidth = e.value*1.0
}
if(is_height){
currentHeight = e.value*1.0
}
})
}
}
});
let currentWidth = null;
let currentHeight = null;
let arFrameTimeout = setTimeout(function() {}, 0);
function dimensionChange(e, is_width, is_height) {
if (is_width) {
currentWidth = e.target.value * 1.0;
}
if (is_height) {
currentHeight = e.target.value * 1.0;
}
var inImg2img = gradioApp().querySelector("#tab_img2img").style.display == "block";
if (!inImg2img) {
return;
}
var targetElement = null;
var tabIndex = get_tab_index('mode_img2img');
if (tabIndex == 0) { // img2img
targetElement = gradioApp().querySelector('#img2img_image div[data-testid=image] img');
} else if (tabIndex == 1) { //Sketch
targetElement = gradioApp().querySelector('#img2img_sketch div[data-testid=image] img');
} else if (tabIndex == 2) { // Inpaint
targetElement = gradioApp().querySelector('#img2maskimg div[data-testid=image] img');
} else if (tabIndex == 3) { // Inpaint sketch
targetElement = gradioApp().querySelector('#inpaint_sketch div[data-testid=image] img');
}
if (targetElement) {
var arPreviewRect = gradioApp().querySelector('#imageARPreview');
if (!arPreviewRect) {
arPreviewRect = document.createElement('div');
arPreviewRect.id = "imageARPreview";
gradioApp().appendChild(arPreviewRect);
}
var viewportOffset = targetElement.getBoundingClientRect();
var viewportscale = Math.min(targetElement.clientWidth / targetElement.naturalWidth, targetElement.clientHeight / targetElement.naturalHeight);
var scaledx = targetElement.naturalWidth * viewportscale;
var scaledy = targetElement.naturalHeight * viewportscale;
var cleintRectTop = (viewportOffset.top + window.scrollY);
var cleintRectLeft = (viewportOffset.left + window.scrollX);
var cleintRectCentreY = cleintRectTop + (targetElement.clientHeight / 2);
var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth / 2);
var arscale = Math.min(scaledx / currentWidth, scaledy / currentHeight);
var arscaledx = currentWidth * arscale;
var arscaledy = currentHeight * arscale;
var arRectTop = cleintRectCentreY - (arscaledy / 2);
var arRectLeft = cleintRectCentreX - (arscaledx / 2);
var arRectWidth = arscaledx;
var arRectHeight = arscaledy;
arPreviewRect.style.top = arRectTop + 'px';
arPreviewRect.style.left = arRectLeft + 'px';
arPreviewRect.style.width = arRectWidth + 'px';
arPreviewRect.style.height = arRectHeight + 'px';
clearTimeout(arFrameTimeout);
arFrameTimeout = setTimeout(function() {
arPreviewRect.style.display = 'none';
}, 2000);
arPreviewRect.style.display = 'block';
}
}
onUiUpdate(function() {
var arPreviewRect = gradioApp().querySelector('#imageARPreview');
if (arPreviewRect) {
arPreviewRect.style.display = 'none';
}
var tabImg2img = gradioApp().querySelector("#tab_img2img");
if (tabImg2img) {
var inImg2img = tabImg2img.style.display == "block";
if (inImg2img) {
let inputs = gradioApp().querySelectorAll('input');
inputs.forEach(function(e) {
var is_width = e.parentElement.id == "img2img_width";
var is_height = e.parentElement.id == "img2img_height";
if ((is_width || is_height) && !e.classList.contains('scrollwatch')) {
e.addEventListener('input', function(e) {
dimensionChange(e, is_width, is_height);
});
e.classList.add('scrollwatch');
}
if (is_width) {
currentWidth = e.value * 1.0;
}
if (is_height) {
currentHeight = e.value * 1.0;
}
});
}
}
});

338
javascript/contextMenus.js
View File

@ -1,166 +1,172 @@
contextMenuInit = function(){
let eventListenerApplied=false;
let menuSpecs = new Map();
const uid = function(){
return Date.now().toString(36) + Math.random().toString(36).substring(2);
}
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')
if(oldMenu){
oldMenu.remove()
}
let baseStyle = window.getComputedStyle(uiCurrentTab)
const contextMenu = document.createElement('nav')
contextMenu.id = "context-menu"
contextMenu.style.background = baseStyle.background
contextMenu.style.color = baseStyle.color
contextMenu.style.fontFamily = baseStyle.fontFamily
contextMenu.style.top = posy+'px'
contextMenu.style.left = posx+'px'
const contextMenuList = document.createElement('ul')
contextMenuList.className = 'context-menu-items';
contextMenu.append(contextMenuList);
menuEntries.forEach(function(entry){
let contextMenuEntry = document.createElement('a')
contextMenuEntry.innerHTML = entry['name']
contextMenuEntry.addEventListener("click", function() {
entry['func']();
})
contextMenuList.append(contextMenuEntry);
})
gradioApp().appendChild(contextMenu)
let menuWidth = contextMenu.offsetWidth + 4;
let menuHeight = contextMenu.offsetHeight + 4;
let windowWidth = window.innerWidth;
let windowHeight = window.innerHeight;
if ( (windowWidth - posx) < menuWidth ) {
contextMenu.style.left = windowWidth - menuWidth + "px";
}
if ( (windowHeight - posy) < menuHeight ) {
contextMenu.style.top = windowHeight - menuHeight + "px";
}
}
function appendContextMenuOption(targetElementSelector,entryName,entryFunction){
var currentItems = menuSpecs.get(targetElementSelector)
if(!currentItems){
currentItems = []
menuSpecs.set(targetElementSelector,currentItems);
}
let newItem = {'id':targetElementSelector+'_'+uid(),
'name':entryName,
'func':entryFunction,
'isNew':true}
currentItems.push(newItem)
return newItem['id']
}
function removeContextMenuOption(uid){
menuSpecs.forEach(function(v) {
let index = -1
v.forEach(function(e,ei){if(e['id']==uid){index=ei}})
if(index>=0){
v.splice(index, 1);
}
})
}
function addContextMenuEventListener(){
if(eventListenerApplied){
return;
}
gradioApp().addEventListener("click", function(e) {
if(! e.isTrusted){
return
}
let oldMenu = gradioApp().querySelector('#context-menu')
if(oldMenu){
oldMenu.remove()
}
});
gradioApp().addEventListener("contextmenu", function(e) {
let oldMenu = gradioApp().querySelector('#context-menu')
if(oldMenu){
oldMenu.remove()
}
menuSpecs.forEach(function(v,k) {
if(e.composedPath()[0].matches(k)){
showContextMenu(e,e.composedPath()[0],v)
e.preventDefault()
}
})
});
eventListenerApplied=true
}
return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener]
}
initResponse = contextMenuInit();
appendContextMenuOption = initResponse[0];
removeContextMenuOption = initResponse[1];
addContextMenuEventListener = initResponse[2];
(function(){
//Start example Context Menu Items
let generateOnRepeat = function(genbuttonid,interruptbuttonid){
let genbutton = gradioApp().querySelector(genbuttonid);
let interruptbutton = gradioApp().querySelector(interruptbuttonid);
if(!interruptbutton.offsetParent){
genbutton.click();
}
clearInterval(window.generateOnRepeatInterval)
window.generateOnRepeatInterval = setInterval(function(){
if(!interruptbutton.offsetParent){
genbutton.click();
}
},
500)
}
appendContextMenuOption('#txt2img_generate','Generate forever',function(){
generateOnRepeat('#txt2img_generate','#txt2img_interrupt');
})
appendContextMenuOption('#img2img_generate','Generate forever',function(){
generateOnRepeat('#img2img_generate','#img2img_interrupt');
})
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(){
addContextMenuEventListener()
});
var contextMenuInit = function() {
let eventListenerApplied = false;
let menuSpecs = new Map();
const uid = function() {
return Date.now().toString(36) + Math.random().toString(36).substring(2);
};
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');
if (oldMenu) {
oldMenu.remove();
}
let baseStyle = window.getComputedStyle(uiCurrentTab);
const contextMenu = document.createElement('nav');
contextMenu.id = "context-menu";
contextMenu.style.background = baseStyle.background;
contextMenu.style.color = baseStyle.color;
contextMenu.style.fontFamily = baseStyle.fontFamily;
contextMenu.style.top = posy + 'px';
contextMenu.style.left = posx + 'px';
const contextMenuList = document.createElement('ul');
contextMenuList.className = 'context-menu-items';
contextMenu.append(contextMenuList);
menuEntries.forEach(function(entry) {
let contextMenuEntry = document.createElement('a');
contextMenuEntry.innerHTML = entry['name'];
contextMenuEntry.addEventListener("click", function() {
entry['func']();
});
contextMenuList.append(contextMenuEntry);
});
gradioApp().appendChild(contextMenu);
let menuWidth = contextMenu.offsetWidth + 4;
let menuHeight = contextMenu.offsetHeight + 4;
let windowWidth = window.innerWidth;
let windowHeight = window.innerHeight;
if ((windowWidth - posx) < menuWidth) {
contextMenu.style.left = windowWidth - menuWidth + "px";
}
if ((windowHeight - posy) < menuHeight) {
contextMenu.style.top = windowHeight - menuHeight + "px";
}
}
function appendContextMenuOption(targetElementSelector, entryName, entryFunction) {
var currentItems = menuSpecs.get(targetElementSelector);
if (!currentItems) {
currentItems = [];
menuSpecs.set(targetElementSelector, currentItems);
}
let newItem = {
id: targetElementSelector + '_' + uid(),
name: entryName,
func: entryFunction,
isNew: true
};
currentItems.push(newItem);
return newItem['id'];
}
function removeContextMenuOption(uid) {
menuSpecs.forEach(function(v) {
let index = -1;
v.forEach(function(e, ei) {
if (e['id'] == uid) {
index = ei;
}
});
if (index >= 0) {
v.splice(index, 1);
}
});
}
function addContextMenuEventListener() {
if (eventListenerApplied) {
return;
}
gradioApp().addEventListener("click", function(e) {
if (!e.isTrusted) {
return;
}
let oldMenu = gradioApp().querySelector('#context-menu');
if (oldMenu) {
oldMenu.remove();
}
});
gradioApp().addEventListener("contextmenu", function(e) {
let oldMenu = gradioApp().querySelector('#context-menu');
if (oldMenu) {
oldMenu.remove();
}
menuSpecs.forEach(function(v, k) {
if (e.composedPath()[0].matches(k)) {
showContextMenu(e, e.composedPath()[0], v);
e.preventDefault();
}
});
});
eventListenerApplied = true;
}
return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener];
};
var initResponse = contextMenuInit();
var appendContextMenuOption = initResponse[0];
var removeContextMenuOption = initResponse[1];
var addContextMenuEventListener = initResponse[2];
(function() {
//Start example Context Menu Items
let generateOnRepeat = function(genbuttonid, interruptbuttonid) {
let genbutton = gradioApp().querySelector(genbuttonid);
let interruptbutton = gradioApp().querySelector(interruptbuttonid);
if (!interruptbutton.offsetParent) {
genbutton.click();
}
clearInterval(window.generateOnRepeatInterval);
window.generateOnRepeatInterval = setInterval(function() {
if (!interruptbutton.offsetParent) {
genbutton.click();
}
},
500);
};
appendContextMenuOption('#txt2img_generate', 'Generate forever', function() {
generateOnRepeat('#txt2img_generate', '#txt2img_interrupt');
});
appendContextMenuOption('#img2img_generate', 'Generate forever', function() {
generateOnRepeat('#img2img_generate', '#img2img_interrupt');
});
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() {
addContextMenuEventListener();
});

52
javascript/dragdrop.js vendored
View File

@ -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 ) {
if ( ! isValidImageList( files ) ) {
function dropReplaceImage(imgWrap, files) {
if (!isValidImageList(files)) {
return;
}
@ -14,44 +14,44 @@ 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 ( files.length === 0 ) {
if (fileInput) {
if (files.length === 0) {
files = new DataTransfer();
files.items.add(tmpFile);
fileInput.files = files.files;
} else {
fileInput.files = files;
}
fileInput.dispatchEvent(new Event('change'));
fileInput.dispatchEvent(new Event('change'));
}
};
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());
}
}
window.document.addEventListener('dragover', e => {
const target = e.composedPath()[0];
const imgWrap = target.closest('[data-testid="image"]');
if ( !imgWrap && target.placeholder && target.placeholder.indexOf("Prompt") == -1) {
if (!imgWrap && target.placeholder && target.placeholder.indexOf("Prompt") == -1) {
return;
}
e.stopPropagation();
@ -65,33 +65,37 @@ window.document.addEventListener('drop', e => {
return;
}
const imgWrap = target.closest('[data-testid="image"]');
if ( !imgWrap ) {
if (!imgWrap) {
return;
}
e.stopPropagation();
e.preventDefault();
const files = e.dataTransfer.files;
dropReplaceImage( imgWrap, files );
dropReplaceImage(imgWrap, files);
});
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));
if ( ! visibleImageFields.length ) {
.filter(el => uiElementIsVisible(el))
.sort((a, b) => uiElementInSight(b) - uiElementInSight(a));
if (!visibleImageFields.length) {
return;
}
const firstFreeImageField = visibleImageFields
.filter(el => el.querySelector('input[type=file]'))?.[0];
dropReplaceImage(
firstFreeImageField ?
firstFreeImageField :
visibleImageFields[visibleImageFields.length - 1]
, files );
firstFreeImageField :
visibleImageFields[visibleImageFields.length - 1]
, files
);
});

240
javascript/edit-attention.js
View File

@ -1,120 +1,120 @@
function keyupEditAttention(event){
let target = event.originalTarget || event.composedPath()[0];
if (! target.matches("[id*='_toprow'] [id*='_prompt'] textarea")) return;
if (! (event.metaKey || event.ctrlKey)) return;
let isPlus = event.key == "ArrowUp"
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){
if (selectionStart !== selectionEnd) return false;
// Find opening parenthesis around current cursor
const before = text.substring(0, selectionStart);
let beforeParen = before.lastIndexOf(OPEN);
if (beforeParen == -1) return false;
let beforeParenClose = before.lastIndexOf(CLOSE);
while (beforeParenClose !== -1 && beforeParenClose > beforeParen) {
beforeParen = before.lastIndexOf(OPEN, beforeParen - 1);
beforeParenClose = before.lastIndexOf(CLOSE, beforeParenClose - 1);
}
// Find closing parenthesis around current cursor
const after = text.substring(selectionStart);
let afterParen = after.indexOf(CLOSE);
if (afterParen == -1) return false;
let afterParenOpen = after.indexOf(OPEN);
while (afterParenOpen !== -1 && afterParen > afterParenOpen) {
afterParen = after.indexOf(CLOSE, afterParen + 1);
afterParenOpen = after.indexOf(OPEN, afterParenOpen + 1);
}
if (beforeParen === -1 || afterParen === -1) return false;
// Set the selection to the text between the parenthesis
const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen);
const lastColon = parenContent.lastIndexOf(":");
selectionStart = beforeParen + 1;
selectionEnd = selectionStart + lastColon;
target.setSelectionRange(selectionStart, selectionEnd);
return true;
}
function selectCurrentWord(){
if (selectionStart !== selectionEnd) return false;
const delimiters = opts.keyedit_delimiters + " \r\n\t";
// seek backward until to find beggining
while (!delimiters.includes(text[selectionStart - 1]) && selectionStart > 0) {
selectionStart--;
}
// seek forward to find end
while (!delimiters.includes(text[selectionEnd]) && selectionEnd < text.length) {
selectionEnd++;
}
target.setSelectionRange(selectionStart, selectionEnd);
return true;
}
// If the user hasn't selected anything, let's select their current parenthesis block or word
if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')')) {
selectCurrentWord();
}
event.preventDefault();
var closeCharacter = ')'
var delta = opts.keyedit_precision_attention
if (selectionStart > 0 && text[selectionStart - 1] == '<'){
closeCharacter = '>'
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] == ' '){
selectionEnd -= 1;
}
if(selectionStart == selectionEnd){
return
}
text = text.slice(0, selectionStart) + "(" + text.slice(selectionStart, selectionEnd) + ":1.0)" + text.slice(selectionEnd);
selectionStart += 1;
selectionEnd += 1;
}
var end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + 1 + end));
if (isNaN(weight)) return;
weight += isPlus ? delta : -delta;
weight = parseFloat(weight.toPrecision(12));
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);
selectionStart--;
selectionEnd--;
} else {
text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1);
}
target.focus();
target.value = text;
target.selectionStart = selectionStart;
target.selectionEnd = selectionEnd;
updateInput(target)
}
addEventListener('keydown', (event) => {
keyupEditAttention(event);
});
function keyupEditAttention(event) {
let target = event.originalTarget || event.composedPath()[0];
if (!target.matches("*:is([id*='_toprow'] [id*='_prompt'], .prompt) textarea")) return;
if (!(event.metaKey || event.ctrlKey)) return;
let isPlus = event.key == "ArrowUp";
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) {
if (selectionStart !== selectionEnd) return false;
// Find opening parenthesis around current cursor
const before = text.substring(0, selectionStart);
let beforeParen = before.lastIndexOf(OPEN);
if (beforeParen == -1) return false;
let beforeParenClose = before.lastIndexOf(CLOSE);
while (beforeParenClose !== -1 && beforeParenClose > beforeParen) {
beforeParen = before.lastIndexOf(OPEN, beforeParen - 1);
beforeParenClose = before.lastIndexOf(CLOSE, beforeParenClose - 1);
}
// Find closing parenthesis around current cursor
const after = text.substring(selectionStart);
let afterParen = after.indexOf(CLOSE);
if (afterParen == -1) return false;
let afterParenOpen = after.indexOf(OPEN);
while (afterParenOpen !== -1 && afterParen > afterParenOpen) {
afterParen = after.indexOf(CLOSE, afterParen + 1);
afterParenOpen = after.indexOf(OPEN, afterParenOpen + 1);
}
if (beforeParen === -1 || afterParen === -1) return false;
// Set the selection to the text between the parenthesis
const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen);
const lastColon = parenContent.lastIndexOf(":");
selectionStart = beforeParen + 1;
selectionEnd = selectionStart + lastColon;
target.setSelectionRange(selectionStart, selectionEnd);
return true;
}
function selectCurrentWord() {
if (selectionStart !== selectionEnd) return false;
const delimiters = opts.keyedit_delimiters + " \r\n\t";
// seek backward until to find beggining
while (!delimiters.includes(text[selectionStart - 1]) && selectionStart > 0) {
selectionStart--;
}
// seek forward to find end
while (!delimiters.includes(text[selectionEnd]) && selectionEnd < text.length) {
selectionEnd++;
}
target.setSelectionRange(selectionStart, selectionEnd);
return true;
}
// If the user hasn't selected anything, let's select their current parenthesis block or word
if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')')) {
selectCurrentWord();
}
event.preventDefault();
var closeCharacter = ')';
var delta = opts.keyedit_precision_attention;
if (selectionStart > 0 && text[selectionStart - 1] == '<') {
closeCharacter = '>';
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] == ' ') {
selectionEnd -= 1;
}
if (selectionStart == selectionEnd) {
return;
}
text = text.slice(0, selectionStart) + "(" + text.slice(selectionStart, selectionEnd) + ":1.0)" + text.slice(selectionEnd);
selectionStart += 1;
selectionEnd += 1;
}
var end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + 1 + end));
if (isNaN(weight)) return;
weight += isPlus ? delta : -delta;
weight = parseFloat(weight.toPrecision(12));
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);
selectionStart--;
selectionEnd--;
} else {
text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1);
}
target.focus();
target.value = text;
target.selectionStart = selectionStart;
target.selectionEnd = selectionEnd;
updateInput(target);
}
addEventListener('keydown', (event) => {
keyupEditAttention(event);
});

145
javascript/extensions.js
View File

@ -1,71 +1,74 @@
function extensions_apply(_disabled_list, _update_list, disable_all){
var disable = []
var update = []
gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x){
if(x.name.startsWith("enable_") && ! x.checked)
disable.push(x.name.substring(7))
if(x.name.startsWith("update_") && x.checked)
update.push(x.name.substring(7))
})
restart_reload()
return [JSON.stringify(disable), JSON.stringify(update), disable_all]
}
function extensions_check(){
var disable = []
gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x){
if(x.name.startsWith("enable_") && ! x.checked)
disable.push(x.name.substring(7))
})
gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x){
x.innerHTML = "Loading..."
})
var id = randomId()
requestProgress(id, gradioApp().getElementById('extensions_installed_top'), null, function(){
})
return [id, JSON.stringify(disable)]
}
function install_extension_from_index(button, url){
button.disabled = "disabled"
button.value = "Installing..."
var textarea = gradioApp().querySelector('#extension_to_install textarea')
textarea.value = url
updateInput(textarea)
gradioApp().querySelector('#install_extension_button').click()
}
function config_state_confirm_restore(_, config_state_name, config_restore_type) {
if (config_state_name == "Current") {
return [false, config_state_name, config_restore_type];
}
let restored = "";
if (config_restore_type == "extensions") {
restored = "all saved extension versions";
} else if (config_restore_type == "webui") {
restored = "the webui version";
} else {
restored = "the webui version and all saved extension versions";
}
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){
x.innerHTML = "Loading..."
})
}
return [confirmed, config_state_name, config_restore_type];
}
function extensions_apply(_disabled_list, _update_list, disable_all) {
var disable = [];
var update = [];
gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
if (x.name.startsWith("enable_") && !x.checked) {
disable.push(x.name.substring(7));
}
if (x.name.startsWith("update_") && x.checked) {
update.push(x.name.substring(7));
}
});
restart_reload();
return [JSON.stringify(disable), JSON.stringify(update), disable_all];
}
function extensions_check() {
var disable = [];
gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
if (x.name.startsWith("enable_") && !x.checked) {
disable.push(x.name.substring(7));
}
});
gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x) {
x.innerHTML = "Loading...";
});
var id = randomId();
requestProgress(id, gradioApp().getElementById('extensions_installed_top'), null, function() {
});
return [id, JSON.stringify(disable)];
}
function install_extension_from_index(button, url) {
button.disabled = "disabled";
button.value = "Installing...";
var textarea = gradioApp().querySelector('#extension_to_install textarea');
textarea.value = url;
updateInput(textarea);
gradioApp().querySelector('#install_extension_button').click();
}
function config_state_confirm_restore(_, config_state_name, config_restore_type) {
if (config_state_name == "Current") {
return [false, config_state_name, config_restore_type];
}
let restored = "";
if (config_restore_type == "extensions") {
restored = "all saved extension versions";
} else if (config_restore_type == "webui") {
restored = "the webui version";
} else {
restored = "the webui version and all saved extension versions";
}
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) {
x.innerHTML = "Loading...";
});
}
return [confirmed, config_state_name, config_restore_type];
}

411
javascript/extraNetworks.js
View File

@ -1,196 +1,215 @@
function setupExtraNetworksForTab(tabname){
gradioApp().querySelector('#'+tabname+'_extra_tabs').classList.add('extra-networks')
var tabs = gradioApp().querySelector('#'+tabname+'_extra_tabs > div')
var search = gradioApp().querySelector('#'+tabname+'_extra_search textarea')
var refresh = gradioApp().getElementById(tabname+'_extra_refresh')
search.classList.add('search')
tabs.appendChild(search)
tabs.appendChild(refresh)
var applyFilter = function(){
var searchTerm = search.value.toLowerCase()
gradioApp().querySelectorAll('#'+tabname+'_extra_tabs div.card').forEach(function(elem){
var searchOnly = elem.querySelector('.search_only')
var text = elem.querySelector('.name').textContent.toLowerCase() + " " + elem.querySelector('.search_term').textContent.toLowerCase()
var visible = text.indexOf(searchTerm) != -1
if(searchOnly && searchTerm.length < 4){
visible = false
}
elem.style.display = visible ? "" : "none"
})
}
search.addEventListener("input", applyFilter);
applyFilter();
extraNetworksApplyFilter[tabname] = applyFilter;
}
function applyExtraNetworkFilter(tabname){
setTimeout(extraNetworksApplyFilter[tabname], 1);
}
var extraNetworksApplyFilter = {}
var activePromptTextarea = {};
function setupExtraNetworks(){
setupExtraNetworksForTab('txt2img')
setupExtraNetworksForTab('img2img')
function registerPrompt(tabname, id){
var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
if (! activePromptTextarea[tabname]){
activePromptTextarea[tabname] = textarea
}
textarea.addEventListener("focus", function(){
activePromptTextarea[tabname] = textarea;
});
}
registerPrompt('txt2img', 'txt2img_prompt')
registerPrompt('txt2img', 'txt2img_neg_prompt')
registerPrompt('img2img', 'img2img_prompt')
registerPrompt('img2img', 'img2img_neg_prompt')
}
onUiLoaded(setupExtraNetworks)
var re_extranet = /<([^:]+:[^:]+):[\d\.]+>/;
var re_extranet_g = /\s+<([^:]+:[^:]+):[\d\.]+>/g;
function tryToRemoveExtraNetworkFromPrompt(textarea, text){
var m = text.match(re_extranet)
if(! m) return false
var partToSearch = m[1]
var replaced = false
var newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found){
m = found.match(re_extranet);
if(m[1] == partToSearch){
replaced = true;
return ""
}
return found;
})
if(replaced){
textarea.value = newTextareaText
return true;
}
return false
}
function cardClicked(tabname, textToAdd, allowNegativePrompt){
var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea")
if(! tryToRemoveExtraNetworkFromPrompt(textarea, textToAdd)){
textarea.value = textarea.value + opts.extra_networks_add_text_separator + textToAdd
}
updateInput(textarea)
}
function saveCardPreview(event, tabname, filename){
var textarea = gradioApp().querySelector("#" + tabname + '_preview_filename > label > textarea')
var button = gradioApp().getElementById(tabname + '_save_preview')
textarea.value = filename
updateInput(textarea)
button.click()
event.stopPropagation()
event.preventDefault()
}
function extraNetworksSearchButton(tabs_id, event){
var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > div > textarea')
var button = event.target
var text = button.classList.contains("search-all") ? "" : button.textContent.trim()
searchTextarea.value = text
updateInput(searchTextarea)
}
var globalPopup = null;
var globalPopupInner = null;
function popup(contents){
if(! globalPopup){
globalPopup = document.createElement('div')
globalPopup.onclick = function(){ globalPopup.style.display = "none"; };
globalPopup.classList.add('global-popup');
var close = document.createElement('div')
close.classList.add('global-popup-close');
close.onclick = function(){ globalPopup.style.display = "none"; };
close.title = "Close";
globalPopup.appendChild(close)
globalPopupInner = document.createElement('div')
globalPopupInner.onclick = function(event){ event.stopPropagation(); return false; };
globalPopupInner.classList.add('global-popup-inner');
globalPopup.appendChild(globalPopupInner)
gradioApp().appendChild(globalPopup);
}
globalPopupInner.innerHTML = '';
globalPopupInner.appendChild(contents);
globalPopup.style.display = "flex";
}
function extraNetworksShowMetadata(text){
var elem = document.createElement('pre')
elem.classList.add('popup-metadata');
elem.textContent = text;
popup(elem);
}
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('&')
xhr.open("GET", url + "?" + args, true);
xhr.onreadystatechange = function () {
if (xhr.readyState === 4) {
if (xhr.status === 200) {
try {
var js = JSON.parse(xhr.responseText);
handler(js)
} catch (error) {
console.error(error);
errorHandler()
}
} else{
errorHandler()
}
}
};
var js = JSON.stringify(data);
xhr.send(js);
}
function extraNetworksRequestMetadata(event, extraPage, cardName){
var showError = function(){ extraNetworksShowMetadata("there was an error getting metadata"); }
requestGet("./sd_extra_networks/metadata", {"page": extraPage, "item": cardName}, function(data){
if(data && data.metadata){
extraNetworksShowMetadata(data.metadata)
} else{
showError()
}
}, showError)
event.stopPropagation()
}
function setupExtraNetworksForTab(tabname) {
gradioApp().querySelector('#' + tabname + '_extra_tabs').classList.add('extra-networks');
var tabs = gradioApp().querySelector('#' + tabname + '_extra_tabs > div');
var search = gradioApp().querySelector('#' + tabname + '_extra_search textarea');
var refresh = gradioApp().getElementById(tabname + '_extra_refresh');
search.classList.add('search');
tabs.appendChild(search);
tabs.appendChild(refresh);
var applyFilter = function() {
var searchTerm = search.value.toLowerCase();
gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card').forEach(function(elem) {
var searchOnly = elem.querySelector('.search_only');
var text = elem.querySelector('.name').textContent.toLowerCase() + " " + elem.querySelector('.search_term').textContent.toLowerCase();
var visible = text.indexOf(searchTerm) != -1;
if (searchOnly && searchTerm.length < 4) {
visible = false;
}
elem.style.display = visible ? "" : "none";
});
};
search.addEventListener("input", applyFilter);
applyFilter();
extraNetworksApplyFilter[tabname] = applyFilter;
}
function applyExtraNetworkFilter(tabname) {
setTimeout(extraNetworksApplyFilter[tabname], 1);
}
var extraNetworksApplyFilter = {};
var activePromptTextarea = {};
function setupExtraNetworks() {
setupExtraNetworksForTab('txt2img');
setupExtraNetworksForTab('img2img');
function registerPrompt(tabname, id) {
var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
if (!activePromptTextarea[tabname]) {
activePromptTextarea[tabname] = textarea;
}
textarea.addEventListener("focus", function() {
activePromptTextarea[tabname] = textarea;
});
}
registerPrompt('txt2img', 'txt2img_prompt');
registerPrompt('txt2img', 'txt2img_neg_prompt');
registerPrompt('img2img', 'img2img_prompt');
registerPrompt('img2img', 'img2img_neg_prompt');
}
onUiLoaded(setupExtraNetworks);
var re_extranet = /<([^:]+:[^:]+):[\d.]+>/;
var re_extranet_g = /\s+<([^:]+:[^:]+):[\d.]+>/g;
function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
var m = text.match(re_extranet);
var replaced = false;
var newTextareaText;
if (m) {
var partToSearch = m[1];
newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found) {
m = found.match(re_extranet);
if (m[1] == partToSearch) {
replaced = true;
return "";
}
return found;
});
} else {
newTextareaText = textarea.value.replaceAll(new RegExp(text, "g"), function(found) {
if (found == text) {
replaced = true;
return "";
}
return found;
});
}
if (replaced) {
textarea.value = newTextareaText;
return true;
}
return false;
}
function cardClicked(tabname, textToAdd, allowNegativePrompt) {
var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea");
if (!tryToRemoveExtraNetworkFromPrompt(textarea, textToAdd)) {
textarea.value = textarea.value + opts.extra_networks_add_text_separator + textToAdd;
}
updateInput(textarea);
}
function saveCardPreview(event, tabname, filename) {
var textarea = gradioApp().querySelector("#" + tabname + '_preview_filename > label > textarea');
var button = gradioApp().getElementById(tabname + '_save_preview');
textarea.value = filename;
updateInput(textarea);
button.click();
event.stopPropagation();
event.preventDefault();
}
function extraNetworksSearchButton(tabs_id, event) {
var searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > div > textarea');
var button = event.target;
var text = button.classList.contains("search-all") ? "" : button.textContent.trim();
searchTextarea.value = text;
updateInput(searchTextarea);
}
var globalPopup = null;
var globalPopupInner = null;
function popup(contents) {
if (!globalPopup) {
globalPopup = document.createElement('div');
globalPopup.onclick = function() {
globalPopup.style.display = "none";
};
globalPopup.classList.add('global-popup');
var close = document.createElement('div');
close.classList.add('global-popup-close');
close.onclick = function() {
globalPopup.style.display = "none";
};
close.title = "Close";
globalPopup.appendChild(close);
globalPopupInner = document.createElement('div');
globalPopupInner.onclick = function(event) {
event.stopPropagation(); return false;
};
globalPopupInner.classList.add('global-popup-inner');
globalPopup.appendChild(globalPopupInner);
gradioApp().appendChild(globalPopup);
}
globalPopupInner.innerHTML = '';
globalPopupInner.appendChild(contents);
globalPopup.style.display = "flex";
}
function extraNetworksShowMetadata(text) {
var elem = document.createElement('pre');
elem.classList.add('popup-metadata');
elem.textContent = text;
popup(elem);
}
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('&');
xhr.open("GET", url + "?" + args, true);
xhr.onreadystatechange = function() {
if (xhr.readyState === 4) {
if (xhr.status === 200) {
try {
var js = JSON.parse(xhr.responseText);
handler(js);
} catch (error) {
console.error(error);
errorHandler();
}
} else {
errorHandler();
}
}
};
var js = JSON.stringify(data);
xhr.send(js);
}
function extraNetworksRequestMetadata(event, extraPage, cardName) {
var showError = function() {
extraNetworksShowMetadata("there was an error getting metadata");
};
requestGet("./sd_extra_networks/metadata", {page: extraPage, item: cardName}, function(data) {
if (data && data.metadata) {
extraNetworksShowMetadata(data.metadata);
} else {
showError();
}
}, showError);
event.stopPropagation();
}

48
javascript/generationParams.js
View File

@ -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(){
if (!txt2img_gallery) {
txt2img_gallery = attachGalleryListeners("txt2img")
}
if (!img2img_gallery) {
img2img_gallery = attachGalleryListeners("img2img")
}
if (!modal) {
modal = gradioApp().getElementById('lightboxModal')
modalObserver.observe(modal, { attributes : true, attributeFilter : ['style'] });
}
onUiUpdate(function() {
if (!txt2img_gallery) {
txt2img_gallery = attachGalleryListeners("txt2img");
}
if (!img2img_gallery) {
img2img_gallery = attachGalleryListeners("img2img");
}
if (!modal) {
modal = gradioApp().getElementById('lightboxModal');
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
if (mutationRecord.target.style.display === 'none' && (selectedTab === 'txt2img' || selectedTab === 'img2img'))
gradioApp().getElementById(selectedTab+"_generation_info_button")?.click()
});
mutations.forEach(function(mutationRecord) {
let selectedTab = gradioApp().querySelector('#tabs div button.selected')?.innerText;
if (mutationRecord.target.style.display === 'none' && (selectedTab === 'txt2img' || selectedTab === 'img2img')) {
gradioApp().getElementById(selectedTab + "_generation_info_button")?.click();
}
});
});
function attachGalleryListeners(tab_name) {
var gallery = gradioApp().querySelector('#'+tab_name+'_gallery')
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
gradioApp().getElementById(tab_name+"_generation_info_button").click()
});
return gallery;
var gallery = gradioApp().querySelector('#' + tab_name + '_gallery');
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
gradioApp().getElementById(tab_name + "_generation_info_button").click();
}
});
return gallery;
}

100
javascript/hints.js
View File

@ -1,16 +1,17 @@
// 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",
"Euler a": "Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps higher than 30-40 does not help",
"DDIM": "Denoising Diffusion Implicit Models - best at inpainting",
"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",
"GFPGAN": "Restore low quality faces using GFPGAN neural network",
"Euler a": "Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps higher than 30-40 does not help",
"DDIM": "Denoising Diffusion Implicit Models - best at inpainting",
"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",
"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)",
"\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",
@ -40,7 +41,7 @@ titles = {
"Inpaint at full resolution": "Upscale masked region to target resolution, do inpainting, downscale back and paste into original image",
"Denoising strength": "Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.",
"Skip": "Stop processing current image and continue processing.",
"Interrupt": "Stop processing images and return any results accumulated so far.",
"Save": "Write image to a directory (default - log/images) and generation parameters into csv file.",
@ -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.",
"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.",
"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 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.",
@ -96,7 +97,7 @@ titles = {
"Add difference": "Result = A + (B - C) * M",
"No interpolation": "Result = A",
"Initialization text": "If the number of tokens is more than the number of vectors, some may be skipped.\nLeave the textbox empty to start with zeroed out vectors",
"Initialization text": "If the number of tokens is more than the number of vectors, some may be skipped.\nLeave the textbox empty to start with zeroed out vectors",
"Learning rate": "How fast should training go. Low values will take longer to train, high values may fail to converge (not generate accurate results) and/or may break the embedding (This has happened if you see Loss: nan in the training info textbox. If this happens, you need to manually restore your embedding from an older not-broken backup).\n\nYou can set a single numeric value, or multiple learning rates using the syntax:\n\n rate_1:max_steps_1, rate_2:max_steps_2, ...\n\nEG: 0.005:100, 1e-3:1000, 1e-5\n\nWill train with rate of 0.005 for first 100 steps, then 1e-3 until 1000 steps, then 1e-5 for all remaining steps.",
"Clip skip": "Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.",
@ -113,38 +114,55 @@ titles = {
"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.",
"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 updateTooltipForSpan(span) {
if (span.title) return; // already has a title
let tooltip = localization[titles[span.textContent]] || titles[span.textContent];
if (!tooltip) {
tooltip = localization[titles[span.value]] || titles[span.value];
}
if (!tooltip) {
for (const c of span.classList) {
if (c in titles) {
tooltip = localization[titles[c]] || titles[c];
break;
}
}
}
if (tooltip) {
span.title = tooltip;
}
}
function updateTooltipForSelect(select) {
if (select.onchange != null) return;
onUiUpdate(function(){
gradioApp().querySelectorAll('span, button, select, p').forEach(function(span){
if (span.title) return; // already has a title
select.onchange = function() {
select.title = localization[titles[select.value]] || titles[select.value] || "";
};
}
let tooltip = localization[titles[span.textContent]] || titles[span.textContent];
var observedTooltipElements = {SPAN: 1, BUTTON: 1, SELECT: 1, P: 1};
if(!tooltip){
tooltip = localization[titles[span.value]] || titles[span.value];
}
onUiUpdate(function(m) {
m.forEach(function(record) {
record.addedNodes.forEach(function(node) {
if (observedTooltipElements[node.tagName]) {
updateTooltipForSpan(node);
}
if (node.tagName == "SELECT") {
updateTooltipForSelect(node);
}
if(!tooltip){
for (const c of span.classList) {
if (c in titles) {
tooltip = localization[titles[c]] || titles[c];
break;
}
}
}
if(tooltip){
span.title = tooltip;
}
})
gradioApp().querySelectorAll('select').forEach(function(select){
if (select.onchange != null) return;
select.onchange = function(){
select.title = localization[titles[select.value]] || titles[select.value] || "";
}
})
})
if (node.querySelectorAll) {
node.querySelectorAll('span, button, select, p').forEach(updateTooltipForSpan);
node.querySelectorAll('select').forEach(updateTooltipForSelect);
}
});
});
});

36
javascript/hires_fix.js
View File

@ -1,18 +1,18 @@
function onCalcResolutionHires(enable, width, height, hr_scale, hr_resize_x, hr_resize_y){
function setInactive(elem, inactive){
elem.classList.toggle('inactive', !!inactive)
}
var hrUpscaleBy = gradioApp().getElementById('txt2img_hr_scale')
var hrResizeX = gradioApp().getElementById('txt2img_hr_resize_x')
var hrResizeY = gradioApp().getElementById('txt2img_hr_resize_y')
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(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)
return [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) {
elem.classList.toggle('inactive', !!inactive);
}
var hrUpscaleBy = gradioApp().getElementById('txt2img_hr_scale');
var hrResizeX = gradioApp().getElementById('txt2img_hr_resize_x');
var hrResizeY = gradioApp().getElementById('txt2img_hr_resize_y');
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(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);
return [enable, width, height, hr_scale, hr_resize_x, hr_resize_y];
}

19
javascript/imageMaskFix.js
View File

@ -4,17 +4,16 @@
*/
function imageMaskResize() {
const canvases = gradioApp().querySelectorAll('#img2maskimg .touch-none canvas');
if ( ! canvases.length ) {
canvases_fixed = false; // TODO: this is unused..?
window.removeEventListener( 'resize', imageMaskResize );
return;
if (!canvases.length) {
window.removeEventListener('resize', imageMaskResize);
return;
}
const wrapper = canvases[0].closest('.touch-none');
const previewImage = wrapper.previousElementSibling;
if ( ! previewImage.complete ) {
previewImage.addEventListener( 'load', imageMaskResize);
if (!previewImage.complete) {
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 wH = Math.min(h, portrait ? h/nh*nh : w/nw*nh);
const wW = Math.min(w, portrait ? h / nh * nw : w / nw * nw);
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%';
@ -41,4 +40,4 @@ function imageMaskResize() {
}
onUiUpdate(imageMaskResize);
window.addEventListener( 'resize', imageMaskResize);
window.addEventListener('resize', imageMaskResize);

4
javascript/imageParams.js
View File

@ -1,4 +1,4 @@
window.onload = (function(){
window.onload = (function() {
window.addEventListener('drop', e => {
const target = e.composedPath()[0];
if (target.placeholder.indexOf("Prompt") == -1) return;
@ -10,7 +10,7 @@ window.onload = (function(){
const imgParent = gradioApp().getElementById(prompt_target);
const files = e.dataTransfer.files;
const fileInput = imgParent.querySelector('input[type="file"]');
if ( fileInput ) {
if (fileInput) {
fileInput.files = files;
fileInput.dispatchEvent(new Event('change'));
}

226
javascript/imageviewer.js
View File

@ -5,24 +5,24 @@ function closeModal() {
function showModal(event) {
const source = event.target || event.srcElement;
const modalImage = gradioApp().getElementById("modalImage")
const lb = gradioApp().getElementById("lightboxModal")
modalImage.src = source.src
const modalImage = gradioApp().getElementById("modalImage");
const lb = gradioApp().getElementById("lightboxModal");
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 tabImg2Img = gradioApp().getElementById("tab_img2img")
const tabTxt2Img = gradioApp().getElementById("tab_txt2img");
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})`);
}
}
}
@ -49,108 +50,109 @@ 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)]
nextButton.click()
var nextButton = galleryButtons[negmod((result + offset), galleryButtons.length)];
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()
}, 10)
modal.focus();
}, 10);
}
}
}
function saveImage(){
const tabTxt2Img = gradioApp().getElementById("tab_txt2img")
const tabImg2Img = gradioApp().getElementById("tab_img2img")
const saveTxt2Img = "save_txt2img"
const saveImg2Img = "save_img2img"
function saveImage() {
const tabTxt2Img = gradioApp().getElementById("tab_txt2img");
const tabImg2Img = gradioApp().getElementById("tab_img2img");
const saveTxt2Img = "save_txt2img";
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()
event.stopPropagation()
saveImage();
event.stopPropagation();
}
function modalNextImage(event) {
modalImageSwitch(1)
event.stopPropagation()
modalImageSwitch(1);
event.stopPropagation();
}
function modalPrevImage(event) {
modalImageSwitch(-1)
event.stopPropagation()
modalImageSwitch(-1);
event.stopPropagation();
}
function modalKeyHandler(event) {
switch (event.key) {
case "s":
saveImage()
break;
case "ArrowLeft":
modalPrevImage(event)
break;
case "ArrowRight":
modalNextImage(event)
break;
case "Escape":
closeModal();
break;
case "s":
saveImage();
break;
case "ArrowLeft":
modalPrevImage(event);
break;
case "ArrowRight":
modalNextImage(event);
break;
case "Escape":
closeModal();
break;
}
}
function setupImageForLightbox(e) {
if (e.dataset.modded)
return;
if (e.dataset.modded) {
return;
}
e.dataset.modded = true;
e.style.cursor='pointer'
e.style.userSelect='none'
e.dataset.modded = true;
e.style.cursor = 'pointer';
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'
// 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';
e.addEventListener(event, function (evt) {
if(!opts.js_modal_lightbox || evt.button != 0) return;
e.addEventListener(event, function(evt) {
if (!opts.js_modal_lightbox || evt.button != 0) return;
modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed)
evt.preventDefault()
showModal(evt)
}, true);
modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed);
evt.preventDefault();
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'))
event.stopPropagation()
modalZoomSet(modalImage, !modalImage.classList.contains('modalImageFullscreen'));
event.stopPropagation();
}
function modalTileImageToggle(event) {
@ -159,99 +161,93 @@ 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()
}
function galleryImageHandler(e) {
//if (e && e.parentElement.tagName == 'BUTTON') {
e.onclick = showGalleryImage;
//}
event.stopPropagation();
}
onUiUpdate(function() {
var fullImg_preview = gradioApp().querySelectorAll('.gradio-gallery > div > img')
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.addEventListener('keydown', modalKeyHandler, true)
modal.tabIndex = 0;
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 = '&#10529;'
modalZoom.addEventListener('click', modalZoomToggle, true)
modalZoom.innerHTML = '&#10529;';
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 = '&#8862;'
modalTileImage.addEventListener('click', modalTileImageToggle, true)
modalTileImage.innerHTML = '&#8862;';
modalTileImage.addEventListener('click', modalTileImageToggle, true);
modalTileImage.title = "Preview tiling";
modalControls.appendChild(modalTileImage)
modalControls.appendChild(modalTileImage);
const modalSave = document.createElement("span")
modalSave.className = "modalSave cursor"
modalSave.id = "modal_save"
modalSave.innerHTML = "&#x1F5AB;"
modalSave.addEventListener("click", modalSaveImage, true)
modalSave.title = "Save Image(s)"
modalControls.appendChild(modalSave)
const modalSave = document.createElement("span");
modalSave.className = "modalSave cursor";
modalSave.id = "modal_save";
modalSave.innerHTML = "&#x1F5AB;";
modalSave.addEventListener("click", modalSaveImage, true);
modalSave.title = "Save Image(s)";
modalControls.appendChild(modalSave);
const modalClose = document.createElement('span')
const modalClose = document.createElement('span');
modalClose.className = 'modalClose cursor';
modalClose.innerHTML = '&times;'
modalClose.innerHTML = '&times;';
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.addEventListener('keydown', modalKeyHandler, true)
modal.appendChild(modalImage)
modalImage.tabIndex = 0;
modalImage.addEventListener('keydown', modalKeyHandler, true);
modal.appendChild(modalImage);
const modalPrev = document.createElement('a')
const modalPrev = document.createElement('a');
modalPrev.className = 'modalPrev';
modalPrev.innerHTML = '&#10094;'
modalPrev.tabIndex = 0
modalPrev.innerHTML = '&#10094;';
modalPrev.tabIndex = 0;
modalPrev.addEventListener('click', modalPrevImage, true);
modalPrev.addEventListener('keydown', modalKeyHandler, true)
modal.appendChild(modalPrev)
modalPrev.addEventListener('keydown', modalKeyHandler, true);
modal.appendChild(modalPrev);
const modalNext = document.createElement('a')
const modalNext = document.createElement('a');
modalNext.className = 'modalNext';
modalNext.innerHTML = '&#10095;'
modalNext.tabIndex = 0
modalNext.innerHTML = '&#10095;';
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);
} catch (e) {
gradioApp().body.appendChild(modal);
}
gradioApp().appendChild(modal);
} catch (e) {
gradioApp().body.appendChild(modal);
}
document.body.appendChild(modal);

4
javascript/imageviewerGamepad.js
View File

@ -1,7 +1,7 @@
window.addEventListener('gamepadconnected', (e) => {
const index = e.gamepad.index;
let isWaiting = false;
setInterval(async () => {
setInterval(async() => {
if (!opts.js_modal_lightbox_gamepad || isWaiting) return;
const gamepad = navigator.getGamepads()[index];
const xValue = gamepad.axes[0];
@ -14,7 +14,7 @@ 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;
}

353
javascript/localization.js
View File

@ -1,177 +1,176 @@
// localization = {} -- the dict with translations is created by the backend
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',
train_embedding: 'OPTION',
train_hypernetwork: 'OPTION',
txt2img_styles: 'OPTION',
img2img_styles: 'OPTION',
setting_random_artist_categories: 'SPAN',
setting_face_restoration_model: 'SPAN',
setting_realesrgan_enabled_models: 'SPAN',
extras_upscaler_1: 'SPAN',
extras_upscaler_2: 'SPAN',
}
re_num = /^[\.\d]+$/
re_emoji = /[\p{Extended_Pictographic}\u{1F3FB}-\u{1F3FF}\u{1F9B0}-\u{1F9B3}]/u
original_lines = {}
translated_lines = {}
function hasLocalization() {
return window.localization && Object.keys(window.localization).length > 0;
}
function textNodesUnder(el){
var n, a=[], walk=document.createTreeWalker(el,NodeFilter.SHOW_TEXT,null,false);
while(n=walk.nextNode()) a.push(n);
return a;
}
function canBeTranslated(node, text){
if(! text) return false;
if(! node.parentElement) return false;
var parentType = node.parentElement.nodeName
if(parentType=='SCRIPT' || parentType=='STYLE' || parentType=='TEXTAREA') return false;
if (parentType=='OPTION' || parentType=='SPAN'){
var pnode = node
for(var level=0; level<4; level++){
pnode = pnode.parentElement
if(! pnode) break;
if(ignore_ids_for_localization[pnode.id] == parentType) return false;
}
}
if(re_num.test(text)) return false;
if(re_emoji.test(text)) return false;
return true
}
function getTranslation(text){
if(! text) return undefined
if(translated_lines[text] === undefined){
original_lines[text] = 1
}
tl = localization[text]
if(tl !== undefined){
translated_lines[tl] = 1
}
return tl
}
function processTextNode(node){
var text = node.textContent.trim()
if(! canBeTranslated(node, text)) return
tl = getTranslation(text)
if(tl !== undefined){
node.textContent = tl
}
}
function processNode(node){
if(node.nodeType == 3){
processTextNode(node)
return
}
if(node.title){
tl = getTranslation(node.title)
if(tl !== undefined){
node.title = tl
}
}
if(node.placeholder){
tl = getTranslation(node.placeholder)
if(tl !== undefined){
node.placeholder = tl
}
}
textNodesUnder(node).forEach(function(node){
processTextNode(node)
})
}
function dumpTranslations(){
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 = {}
if (localization.rtl) {
dumped.rtl = true;
}
for (const text in original_lines) {
if(dumped[text] !== undefined) continue;
dumped[text] = localization[text] || text;
}
return dumped;
}
function download_localization() {
var text = JSON.stringify(dumpTranslations(), null, 4)
var element = document.createElement('a');
element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(text));
element.setAttribute('download', "localization.json");
element.style.display = 'none';
document.body.appendChild(element);
element.click();
document.body.removeChild(element);
}
document.addEventListener("DOMContentLoaded", function () {
if (!hasLocalization()) {
return;
}
onUiUpdate(function (m) {
m.forEach(function (mutation) {
mutation.addedNodes.forEach(function (node) {
processNode(node)
})
});
})
processNode(gradioApp())
if (localization.rtl) { // if the language is from right to left,
(new MutationObserver((mutations, observer) => { // wait for the style to load
mutations.forEach(mutation => {
mutation.addedNodes.forEach(node => {
if (node.tagName === 'STYLE') {
observer.disconnect();
for (const x of node.sheet.rules) { // find all rtl media rules
if (Array.from(x.media || []).includes('rtl')) {
x.media.appendMedium('all'); // enable them
}
}
}
})
});
})).observe(gradioApp(), { childList: true });
}
})
// localization = {} -- the dict with translations is created by the backend
var ignore_ids_for_localization = {
setting_sd_hypernetwork: 'OPTION',
setting_sd_model_checkpoint: 'OPTION',
modelmerger_primary_model_name: 'OPTION',
modelmerger_secondary_model_name: 'OPTION',
modelmerger_tertiary_model_name: 'OPTION',
train_embedding: 'OPTION',
train_hypernetwork: 'OPTION',
txt2img_styles: 'OPTION',
img2img_styles: 'OPTION',
setting_random_artist_categories: 'SPAN',
setting_face_restoration_model: 'SPAN',
setting_realesrgan_enabled_models: 'SPAN',
extras_upscaler_1: 'SPAN',
extras_upscaler_2: 'SPAN',
};
var re_num = /^[.\d]+$/;
var re_emoji = /[\p{Extended_Pictographic}\u{1F3FB}-\u{1F3FF}\u{1F9B0}-\u{1F9B3}]/u;
var original_lines = {};
var translated_lines = {};
function hasLocalization() {
return window.localization && Object.keys(window.localization).length > 0;
}
function textNodesUnder(el) {
var n, a = [], walk = document.createTreeWalker(el, NodeFilter.SHOW_TEXT, null, false);
while ((n = walk.nextNode())) a.push(n);
return a;
}
function canBeTranslated(node, text) {
if (!text) return false;
if (!node.parentElement) return false;
var parentType = node.parentElement.nodeName;
if (parentType == 'SCRIPT' || parentType == 'STYLE' || parentType == 'TEXTAREA') return false;
if (parentType == 'OPTION' || parentType == 'SPAN') {
var pnode = node;
for (var level = 0; level < 4; level++) {
pnode = pnode.parentElement;
if (!pnode) break;
if (ignore_ids_for_localization[pnode.id] == parentType) return false;
}
}
if (re_num.test(text)) return false;
if (re_emoji.test(text)) return false;
return true;
}
function getTranslation(text) {
if (!text) return undefined;
if (translated_lines[text] === undefined) {
original_lines[text] = 1;
}
var tl = localization[text];
if (tl !== undefined) {
translated_lines[tl] = 1;
}
return tl;
}
function processTextNode(node) {
var text = node.textContent.trim();
if (!canBeTranslated(node, text)) return;
var tl = getTranslation(text);
if (tl !== undefined) {
node.textContent = tl;
}
}
function processNode(node) {
if (node.nodeType == 3) {
processTextNode(node);
return;
}
if (node.title) {
let tl = getTranslation(node.title);
if (tl !== undefined) {
node.title = tl;
}
}
if (node.placeholder) {
let tl = getTranslation(node.placeholder);
if (tl !== undefined) {
node.placeholder = tl;
}
}
textNodesUnder(node).forEach(function(node) {
processTextNode(node);
});
}
function dumpTranslations() {
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 = {};
if (localization.rtl) {
dumped.rtl = true;
}
for (const text in original_lines) {
if (dumped[text] !== undefined) continue;
dumped[text] = localization[text] || text;
}
return dumped;
}
function download_localization() {
var text = JSON.stringify(dumpTranslations(), null, 4);
var element = document.createElement('a');
element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(text));
element.setAttribute('download', "localization.json");
element.style.display = 'none';
document.body.appendChild(element);
element.click();
document.body.removeChild(element);
}
document.addEventListener("DOMContentLoaded", function() {
if (!hasLocalization()) {
return;
}
onUiUpdate(function(m) {
m.forEach(function(mutation) {
mutation.addedNodes.forEach(function(node) {
processNode(node);
});
});
});
processNode(gradioApp());
if (localization.rtl) { // if the language is from right to left,
(new MutationObserver((mutations, observer) => { // wait for the style to load
mutations.forEach(mutation => {
mutation.addedNodes.forEach(node => {
if (node.tagName === 'STYLE') {
observer.disconnect();
for (const x of node.sheet.rules) { // find all rtl media rules
if (Array.from(x.media || []).includes('rtl')) {
x.media.appendMedium('all'); // enable them
}
}
}
});
});
})).observe(gradioApp(), {childList: true});
}
});

12
javascript/notification.js
View File

@ -4,14 +4,14 @@ let lastHeadImg = null;
let notificationButton = null;
onUiUpdate(function(){
if(notificationButton == null){
notificationButton = gradioApp().getElementById('request_notifications')
onUiUpdate(function() {
if (notificationButton == null) {
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();
};

178
javascript/progressbar.js
View File

@ -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{
errorHandler()
} else {
errorHandler();
}
}
};
@ -31,147 +31,147 @@ function request(url, data, handler, errorHandler){
xhr.send(js);
}
function pad2(x){
return x<10 ? '0'+x : x
function pad2(x) {
return x < 10 ? '0' + x : x;
}
function formatTime(secs){
if(secs > 3600){
return pad2(Math.floor(secs/60/60)) + ":" + pad2(Math.floor(secs/60)%60) + ":" + pad2(Math.floor(secs)%60)
} else if(secs > 60){
return pad2(Math.floor(secs/60)) + ":" + pad2(Math.floor(secs)%60)
} else{
return Math.floor(secs) + "s"
function formatTime(secs) {
if (secs > 3600) {
return pad2(Math.floor(secs / 60 / 60)) + ":" + pad2(Math.floor(secs / 60) % 60) + ":" + pad2(Math.floor(secs) % 60);
} else if (secs > 60) {
return pad2(Math.floor(secs / 60)) + ":" + pad2(Math.floor(secs) % 60);
} else {
return Math.floor(secs) + "s";
}
}
function setTitle(progress){
var title = 'Stable Diffusion'
function setTitle(progress) {
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){
document.title = title;
if (document.title != title) {
document.title = title;
}
}
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)+")"
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) + ")";
}
// 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){
var dateStart = new Date()
var wasEverActive = false
var parentProgressbar = progressbarContainer.parentNode
var parentGallery = gallery ? gallery.parentNode : null
function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgress, inactivityTimeout = 40) {
var dateStart = new Date();
var wasEverActive = false;
var parentProgressbar = progressbarContainer.parentNode;
var parentGallery = gallery ? gallery.parentNode : null;
var divProgress = document.createElement('div')
divProgress.className='progressDiv'
divProgress.style.display = opts.show_progressbar ? "block" : "none"
var divInner = document.createElement('div')
divInner.className='progress'
var divProgress = document.createElement('div');
divProgress.className = 'progressDiv';
divProgress.style.display = opts.show_progressbar ? "block" : "none";
var divInner = document.createElement('div');
divInner.className = 'progress';
divProgress.appendChild(divInner)
parentProgressbar.insertBefore(divProgress, progressbarContainer)
divProgress.appendChild(divInner);
parentProgressbar.insertBefore(divProgress, progressbarContainer);
if(parentGallery){
var livePreview = document.createElement('div')
livePreview.className='livePreview'
parentGallery.insertBefore(livePreview, gallery)
if (parentGallery) {
var livePreview = document.createElement('div');
livePreview.className = 'livePreview';
parentGallery.insertBefore(livePreview, gallery);
}
var removeProgressBar = function(){
setTitle("")
parentProgressbar.removeChild(divProgress)
if(parentGallery) parentGallery.removeChild(livePreview)
atEnd()
}
var removeProgressBar = function() {
setTitle("");
parentProgressbar.removeChild(divProgress);
if (parentGallery) parentGallery.removeChild(livePreview);
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) {
request("./internal/progress", {id_task: id_task, id_live_preview: id_live_preview}, function(res) {
if (res.completed) {
removeProgressBar();
return;
}
var rect = progressbarContainer.getBoundingClientRect()
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.background = res.progress ? "" : "transparent"
divInner.style.width = ((res.progress || 0) * 100.0) + '%';
divInner.style.background = res.progress ? "" : "transparent";
if(res.progress > 0){
progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%'
if (res.progress > 0) {
progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%';
}
if(res.eta){
progressText += " ETA: " + formatTime(res.eta)
if (res.eta) {
progressText += " ETA: " + formatTime(res.eta);
}
setTitle(progressText)
setTitle(progressText);
if(res.textinfo && res.textinfo.indexOf("\n") == -1){
progressText = res.textinfo + " " + progressText
if (res.textinfo && res.textinfo.indexOf("\n") == -1) {
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){
removeProgressBar()
return
if (!res.active && wasEverActive) {
removeProgressBar();
return;
}
if(elapsedFromStart > inactivityTimeout && !res.queued && !res.active){
removeProgressBar()
return
if (elapsedFromStart > inactivityTimeout && !res.queued && !res.active) {
removeProgressBar();
return;
}
if(res.live_preview && gallery){
var rect = gallery.getBoundingClientRect()
if(rect.width){
livePreview.style.width = rect.width + "px"
livePreview.style.height = rect.height + "px"
if (res.live_preview && gallery) {
rect = gallery.getBoundingClientRect();
if (rect.width) {
livePreview.style.width = rect.width + "px";
livePreview.style.height = rect.height + "px";
}
var img = new Image();
img.onload = function() {
livePreview.appendChild(img)
if(livePreview.childElementCount > 2){
livePreview.removeChild(livePreview.firstElementChild)
livePreview.appendChild(img);
if (livePreview.childElementCount > 2) {
livePreview.removeChild(livePreview.firstElementChild);
}
}
};
img.src = res.live_preview;
}
if(onProgress){
onProgress(res)
if (onProgress) {
onProgress(res);
}
setTimeout(() => {
fun(id_task, res.id_live_preview);
}, opts.live_preview_refresh_period || 500)
}, function(){
removeProgressBar()
})
}
}, opts.live_preview_refresh_period || 500);
}, function() {
removeProgressBar();
});
};
fun(id_task, 0)
fun(id_task, 0);
}

34
javascript/textualInversion.js
View File

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

463
javascript/ui.js
View File

@ -1,9 +1,9 @@
// various functions for interaction with ui.py not large enough to warrant putting them in separate files
function set_theme(theme){
var gradioURL = window.location.href
function set_theme(theme) {
var gradioURL = window.location.href;
if (!gradioURL.includes('?__theme=')) {
window.location.replace(gradioURL + '?__theme=' + 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
buttons.forEach(function(v, i){ if(v==button) { result = i } })
var result = -1;
buttons.forEach(function(v, i) {
if (v == button) {
result = i;
}
});
return result
return result;
}
function extract_image_from_gallery(gallery){
if (gallery.length == 0){
function extract_image_from_gallery(gallery) {
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 +61,226 @@ function extract_image_from_gallery(gallery){
return [gallery[index]];
}
function args_to_array(args){
var res = []
for(var i=0;i<args.length;i++){
res.push(args[i])
}
return res
}
window.args_to_array = Array.from; // Compatibility with e.g. extensions that may expect this to be around
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(){
gradioApp().querySelector('#tabs').querySelectorAll('button')[1].click();
gradioApp().getElementById('mode_img2img').querySelectorAll('button')[2].click();
return args_to_array(arguments);
}
function switch_to_extras(){
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){
var res = 0
gradioApp().getElementById(tabId).querySelector('div').querySelectorAll('button').forEach(function(button, i){
if(button.className.indexOf('selected') != -1)
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])
function get_tab_index(tabId) {
let buttons = gradioApp().getElementById(tabId).querySelector('div').querySelectorAll('button');
for (let i = 0; i < buttons.length; i++) {
if (buttons[i].classList.contains('selected')) {
return i;
}
}
return 0;
}
res[0] = get_tab_index(tabId)
return res
function create_tab_index_args(tabId, args) {
var res = Array.from(args);
res[0] = get_tab_index(tabId);
return res;
}
function get_img2img_tab_index() {
let res = args_to_array(arguments)
res.splice(-2)
res[0] = get_tab_index('mode_img2img')
return res
let res = Array.from(arguments);
res.splice(-2);
res[0] = get_tab_index('mode_img2img');
return res;
}
function create_submit_args(args){
var res = []
for(var i=0;i<args.length;i++){
res.push(args[i])
}
function create_submit_args(args) {
var res = Array.from(args);
// 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])){
res[res.length - 3] = null
if (Array.isArray(res[res.length - 3])) {
res[res.length - 3] = null;
}
return res
return res;
}
function showSubmitButtons(tabname, show){
gradioApp().getElementById(tabname+'_interrupt').style.display = show ? "none" : "block"
gradioApp().getElementById(tabname+'_skip').style.display = show ? "none" : "block"
function showSubmitButtons(tabname, show) {
gradioApp().getElementById(tabname + '_interrupt').style.display = show ? "none" : "block";
gradioApp().getElementById(tabname + '_skip').style.display = show ? "none" : "block";
}
function showRestoreProgressButton(tabname, show){
var button = gradioApp().getElementById(tabname + "_restore_progress")
if(! button) return
function showRestoreProgressButton(tabname, show) {
var button = gradioApp().getElementById(tabname + "_restore_progress");
if (!button) return;
button.style.display = show ? "flex" : "none"
button.style.display = show ? "flex" : "none";
}
function submit(){
rememberGallerySelection('txt2img_gallery')
showSubmitButtons('txt2img', false)
function submit() {
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(){
showSubmitButtons('txt2img', true)
localStorage.removeItem("txt2img_task_id")
showRestoreProgressButton('txt2img', false)
})
requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
showSubmitButtons('txt2img', true);
localStorage.removeItem("txt2img_task_id");
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(){
rememberGallerySelection('img2img_gallery')
showSubmitButtons('img2img', false)
function submit_img2img() {
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(){
showSubmitButtons('img2img', true)
localStorage.removeItem("img2img_task_id")
showRestoreProgressButton('img2img', false)
})
requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
showSubmitButtons('img2img', true);
localStorage.removeItem("img2img_task_id");
showRestoreProgressButton('img2img', false);
});
var res = create_submit_args(arguments)
var res = create_submit_args(arguments);
res[0] = id
res[1] = get_tab_index('mode_img2img')
res[0] = id;
res[1] = get_tab_index('mode_img2img');
return res
return res;
}
function restoreProgressTxt2img(){
showRestoreProgressButton("txt2img", false)
var id = localStorage.getItem("txt2img_task_id")
function restoreProgressTxt2img() {
showRestoreProgressButton("txt2img", false);
var id = localStorage.getItem("txt2img_task_id");
id = localStorage.getItem("txt2img_task_id")
id = localStorage.getItem("txt2img_task_id");
if(id) {
requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function(){
showSubmitButtons('txt2img', true)
}, null, 0)
if (id) {
requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() {
showSubmitButtons('txt2img', true);
}, null, 0);
}
return id
return id;
}
function restoreProgressImg2img(){
showRestoreProgressButton("img2img", false)
var id = localStorage.getItem("img2img_task_id")
function restoreProgressImg2img() {
showRestoreProgressButton("img2img", false);
if(id) {
requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function(){
showSubmitButtons('img2img', true)
}, null, 0)
var id = localStorage.getItem("img2img_task_id");
if (id) {
requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() {
showSubmitButtons('img2img', true);
}, null, 0);
}
return id
return id;
}
onUiLoaded(function () {
showRestoreProgressButton('txt2img', localStorage.getItem("txt2img_task_id"))
showRestoreProgressButton('img2img', localStorage.getItem("img2img_task_id"))
onUiLoaded(function() {
showRestoreProgressButton('txt2img', localStorage.getItem("txt2img_task_id"));
showRestoreProgressButton('img2img', localStorage.getItem("img2img_task_id"));
});
function modelmerger(){
var id = randomId()
requestProgress(id, gradioApp().getElementById('modelmerger_results_panel'), null, function(){})
function modelmerger() {
var id = randomId();
requestProgress(id, gradioApp().getElementById('modelmerger_results_panel'), null, function() {});
var res = create_submit_args(arguments)
res[0] = id
return res
var res = create_submit_args(arguments);
res[0] = id;
return res;
}
function ask_for_style_name(_, prompt_text, negative_prompt_text) {
var name_ = prompt('Style name:')
return [name_, prompt_text, negative_prompt_text]
var name_ = prompt('Style name:');
return [name_, prompt_text, negative_prompt_text];
}
function confirm_clear_prompt(prompt, negative_prompt) {
if(confirm("Delete prompt?")) {
prompt = ""
negative_prompt = ""
if (confirm("Delete prompt?")) {
prompt = "";
negative_prompt = "";
}
return [prompt, negative_prompt]
return [prompt, negative_prompt];
}
promptTokecountUpdateFuncs = {}
var promptTokecountUpdateFuncs = {};
function recalculatePromptTokens(name){
if(promptTokecountUpdateFuncs[name]){
promptTokecountUpdateFuncs[name]()
function recalculatePromptTokens(name) {
if (promptTokecountUpdateFuncs[name]) {
promptTokecountUpdateFuncs[name]();
}
}
function recalculate_prompts_txt2img(){
recalculatePromptTokens('txt2img_prompt')
recalculatePromptTokens('txt2img_neg_prompt')
return args_to_array(arguments);
function recalculate_prompts_txt2img() {
recalculatePromptTokens('txt2img_prompt');
recalculatePromptTokens('txt2img_neg_prompt');
return Array.from(arguments);
}
function recalculate_prompts_img2img(){
recalculatePromptTokens('img2img_prompt')
recalculatePromptTokens('img2img_neg_prompt')
return args_to_array(arguments);
function recalculate_prompts_img2img() {
recalculatePromptTokens('img2img_prompt');
recalculatePromptTokens('img2img_neg_prompt');
return Array.from(arguments);
}
var opts = {}
onUiUpdate(function(){
if(Object.keys(opts).length != 0) return;
var opts = {};
onUiUpdate(function() {
if (Object.keys(opts).length != 0) return;
var json_elem = gradioApp().getElementById('settings_json')
if(json_elem == null) 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);
var textarea = json_elem.querySelector('textarea');
var jsdata = textarea.value;
opts = JSON.parse(jsdata);
executeCallbacks(optionsChangedCallbacks); /*global optionsChangedCallbacks*/
Object.defineProperty(textarea, 'value', {
set: function(newValue) {
@ -308,7 +289,7 @@ onUiUpdate(function(){
valueProp.set.call(textarea, newValue);
if (oldValue != newValue) {
opts = JSON.parse(textarea.value)
opts = JSON.parse(textarea.value);
}
executeCallbacks(optionsChangedCallbacks);
@ -319,123 +300,157 @@ onUiUpdate(function(){
}
});
json_elem.parentElement.style.display="none"
json_elem.parentElement.style.display = "none";
function registerTextarea(id, id_counter, id_button){
var prompt = gradioApp().getElementById(id)
var counter = gradioApp().getElementById(id_counter)
function registerTextarea(id, id_counter, id_button) {
var prompt = gradioApp().getElementById(id);
var counter = gradioApp().getElementById(id_counter);
var textarea = gradioApp().querySelector("#" + id + " > label > textarea");
if(counter.parentElement == prompt.parentElement){
return
if (counter.parentElement == prompt.parentElement) {
return;
}
prompt.parentElement.insertBefore(counter, prompt)
prompt.parentElement.style.position = "relative"
prompt.parentElement.insertBefore(counter, prompt);
prompt.parentElement.style.position = "relative";
promptTokecountUpdateFuncs[id] = function(){ update_token_counter(id_button); }
textarea.addEventListener("input", promptTokecountUpdateFuncs[id]);
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')
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")
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(){
var elem = gradioApp().getElementById('sd_checkpoint_hash')
var sd_checkpoint_hash = opts.sd_checkpoint_hash || ""
var shorthash = sd_checkpoint_hash.substring(0,10)
onOptionsChanged(function() {
var elem = gradioApp().getElementById('sd_checkpoint_hash');
var sd_checkpoint_hash = opts.sd_checkpoint_hash || "";
var shorthash = sd_checkpoint_hash.substring(0, 10);
if(elem && elem.textContent != shorthash){
elem.textContent = shorthash
elem.title = sd_checkpoint_hash
elem.href = "https://google.com/search?q=" + sd_checkpoint_hash
}
})
if (elem && elem.textContent != shorthash) {
elem.textContent = shorthash;
elem.title = sd_checkpoint_hash;
elem.href = "https://google.com/search?q=" + sd_checkpoint_hash;
}
});
let txt2img_textarea, img2img_textarea = undefined;
let wait_time = 800
let wait_time = 800;
let token_timeouts = {};
function update_txt2img_tokens(...args) {
update_token_counter("txt2img_token_button")
if (args.length == 2)
return args[0]
return args;
update_token_counter("txt2img_token_button");
if (args.length == 2) {
return args[0];
}
return args;
}
function update_img2img_tokens(...args) {
update_token_counter("img2img_token_button")
if (args.length == 2)
return args[0]
return args;
update_token_counter(
"img2img_token_button"
);
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);
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>';
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){
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){
let e = new Event("input", { bubbles: true })
Object.defineProperty(e, "target", {value: target})
target.dispatchEvent(e);
function updateInput(target) {
let e = new Event("input", {bubbles: true});
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){
var img = gradioApp().querySelector('#mode_img2img > div[style="display: block;"] img')
return img ? [img.naturalWidth, img.naturalHeight, scaleBy] : [0, 0, scaleBy]
function currentImg2imgSourceResolution(w, h, scaleBy) {
var img = gradioApp().querySelector('#mode_img2img > div[style="display: block;"] img');
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 [];
}

103
javascript/ui_settings_hints.js
View File

@ -1,41 +1,62 @@
// various hints and extra info for the settings tab
onUiLoaded(function(){
createLink = function(elem_id, text, href){
var a = document.createElement('A')
a.textContent = text
a.target = '_blank';
elem = gradioApp().querySelector('#'+elem_id)
elem.insertBefore(a, elem.querySelector('label'))
return a
}
createLink("setting_samples_filename_pattern", "[wiki] ").href = "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"
createLink("setting_directories_filename_pattern", "[wiki] ").href = "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"
createLink("setting_quicksettings_list", "[info] ").addEventListener("click", function(event){
requestGet("./internal/quicksettings-hint", {}, function(data){
var table = document.createElement('table')
table.className = 'settings-value-table'
data.forEach(function(obj){
var tr = document.createElement('tr')
var td = document.createElement('td')
td.textContent = obj.name
tr.appendChild(td)
var td = document.createElement('td')
td.textContent = obj.label
tr.appendChild(td)
table.appendChild(tr)
})
popup(table);
})
});
})
// various hints and extra info for the settings tab
var settingsHintsSetup = false;
onOptionsChanged(function() {
if (settingsHintsSetup) return;
settingsHintsSetup = true;
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);
}
});
});
function settingsHintsShowQuicksettings() {
requestGet("./internal/quicksettings-hint", {}, function(data) {
var table = document.createElement('table');
table.className = 'settings-value-table';
data.forEach(function(obj) {
var tr = document.createElement('tr');
var td = document.createElement('td');
td.textContent = obj.name;
tr.appendChild(td);
td = document.createElement('td');
td.textContent = obj.label;
tr.appendChild(td);
table.appendChild(tr);
});
popup(table);
});
}

384
launch.py
View File

@ -1,370 +1,38 @@
# this scripts installs necessary requirements and launches main program in webui.py
import subprocess
import os
import sys
import importlib.util
import shlex
import platform
import json
from modules import launch_utils
from modules import cmd_args
from modules.paths_internal import script_path, extensions_dir
commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
sys.argv += shlex.split(commandline_args)
args = launch_utils.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
git = os.environ.get('GIT', "git")
index_url = os.environ.get('INDEX_URL', "")
stored_commit_hash = None
stored_git_tag = None
dir_repos = "repositories"
run = launch_utils.run
is_installed = launch_utils.is_installed
repo_dir = launch_utils.repo_dir
if 'GRADIO_ANALYTICS_ENABLED' not in os.environ:
os.environ['GRADIO_ANALYTICS_ENABLED'] = 'False'
run_pip = launch_utils.run_pip
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():
is_windows = platform.system() == "Windows"
major = sys.version_info.major
minor = sys.version_info.minor
micro = sys.version_info.micro
def main():
if not args.skip_prepare_environment:
prepare_environment()
if is_windows:
supported_minors = [10]
else:
supported_minors = [7, 8, 9, 10, 11]
if args.test_server:
configure_for_tests()
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.
""")
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()
start()
if __name__ == "__main__":
prepare_environment()
start()
main()

BIN
modules/Roboto-Regular.ttf Normal file
View File

Binary file not shown.

174
modules/api/api.py
View File

@ -15,7 +15,8 @@ from secrets import compare_digest
import modules.shared as shared
from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing
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
@ -25,21 +26,24 @@ from modules.sd_models import checkpoints_list, unload_model_weights, reload_mod
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
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])}")
except Exception as e:
raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in shared.sd_upscalers])}") from e
def script_name_to_index(name, scripts):
try:
return [script.title().lower() for script in scripts].index(name.lower())
except:
raise HTTPException(status_code=422, detail=f"Script '{name}' not found")
except Exception as e:
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 +52,23 @@ 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:
raise HTTPException(status_code=500, detail="Invalid encoded image")
except Exception as e:
raise HTTPException(status_code=500, detail="Invalid encoded image") from e
def encode_pil_to_base64(image):
with io.BytesIO() as output_bytes:
@ -92,6 +99,7 @@ def encode_pil_to_base64(image):
return base64.b64encode(bytes_data)
def api_middleware(app: FastAPI):
rich_available = True
try:
@ -99,7 +107,7 @@ 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
@ -157,7 +165,7 @@ 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 +174,37 @@ 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/img2img", self.img2imgapi, methods=["POST"], response_model=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-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=ExtrasBatchImagesResponse)
self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=PNGInfoResponse)
self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=ProgressResponse)
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=models.ImageToImageResponse)
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=models.ExtrasBatchImagesResponse)
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=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/samplers", self.get_samplers, methods=["GET"], response_model=List[SamplerItem])
self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[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/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem])
self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem])
self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem])
self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem])
self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse)
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[models.SamplerItem])
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[models.SDModelItem])
self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[models.HypernetworkItem])
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/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/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse)
self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=PreprocessResponse)
self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=TrainResponse)
self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=TrainResponse)
self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=MemoryResponse)
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=models.CreateResponse)
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=models.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=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])
self.default_script_arg_txt2img = []
self.default_script_arg_img2img = []
@ -219,17 +228,25 @@ class Api:
script_idx = script_name_to_index(script_name, script_runner.selectable_scripts)
script = script_runner.selectable_scripts[script_idx]
return script, script_idx
def get_scripts_list(self):
t2ilist = [str(title.lower()) for title in scripts.scripts_txt2img.titles]
i2ilist = [str(title.lower()) for title in scripts.scripts_img2img.titles]
return ScriptsList(txt2img = t2ilist, img2img = i2ilist)
def get_scripts_list(self):
t2ilist = [script.name for script in scripts.scripts_txt2img.scripts if script.name is not None]
i2ilist = [script.name for script in scripts.scripts_img2img.scripts if script.name is not None]
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 == "":
return None, None
script_idx = script_name_to_index(script_name, script_runner.scripts)
return script_runner.scripts[script_idx]
@ -264,11 +281,11 @@ class Api:
if request.alwayson_scripts and (len(request.alwayson_scripts) > 0):
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:
raise HTTPException(status_code=422, detail=f"Cannot have a selectable script in the always on scripts params")
if alwayson_script.alwayson is False:
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 +293,7 @@ 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)
@ -310,7 +327,7 @@ class Api:
p.outpath_samples = opts.outdir_txt2img_samples
shared.state.begin()
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 +337,9 @@ 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")
@ -367,7 +384,7 @@ class Api:
p.outpath_samples = opts.outdir_img2img_samples
shared.state.begin()
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 +398,9 @@ 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 +408,9 @@ 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 +419,15 @@ 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 +435,13 @@ 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 +463,9 @@ 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 +482,7 @@ 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()
@ -570,36 +587,36 @@ class Api:
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 CreateResponse(info=f"create embedding filename: {filename}")
return models.CreateResponse(info=f"create embedding filename: {filename}")
except AssertionError as e:
shared.state.end()
return TrainResponse(info=f"create embedding error: {e}")
return models.TrainResponse(info=f"create embedding error: {e}")
def create_hypernetwork(self, args: dict):
try:
shared.state.begin()
filename = create_hypernetwork(**args) # create empty embedding
shared.state.end()
return CreateResponse(info=f"create hypernetwork filename: {filename}")
return models.CreateResponse(info=f"create hypernetwork filename: {filename}")
except AssertionError as e:
shared.state.end()
return TrainResponse(info=f"create hypernetwork error: {e}")
return models.TrainResponse(info=f"create hypernetwork error: {e}")
def preprocess(self, args: dict):
try:
shared.state.begin()
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:
shared.state.end()
return PreprocessResponse(info=f"preprocess error: invalid token: {e}")
return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}")
except AssertionError as e:
shared.state.end()
return PreprocessResponse(info=f"preprocess error: {e}")
return models.PreprocessResponse(info=f"preprocess error: {e}")
except FileNotFoundError as e:
shared.state.end()
return PreprocessResponse(info=f'preprocess error: {e}')
return models.PreprocessResponse(info=f'preprocess error: {e}')
def train_embedding(self, args: dict):
try:
@ -617,10 +634,10 @@ 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:
shared.state.end()
return TrainResponse(info=f"train embedding error: {msg}")
return models.TrainResponse(info=f"train embedding error: {msg}")
def train_hypernetwork(self, args: dict):
try:
@ -641,14 +658,15 @@ class Api:
if not apply_optimizations:
sd_hijack.apply_optimizations()
shared.state.end()
return TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
except AssertionError as msg:
return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}")
except AssertionError:
shared.state.end()
return TrainResponse(info=f"train embedding error: {error}")
return models.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
@ -675,10 +693,10 @@ class Api:
'events': warnings,
}
else:
cuda = { 'error': 'unavailable' }
cuda = {'error': 'unavailable'}
except Exception as err:
cuda = { 'error': f'{err}' }
return MemoryResponse(ram = ram, cuda = cuda)
cuda = {'error': f'{err}'}
return models.MemoryResponse(ram=ram, cuda=cuda)
def launch(self, server_name, port):
self.app.include_router(self.router)

26
modules/api/models.py
View File

@ -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)
flags.update({flag.dest: (_type,Field(default=flag.default, description=flag.help))})
if _options[key].default is not None:
_type = type(_options[key].default)
flags.update({flag.dest: (_type, Field(default=flag.default, description=flag.help))})
FlagsModel = create_model("Flags", **flags)
@ -286,6 +287,23 @@ 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)")
img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)")
txt2img: list = Field(default=None, title="Txt2img", description="Titles of scripts (txt2img)")
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")

28
modules/cmd_args.py
View File

@ -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()
@ -11,8 +12,8 @@ parser.add_argument("--skip-torch-cuda-test", action='store_true', help="launch.
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("--tests", type=str, default=None, help="launch.py argument: run tests in the specified directory")
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("--test-server", action='store_true', help="launch.py argument: configure server for testing")
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-sub-quad-attention", action='store_true', help="enable memory efficient sub-quadratic cross-attention layer optimization")
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="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-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-sdp-attention", action='store_true', help="enable scaled dot product cross-attention layer 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("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
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="prefer older version of split attention optimization for automatic choice of optimization")
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="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="does not do anything")
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)
@ -102,4 +105,5 @@ parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gra
parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers")
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('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy')
parser.add_argument('--add-stop-route', action='store_true', help='add /_stop route to stop server')

24
modules/codeformer/codeformer_arch.py
View File

@ -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 basicsr.utils import get_root_logger
from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock
from basicsr.utils.registry import ARCH_REGISTRY
def calc_mean_std(feat, eps=1e-5):
@ -121,7 +119,7 @@ class TransformerSALayer(nn.Module):
tgt_mask: Optional[Tensor] = None,
tgt_key_padding_mask: Optional[Tensor] = None,
query_pos: Optional[Tensor] = None):
# self attention
tgt2 = self.norm1(tgt)
q = k = self.with_pos_embed(tgt2, query_pos)
@ -161,10 +159,10 @@ class Fuse_sft_block(nn.Module):
@ARCH_REGISTRY.register()
class CodeFormer(VQAutoEncoder):
def __init__(self, dim_embd=512, n_head=8, n_layers=9,
def __init__(self, dim_embd=512, n_head=8, n_layers=9,
codebook_size=1024, latent_size=256,
connect_list=['32', '64', '128', '256'],
fix_modules=['quantize','generator']):
connect_list=('32', '64', '128', '256'),
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:
@ -181,14 +179,14 @@ class CodeFormer(VQAutoEncoder):
self.feat_emb = nn.Linear(256, self.dim_embd)
# transformer
self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0)
self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0)
for _ in range(self.n_layers)])
# logits_predict head
self.idx_pred_layer = nn.Sequential(
nn.LayerNorm(dim_embd),
nn.Linear(dim_embd, codebook_size, bias=False))
self.channels = {
'16': 512,
'32': 256,
@ -223,7 +221,7 @@ class CodeFormer(VQAutoEncoder):
enc_feat_dict = {}
out_list = [self.fuse_encoder_block[f_size] for f_size in self.connect_list]
for i, block in enumerate(self.encoder.blocks):
x = block(x)
x = block(x)
if i in out_list:
enc_feat_dict[str(x.shape[-1])] = x.clone()
@ -268,11 +266,11 @@ class CodeFormer(VQAutoEncoder):
fuse_list = [self.fuse_generator_block[f_size] for f_size in self.connect_list]
for i, block in enumerate(self.generator.blocks):
x = block(x)
x = block(x)
if i in fuse_list: # fuse after i-th block
f_size = str(x.shape[-1])
if w>0:
x = self.fuse_convs_dict[f_size](enc_feat_dict[f_size].detach(), x, w)
out = x
# logits doesn't need softmax before cross_entropy loss
return out, logits, lq_feat
return out, logits, lq_feat

44
modules/codeformer/vqgan_arch.py
View File

@ -5,17 +5,15 @@ 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
def normalize(in_channels):
return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
@torch.jit.script
def swish(x):
@ -212,15 +210,15 @@ class AttnBlock(nn.Module):
# compute attention
b, c, h, w = q.shape
q = q.reshape(b, c, h*w)
q = q.permute(0, 2, 1)
q = q.permute(0, 2, 1)
k = k.reshape(b, c, h*w)
w_ = torch.bmm(q, k)
w_ = torch.bmm(q, k)
w_ = w_ * (int(c)**(-0.5))
w_ = F.softmax(w_, dim=2)
# attend to values
v = v.reshape(b, c, h*w)
w_ = w_.permute(0, 2, 1)
w_ = w_.permute(0, 2, 1)
h_ = torch.bmm(v, w_)
h_ = h_.reshape(b, c, h, w)
@ -272,18 +270,18 @@ class Encoder(nn.Module):
def forward(self, x):
for block in self.blocks:
x = block(x)
return x
class Generator(nn.Module):
def __init__(self, nf, emb_dim, ch_mult, res_blocks, img_size, attn_resolutions):
super().__init__()
self.nf = nf
self.ch_mult = ch_mult
self.nf = nf
self.ch_mult = ch_mult
self.num_resolutions = len(self.ch_mult)
self.num_res_blocks = res_blocks
self.resolution = img_size
self.resolution = img_size
self.attn_resolutions = attn_resolutions
self.in_channels = emb_dim
self.out_channels = 3
@ -317,29 +315,29 @@ class Generator(nn.Module):
blocks.append(nn.Conv2d(block_in_ch, self.out_channels, kernel_size=3, stride=1, padding=1))
self.blocks = nn.ModuleList(blocks)
def forward(self, x):
for block in self.blocks:
x = block(x)
return x
@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()
self.in_channels = 3
self.nf = nf
self.n_blocks = res_blocks
self.in_channels = 3
self.nf = nf
self.n_blocks = res_blocks
self.codebook_size = codebook_size
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,
@ -365,11 +363,11 @@ class VQAutoEncoder(nn.Module):
self.kl_weight
)
self.generator = Generator(
self.nf,
self.nf,
self.embed_dim,
self.ch_mult,
self.n_blocks,
self.resolution,
self.ch_mult,
self.n_blocks,
self.resolution,
self.attn_resolutions
)
@ -434,4 +432,4 @@ class VQGANDiscriminator(nn.Module):
raise ValueError('Wrong params!')
def forward(self, x):
return self.main(x)
return self.main(x)

6
modules/codeformer_model.py
View File

@ -33,11 +33,9 @@ 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 imwrite, img2tensor, tensor2img
from basicsr.utils import 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 +94,7 @@ 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)

6
modules/config_states.py
View File

@ -14,7 +14,7 @@ from collections import OrderedDict
import git
from modules import shared, extensions
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 +35,7 @@ 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"]))
@ -83,6 +83,8 @@ def get_extension_config():
ext_config = {}
for ext in extensions.extensions:
ext.read_info_from_repo()
entry = {
"name": ext.name,
"path": ext.path,

3
modules/deepbooru.py
View File

@ -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]

2
modules/devices.py
View File

@ -65,7 +65,7 @@ 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

12
modules/esrgan_model.py
View File

@ -6,7 +6,7 @@ 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
@ -16,9 +16,7 @@ def mod2normal(state_dict):
# this code is copied from https://github.com/victorca25/iNNfer
if 'conv_first.weight' in state_dict:
crt_net = {}
items = []
for k, v in state_dict.items():
items.append(k)
items = list(state_dict)
crt_net['model.0.weight'] = state_dict['conv_first.weight']
crt_net['model.0.bias'] = state_dict['conv_first.bias']
@ -52,9 +50,7 @@ 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 = []
for k, v in state_dict.items():
items.append(k)
items = list(state_dict)
crt_net['model.0.weight'] = state_dict['conv_first.weight']
crt_net['model.0.bias'] = state_dict['conv_first.bias']
@ -158,7 +154,7 @@ class UpscalerESRGAN(Upscaler):
if "http" in path:
filename = 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,
)

7
modules/esrgan_model_arch.py
View File

@ -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
@ -106,7 +105,7 @@ class ResidualDenseBlock_5C(nn.Module):
Modified options that can be used:
- "Partial Convolution based Padding" arXiv:1811.11718
- "Spectral normalization" arXiv:1802.05957
- "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C.
- "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C.
{Rakotonirina} and A. {Rasoanaivo}
"""
@ -171,7 +170,7 @@ class GaussianNoise(nn.Module):
scale = self.sigma * x.detach() if self.is_relative_detach else self.sigma * x
sampled_noise = self.noise.repeat(*x.size()).normal_() * scale
x = x + sampled_noise
return x
return x
def conv1x1(in_planes, out_planes, stride=1):
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
@ -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':

25
modules/extensions.py
View File

@ -1,13 +1,12 @@
import os
import sys
import threading
import traceback
import time
from datetime import datetime
import git
from modules import shared
from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path
from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path # noqa: F401
extensions = []
@ -25,6 +24,8 @@ def active():
class Extension:
lock = threading.Lock()
def __init__(self, name, path, enabled=True, is_builtin=False):
self.name = name
self.path = path
@ -43,8 +44,13 @@ 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")):
@ -59,18 +65,19 @@ class Extension:
try:
self.status = 'unknown'
self.remote = next(repo.remote().urls, None)
head = repo.head.commit
self.commit_date = repo.head.commit.committed_date
ts = time.asctime(time.gmtime(self.commit_date))
commit = repo.head.commit
self.commit_date = commit.committed_date
if repo.active_branch:
self.branch = repo.active_branch.name
self.commit_hash = head.hexsha
self.version = f'{self.commit_hash[:8]} ({ts})'
self.commit_hash = commit.hexsha
self.version = self.commit_hash[:8]
except Exception as ex:
print(f"Failed reading extension data from Git repository ({self.name}): {ex}", file=sys.stderr)
self.remote = None
self.have_info_from_repo = True
def list_files(self, subdir, extension):
from modules import scripts

16
modules/extra_networks.py
View File

@ -14,9 +14,23 @@ 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 len(parts) == 2:
self.named[parts[0]] = parts[1]
else:
self.positional.append(item)
class ExtraNetwork:
@ -91,7 +105,7 @@ 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

2
modules/extra_networks_hypernet.py
View File

@ -1,4 +1,4 @@
from modules import extra_networks, shared, extra_networks
from modules import extra_networks, shared
from modules.hypernetworks import hypernetwork

18
modules/extras.py
View File

@ -136,14 +136,14 @@ 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')
@ -199,7 +199,7 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_
result_is_inpainting_model = True
else:
theta_0[key] = theta_func2(a, b, multiplier)
theta_0[key] = to_half(theta_0[key], save_as_half)
shared.state.sampling_step += 1
@ -242,9 +242,11 @@ 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 +264,17 @@ 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 +282,7 @@ 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":

44
modules/generation_parameters_copypaste.py
View File

@ -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():
@ -38,13 +35,20 @@ def reset():
def quote(text):
if ',' not in str(text):
if ',' not in str(text) and '\n' not in str(text):
return text
text = str(text)
text = text.replace('\\', '\\\\')
text = text.replace('"', '\\"')
return f'"{text}"'
return json.dumps(text, ensure_ascii=False)
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):
@ -251,12 +255,11 @@ 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:
@ -266,7 +269,9 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
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
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)
@ -286,6 +291,15 @@ 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
@ -312,6 +326,8 @@ 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'),
]

2
modules/gfpgan_model.py
View File

@ -78,7 +78,7 @@ def setup_model(dirname):
try:
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

29
modules/hashes.py
View File

@ -46,8 +46,8 @@ def calculate_sha256(filename):
return hash_sha256.hexdigest()
def sha256_from_cache(filename, title):
hashes = cache("hashes")
def sha256_from_cache(filename, title, use_addnet_hash=False):
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):
hashes = cache("hashes")
def sha256(filename, title, use_addnet_hash=False):
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
@ -73,7 +73,11 @@ def sha256(filename, title):
return None
print(f"Calculating sha256 for {filename}: ", end='')
sha256_value = calculate_sha256(filename)
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}")
hashes[title] = {
@ -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()

29
modules/hypernetworks/hypernetwork.py
View File

@ -1,4 +1,3 @@
import csv
import datetime
import glob
import html
@ -18,7 +17,7 @@ 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 +177,34 @@ 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():
@ -404,7 +403,7 @@ 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
@ -541,7 +540,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
return hypernetwork, filename
scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else None
if clip_grad:
clip_grad_sched = LearnRateScheduler(clip_grad_value, steps, initial_step, verbose=False)
@ -594,7 +593,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
print(e)
scaler = torch.cuda.amp.GradScaler()
batch_size = ds.batch_size
gradient_step = ds.gradient_step
# n steps = batch_size * gradient_step * n image processed
@ -620,7 +619,7 @@ 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:
@ -637,7 +636,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
if clip_grad:
clip_grad_sched.step(hypernetwork.step)
with devices.autocast():
x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
if use_weight:
@ -658,14 +657,14 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
_loss_step += loss.item()
scaler.scale(loss).backward()
# go back until we reach gradient accumulation steps
if (j + 1) % gradient_step != 0:
continue
loss_logging.append(_loss_step)
if clip_grad:
clip_grad(weights, clip_grad_sched.learn_rate)
scaler.step(optimizer)
scaler.update()
hypernetwork.step += 1
@ -675,7 +674,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
_loss_step = 0
steps_done = hypernetwork.step + 1
epoch_num = hypernetwork.step // steps_per_epoch
epoch_step = hypernetwork.step % steps_per_epoch

6
modules/hypernetworks/ui.py
View File

@ -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):

99
modules/images.py
View File

@ -13,17 +13,24 @@ import numpy as np
import piexif
import piexif.helper
from PIL import Image, ImageFont, ImageDraw, 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
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:
@ -142,14 +149,8 @@ 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:
@ -366,7 +367,7 @@ class FilenameGenerator:
self.seed = seed
self.prompt = prompt
self.image = image
def hasprompt(self, *args):
lower = self.prompt.lower()
if self.p is None or self.prompt is None:
@ -409,13 +410,13 @@ class FilenameGenerator:
time_format = args[0] if len(args) > 0 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)
@ -472,15 +473,52 @@ 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):
if extension is None:
extension = os.path.splitext(filename)[1]
image_format = Image.registered_extensions()[extension]
existing_pnginfo = existing_pnginfo or {}
if opts.enable_pnginfo:
existing_pnginfo['parameters'] = geninfo
if extension.lower() == '.png':
pnginfo_data = PngImagePlugin.PngInfo()
for k, v in (existing_pnginfo or {}).items():
pnginfo_data.add_text(k, str(v))
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 +603,13 @@ 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':
pnginfo_data = PngImagePlugin.PngInfo()
if opts.enable_pnginfo:
for k, v in params.pnginfo.items():
pnginfo_data.add_text(k, str(v))
save_image_with_geninfo(image_to_save, info, temp_file_path, extension, params.pnginfo)
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)

8
modules/img2img.py
View File

@ -1,19 +1,15 @@
import math
import os
import sys
import traceback
import numpy as np
from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops, UnidentifiedImageError
from modules import devices, sd_samplers
from modules import sd_samplers
from modules.generation_parameters_copypaste import create_override_settings_dict
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
@ -59,7 +55,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args):
# 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 not found use first one ("same mask for all images" use-case)
if not mask_image_path in inpaint_masks:
if mask_image_path not in inpaint_masks:
mask_image_path = inpaint_masks[0]
mask_image = Image.open(mask_image_path)
p.image_mask = mask_image

7
modules/interrogate.py
View File

@ -11,7 +11,6 @@ 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 +159,7 @@ 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)
@ -208,8 +207,8 @@ class InterrogateModels:
image_features /= image_features.norm(dim=-1, keepdim=True)
for name, topn, items in self.categories():
matches = self.rank(image_features, items, top_count=topn)
for cat in self.categories():
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})"

334
modules/launch_utils.py Normal file
View File

@ -0,0 +1,334 @@
# 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
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:
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}").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_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==0.0.17')
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")
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', "c9fe758757e022f05ca5a53fa8fac28889e4f1cf")
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 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(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)
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()

5
modules/mac_specific.py
View File

@ -1,6 +1,5 @@
import torch
import platform
from modules import paths
from modules.sd_hijack_utils import CondFunc
from packaging import version
@ -43,7 +42,7 @@ if has_mps:
# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
CondFunc('torch.Tensor.to', lambda orig_func, self, *args, **kwargs: orig_func(self.contiguous(), *args, **kwargs),
lambda _, self, *args, **kwargs: self.device.type != 'mps' and (args and isinstance(args[0], torch.device) and args[0].type == 'mps' or isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps'))
# MPS workaround for https://github.com/pytorch/pytorch/issues/80800
# MPS workaround for https://github.com/pytorch/pytorch/issues/80800
CondFunc('torch.nn.functional.layer_norm', lambda orig_func, *args, **kwargs: orig_func(*([args[0].contiguous()] + list(args[1:])), **kwargs),
lambda _, *args, **kwargs: args and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps')
# MPS workaround for https://github.com/pytorch/pytorch/issues/90532
@ -61,4 +60,4 @@ if has_mps:
# MPS workaround for https://github.com/pytorch/pytorch/issues/92311
if platform.processor() == 'i386':
for funcName in ['torch.argmax', 'torch.Tensor.argmax']:
CondFunc(funcName, lambda _, input, *args, **kwargs: torch.max(input.float() if input.dtype == torch.int64 else input, *args, **kwargs)[1], lambda _, input, *args, **kwargs: input.device.type == 'mps')
CondFunc(funcName, lambda _, input, *args, **kwargs: torch.max(input.float() if input.dtype == torch.int64 else input, *args, **kwargs)[1], lambda _, input, *args, **kwargs: input.device.type == 'mps')

2
modules/masking.py
View File

@ -4,7 +4,7 @@ from PIL import Image, ImageFilter, ImageOps
def get_crop_region(mask, pad=0):
"""finds a rectangular region that contains all masked ares in an image. Returns (x1, y1, x2, y2) coordinates of the rectangle.
For example, if a user has painted the top-right part of a 512x512 image", the result may be (256, 0, 512, 256)"""
h, w = mask.shape
crop_left = 0

16
modules/modelloader.py
View File

@ -1,4 +1,3 @@
import glob
import os
import shutil
import importlib
@ -40,7 +39,7 @@ 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)
@ -48,7 +47,7 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None
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
dl = load_file_from_url(model_url, model_path, True, download_name)
dl = load_file_from_url(model_url, places[0], True, download_name)
output.append(dl)
else:
output.append(model_url)
@ -108,12 +107,12 @@ 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 +126,7 @@ def load_upscalers():
full_model = f"modules.{model_name}_model"
try:
importlib.import_module(full_model)
except:
except Exception:
pass
datas = []
@ -145,7 +144,10 @@ 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(

52
modules/models/diffusion/ddpm_edit.py
View File

@ -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"]
@ -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 img_callback: img_callback(img, i)
if callback:
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 img_callback: img_callback(img, i)
if callback:
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]

2
modules/models/diffusion/uni_pc/__init__.py
View File

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

3
modules/models/diffusion/uni_pc/sampler.py
View File

@ -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}")

82
modules/models/diffusion/uni_pc/uni_pc.py
View File

@ -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]]))
@ -757,40 +759,44 @@ class UniPC:
vec_t = timesteps[0].expand((x.shape[0]))
model_prev_list = [self.model_fn(x, vec_t)]
t_prev_list = [vec_t]
# 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])
x, model_x = self.multistep_uni_pc_update(x, model_prev_list, t_prev_list, vec_t, init_order, use_corrector=True)
if model_x is None:
model_x = self.model_fn(x, vec_t)
if self.after_update is not None:
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):
vec_t = timesteps[step].expand(x.shape[0])
if lower_order_final:
step_order = min(order, steps + 1 - step)
else:
step_order = order
#print('this step order:', step_order)
if step == steps:
#print('do not run corrector at the last step')
use_corrector = False
else:
use_corrector = True
x, model_x = self.multistep_uni_pc_update(x, model_prev_list, t_prev_list, vec_t, step_order, use_corrector=use_corrector)
if self.after_update is not None:
self.after_update(x, model_x)
for i in range(order - 1):
t_prev_list[i] = t_prev_list[i + 1]
model_prev_list[i] = model_prev_list[i + 1]
t_prev_list[-1] = vec_t
# We do not need to evaluate the final model value.
if step < steps:
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])
x, model_x = self.multistep_uni_pc_update(x, model_prev_list, t_prev_list, vec_t, init_order, use_corrector=True)
if model_x is None:
model_x = self.model_fn(x, vec_t)
model_prev_list[-1] = model_x
if self.after_update is not None:
self.after_update(x, model_x)
model_prev_list.append(model_x)
t_prev_list.append(vec_t)
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)
else:
step_order = order
#print('this step order:', step_order)
if step == steps:
#print('do not run corrector at the last step')
use_corrector = False
else:
use_corrector = True
x, model_x = self.multistep_uni_pc_update(x, model_prev_list, t_prev_list, vec_t, step_order, use_corrector=use_corrector)
if self.after_update is not None:
self.after_update(x, model_x)
for i in range(order - 1):
t_prev_list[i] = t_prev_list[i + 1]
model_prev_list[i] = model_prev_list[i + 1]
t_prev_list[-1] = vec_t
# We do not need to evaluate the final model value.
if step < steps:
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:

38
modules/ngrok.py
View File

@ -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(
auth_token=token, region=region
)
# 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
# For all options see: https://github.com/ngrok/ngrok-py/blob/main/examples/ngrok-connect-full.py
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'
try:
if account is None:
public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True).public_url
else:
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'
public_url = ngrok.connect(f"127.0.0.1:{port}", **options).url()
except Exception as e:
print(f'Invalid ngrok authtoken? ngrok connection aborted due to: {e}\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'

4
modules/paths.py
View File

@ -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

12
modules/paths_internal.py
View File

@ -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')

260
modules/processing.py
View File

@ -2,7 +2,6 @@ import json
import math
import os
import sys
import warnings
import hashlib
import torch
@ -11,10 +10,10 @@ from PIL import Image, ImageFilter, 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
from modules.sd_hijack import model_hijack
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
@ -31,6 +30,7 @@ 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
@ -150,6 +150,8 @@ 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 +167,18 @@ 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.seeds = None
self.subseeds = None
self.step_multiplier = 1
self.cached_uc = [None, None]
self.cached_c = [None, None]
self.uc = None
self.c = None
@property
def sd_model(self):
@ -273,6 +286,62 @@ class StableDiffusionProcessing:
def close(self):
self.sampler = None
self.c = None
self.uc = None
self.cached_c = [None, None]
self.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, 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]
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.c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, self.prompts, self.steps * self.step_multiplier, self.cached_c)
def parse_extra_network_prompts(self):
self.prompts, extra_network_data = extra_networks.parse_prompts(self.prompts)
return extra_network_data
class Processed:
@ -303,6 +372,8 @@ 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 +381,7 @@ 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 +432,9 @@ 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):
@ -472,6 +547,13 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
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,
@ -489,15 +571,16 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
"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,
}
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])
negative_prompt_text = f"\nNegative prompt: {p.all_negative_prompts[index]}" if p.all_negative_prompts[index] else ""
@ -523,9 +606,13 @@ 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 +642,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
comments = {}
if type(p.prompt) == list:
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)]
p.setup_prompts()
if type(seed) == list:
p.all_seeds = seed
@ -587,29 +666,6 @@ 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)
@ -631,25 +687,25 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
if state.interrupted:
break
prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
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]
subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size]
p.prompts = p.all_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]
p.seeds = p.all_seeds[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)
extra_network_data = p.parse_extra_network_prompts()
if not p.disable_extra_networks:
with devices.autocast():
extra_networks.activate(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 +716,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
processed = Processed(p, [], p.seed, "")
file.write(processed.infotext(p, 0))
step_multiplier = 1
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)
p.setup_conds()
if len(model_hijack.comments) > 0:
for comment in model_hijack.comments:
@ -677,7 +726,7 @@ 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:
@ -704,7 +753,7 @@ 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 +770,13 @@ 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 +789,10 @@ 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)
@ -785,7 +834,7 @@ 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,
@ -812,7 +861,7 @@ def old_hires_fix_first_pass_dimensions(width, height):
class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
sampler = 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 +872,11 @@ 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 +888,24 @@ 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.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
@ -965,9 +1035,11 @@ 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]
@ -978,12 +1050,67 @@ 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)
sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio(for_hr=True))
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):
self.hr_c = None
self.hr_uc = 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 setup_conds(self):
super().setup_conds()
if self.enable_hr:
self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, self.hr_negative_prompts, self.steps * self.step_multiplier, self.cached_uc)
self.hr_c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, self.hr_prompts, self.steps * self.step_multiplier, self.cached_c)
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
@ -1141,3 +1268,6 @@ 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

15
modules/progress.py
View File

@ -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

27
modules/prompt_parser.py
View File

@ -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):
if current_step <= end_at:
for current, entry in enumerate(cond_schedule):
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):
if current_step <= end_at:
for current, entry in enumerate(composable_prompt.schedules):
if current_step <= entry.end_at_step:
target_index = current
break

10
modules/realesrgan_model.py
View File

@ -17,9 +17,9 @@ class UpscalerRealESRGAN(Upscaler):
self.user_path = path
super().__init__()
try:
from basicsr.archs.rrdbnet_arch import RRDBNet
from realesrgan import RealESRGANer
from realesrgan.archs.srvgg_arch import SRVGGNetCompact
from basicsr.archs.rrdbnet_arch import RRDBNet # noqa: F401
from realesrgan import RealESRGANer # noqa: F401
from realesrgan.archs.srvgg_arch import SRVGGNetCompact # noqa: F401
self.enable = True
self.scalers = []
scalers = self.load_models(path)
@ -73,7 +73,7 @@ class UpscalerRealESRGAN(Upscaler):
return None
if info.local_data_path.startswith("http"):
info.local_data_path = load_file_from_url(url=info.data_path, model_dir=self.model_path, progress=True)
info.local_data_path = load_file_from_url(url=info.data_path, model_dir=self.model_download_path, progress=True)
return info
except Exception as e:
@ -134,6 +134,6 @@ def get_realesrgan_models(scaler):
),
]
return models
except Exception as e:
except Exception:
print("Error making Real-ESRGAN models list:", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)

6
modules/safe.py
View File

@ -95,16 +95,16 @@ def check_pt(filename, extra_handler):
except zipfile.BadZipfile:
# if it's not a zip file, it's an olf pytorch format, with five objects written to pickle
# if it's not a zip file, it's an old pytorch format, with five objects written to pickle
with open(filename, "rb") as file:
unpickler = RestrictedUnpickler(file)
unpickler.extra_handler = extra_handler
for i in range(5):
for _ in range(5):
unpickler.load()
def load(filename, *args, **kwargs):
return load_with_extra(filename, extra_handler=global_extra_handler, *args, **kwargs)
return load_with_extra(filename, *args, extra_handler=global_extra_handler, **kwargs)
def load_with_extra(filename, extra_handler=None, *args, **kwargs):

67
modules/script_callbacks.py
View File

@ -32,27 +32,42 @@ class CFGDenoiserParams:
def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps, text_cond, text_uncond):
self.x = x
"""Latent image representation in the process of being denoised"""
self.image_cond = image_cond
"""Conditioning image"""
self.sigma = sigma
"""Current sigma noise step value"""
self.sampling_step = sampling_step
"""Current Sampling step number"""
self.total_sampling_steps = total_sampling_steps
"""Total number of sampling steps planned"""
self.text_cond = text_cond
""" Encoder hidden states of text conditioning from prompt"""
self.text_uncond = text_uncond
""" Encoder hidden states of text conditioning from negative prompt"""
class CFGDenoisedParams:
def __init__(self, x, sampling_step, total_sampling_steps, inner_model):
self.x = x
"""Latent image representation in the process of being denoised"""
self.sampling_step = sampling_step
"""Current Sampling step number"""
self.total_sampling_steps = total_sampling_steps
"""Total number of sampling steps planned"""
self.inner_model = inner_model
"""Inner model reference used for denoising"""
class AfterCFGCallbackParams:
def __init__(self, x, sampling_step, total_sampling_steps):
self.x = x
"""Latent image representation in the process of being denoised"""
@ -87,6 +102,7 @@ callback_map = dict(
callbacks_image_saved=[],
callbacks_cfg_denoiser=[],
callbacks_cfg_denoised=[],
callbacks_cfg_after_cfg=[],
callbacks_before_component=[],
callbacks_after_component=[],
callbacks_image_grid=[],
@ -94,6 +110,7 @@ callback_map = dict(
callbacks_script_unloaded=[],
callbacks_before_ui=[],
callbacks_on_reload=[],
callbacks_list_optimizers=[],
)
@ -186,6 +203,14 @@ def cfg_denoised_callback(params: CFGDenoisedParams):
report_exception(c, 'cfg_denoised_callback')
def cfg_after_cfg_callback(params: AfterCFGCallbackParams):
for c in callback_map['callbacks_cfg_after_cfg']:
try:
c.callback(params)
except Exception:
report_exception(c, 'cfg_after_cfg_callback')
def before_component_callback(component, **kwargs):
for c in callback_map['callbacks_before_component']:
try:
@ -234,13 +259,25 @@ def before_ui_callback():
report_exception(c, 'before_ui')
def list_optimizers_callback():
res = []
for c in callback_map['callbacks_list_optimizers']:
try:
c.callback(res)
except Exception:
report_exception(c, 'list_optimizers')
return res
def add_callback(callbacks, fun):
stack = [x for x in inspect.stack() if x.filename != __file__]
filename = stack[0].filename if len(stack) > 0 else 'unknown file'
callbacks.append(ScriptCallback(filename, fun))
def remove_current_script_callbacks():
stack = [x for x in inspect.stack() if x.filename != __file__]
filename = stack[0].filename if len(stack) > 0 else 'unknown file'
@ -332,6 +369,14 @@ def on_cfg_denoised(callback):
add_callback(callback_map['callbacks_cfg_denoised'], callback)
def on_cfg_after_cfg(callback):
"""register a function to be called in the kdiffussion cfg_denoiser method after cfg calculations are completed.
The callback is called with one argument:
- params: AfterCFGCallbackParams - parameters to be passed to the script for post-processing after cfg calculation.
"""
add_callback(callback_map['callbacks_cfg_after_cfg'], callback)
def on_before_component(callback):
"""register a function to be called before a component is created.
The callback is called with arguments:
@ -377,3 +422,11 @@ def on_before_ui(callback):
"""register a function to be called before the UI is created."""
add_callback(callback_map['callbacks_before_ui'], callback)
def on_list_optimizers(callback):
"""register a function to be called when UI is making a list of cross attention optimization options.
The function will be called with one argument, a list, and shall add objects of type modules.sd_hijack_optimizations.SdOptimization
to it."""
add_callback(callback_map['callbacks_list_optimizers'], callback)

1
modules/script_loading.py
View File

@ -2,7 +2,6 @@ import os
import sys
import traceback
import importlib.util
from types import ModuleType
def load_module(path):

60
modules/scripts.py
View File

@ -17,6 +17,9 @@ class PostprocessImageArgs:
class Script:
name = None
"""script's internal name derived from title"""
filename = None
args_from = None
args_to = None
@ -25,8 +28,8 @@ class Script:
is_txt2img = False
is_img2img = False
"""A gr.Group component that has all script's UI inside it"""
group = None
"""A gr.Group component that has all script's UI inside it"""
infotext_fields = None
"""if set in ui(), this is a list of pairs of gradio component + text; the text will be used when
@ -38,6 +41,9 @@ class Script:
various "Send to <X>" buttons when clicked
"""
api_info = None
"""Generated value of type modules.api.models.ScriptInfo with information about the script for API"""
def title(self):
"""this function should return the title of the script. This is what will be displayed in the dropdown menu."""
@ -231,7 +237,7 @@ def load_scripts():
syspath = sys.path
def register_scripts_from_module(module):
for key, script_class in module.__dict__.items():
for script_class in module.__dict__.values():
if type(script_class) != type:
continue
@ -265,6 +271,12 @@ def load_scripts():
sys.path = syspath
current_basedir = paths.script_path
global scripts_txt2img, scripts_img2img, scripts_postproc
scripts_txt2img = ScriptRunner()
scripts_img2img = ScriptRunner()
scripts_postproc = scripts_postprocessing.ScriptPostprocessingRunner()
def wrap_call(func, filename, funcname, *args, default=None, **kwargs):
try:
@ -295,9 +307,9 @@ class ScriptRunner:
auto_processing_scripts = scripts_auto_postprocessing.create_auto_preprocessing_script_data()
for script_class, path, basedir, script_module in auto_processing_scripts + scripts_data:
script = script_class()
script.filename = path
for script_data in auto_processing_scripts + scripts_data:
script = script_data.script_class()
script.filename = script_data.path
script.is_txt2img = not is_img2img
script.is_img2img = is_img2img
@ -313,6 +325,8 @@ class ScriptRunner:
self.selectable_scripts.append(script)
def setup_ui(self):
import modules.api.models as api_models
self.titles = [wrap_call(script.title, script.filename, "title") or f"{script.filename} [error]" for script in self.selectable_scripts]
inputs = [None]
@ -327,9 +341,28 @@ class ScriptRunner:
if controls is None:
return
script.name = wrap_call(script.title, script.filename, "title", default=script.filename).lower()
api_args = []
for control in controls:
control.custom_script_source = os.path.basename(script.filename)
arg_info = api_models.ScriptArg(label=control.label or "")
for field in ("value", "minimum", "maximum", "step", "choices"):
v = getattr(control, field, None)
if v is not None:
setattr(arg_info, field, v)
api_args.append(arg_info)
script.api_info = api_models.ScriptInfo(
name=script.name,
is_img2img=script.is_img2img,
is_alwayson=script.alwayson,
args=api_args,
)
if script.infotext_fields is not None:
self.infotext_fields += script.infotext_fields
@ -492,7 +525,7 @@ class ScriptRunner:
module = script_loading.load_module(script.filename)
cache[filename] = module
for key, script_class in module.__dict__.items():
for script_class in module.__dict__.values():
if type(script_class) == type and issubclass(script_class, Script):
self.scripts[si] = script_class()
self.scripts[si].filename = filename
@ -500,9 +533,9 @@ class ScriptRunner:
self.scripts[si].args_to = args_to
scripts_txt2img = ScriptRunner()
scripts_img2img = ScriptRunner()
scripts_postproc = scripts_postprocessing.ScriptPostprocessingRunner()
scripts_txt2img: ScriptRunner = None
scripts_img2img: ScriptRunner = None
scripts_postproc: scripts_postprocessing.ScriptPostprocessingRunner = None
scripts_current: ScriptRunner = None
@ -512,14 +545,7 @@ def reload_script_body_only():
scripts_img2img.reload_sources(cache)
def reload_scripts():
global scripts_txt2img, scripts_img2img, scripts_postproc
load_scripts()
scripts_txt2img = ScriptRunner()
scripts_img2img = ScriptRunner()
scripts_postproc = scripts_postprocessing.ScriptPostprocessingRunner()
reload_scripts = load_scripts # compatibility alias
def add_classes_to_gradio_component(comp):

2
modules/scripts_auto_postprocessing.py
View File

@ -17,7 +17,7 @@ class ScriptPostprocessingForMainUI(scripts.Script):
return self.postprocessing_controls.values()
def postprocess_image(self, p, script_pp, *args):
args_dict = {k: v for k, v in zip(self.postprocessing_controls, args)}
args_dict = dict(zip(self.postprocessing_controls, args))
pp = scripts_postprocessing.PostprocessedImage(script_pp.image)
pp.info = {}

8
modules/scripts_postprocessing.py
View File

@ -66,9 +66,9 @@ class ScriptPostprocessingRunner:
def initialize_scripts(self, scripts_data):
self.scripts = []
for script_class, path, basedir, script_module in scripts_data:
script: ScriptPostprocessing = script_class()
script.filename = path
for script_data in scripts_data:
script: ScriptPostprocessing = script_data.script_class()
script.filename = script_data.path
if script.name == "Simple Upscale":
continue
@ -124,7 +124,7 @@ class ScriptPostprocessingRunner:
script_args = args[script.args_from:script.args_to]
process_args = {}
for (name, component), value in zip(script.controls.items(), script_args):
for (name, _component), value in zip(script.controls.items(), script_args):
process_args[name] = value
script.process(pp, **process_args)

2
modules/sd_disable_initialization.py
View File

@ -61,7 +61,7 @@ class DisableInitialization:
if res is None:
res = original(url, *args, local_files_only=False, **kwargs)
return res
except Exception as e:
except Exception:
return original(url, *args, local_files_only=False, **kwargs)
def transformers_utils_hub_get_from_cache(url, *args, local_files_only=False, **kwargs):

113
modules/sd_hijack.py
View File

@ -3,7 +3,7 @@ from torch.nn.functional import silu
from types import MethodType
import modules.textual_inversion.textual_inversion
from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint
from modules import devices, sd_hijack_optimizations, shared, script_callbacks, errors
from modules.hypernetworks import hypernetwork
from modules.shared import cmd_opts
from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr
@ -28,57 +28,62 @@ ldm.modules.attention.BasicTransformerBlock.ATTENTION_MODES["softmax-xformers"]
ldm.modules.attention.print = lambda *args: None
ldm.modules.diffusionmodules.model.print = lambda *args: None
optimizers = []
current_optimizer: sd_hijack_optimizations.SdOptimization = None
def list_optimizers():
new_optimizers = script_callbacks.list_optimizers_callback()
new_optimizers = [x for x in new_optimizers if x.is_available()]
new_optimizers = sorted(new_optimizers, key=lambda x: x.priority, reverse=True)
optimizers.clear()
optimizers.extend(new_optimizers)
def apply_optimizations():
global current_optimizer
undo_optimizations()
if len(optimizers) == 0:
# a script can access the model very early, and optimizations would not be filled by then
current_optimizer = None
return ''
ldm.modules.diffusionmodules.model.nonlinearity = silu
ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th
optimization_method = None
can_use_sdp = hasattr(torch.nn.functional, "scaled_dot_product_attention") and callable(getattr(torch.nn.functional, "scaled_dot_product_attention")) # not everyone has torch 2.x to use sdp
if current_optimizer is not None:
current_optimizer.undo()
current_optimizer = None
if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):
print("Applying xformers cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
optimization_method = 'xformers'
elif cmd_opts.opt_sdp_no_mem_attention and can_use_sdp:
print("Applying scaled dot product cross attention optimization (without memory efficient attention).")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.scaled_dot_product_no_mem_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.sdp_no_mem_attnblock_forward
optimization_method = 'sdp-no-mem'
elif cmd_opts.opt_sdp_attention and can_use_sdp:
print("Applying scaled dot product cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.scaled_dot_product_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.sdp_attnblock_forward
optimization_method = 'sdp'
elif cmd_opts.opt_sub_quad_attention:
print("Applying sub-quadratic cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.sub_quad_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.sub_quad_attnblock_forward
optimization_method = 'sub-quadratic'
elif cmd_opts.opt_split_attention_v1:
print("Applying v1 cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
optimization_method = 'V1'
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention_invokeai or not cmd_opts.opt_split_attention and not torch.cuda.is_available()):
print("Applying cross attention optimization (InvokeAI).")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_invokeAI
optimization_method = 'InvokeAI'
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
print("Applying cross attention optimization (Doggettx).")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
optimization_method = 'Doggettx'
selection = shared.opts.cross_attention_optimization
if selection == "Automatic" and len(optimizers) > 0:
matching_optimizer = next(iter([x for x in optimizers if x.cmd_opt and getattr(shared.cmd_opts, x.cmd_opt, False)]), optimizers[0])
else:
matching_optimizer = next(iter([x for x in optimizers if x.title() == selection]), None)
return optimization_method
if selection == "None":
matching_optimizer = None
elif matching_optimizer is None:
matching_optimizer = optimizers[0]
if matching_optimizer is not None:
print(f"Applying optimization: {matching_optimizer.name}... ", end='')
matching_optimizer.apply()
print("done.")
current_optimizer = matching_optimizer
return current_optimizer.name
else:
return ''
def undo_optimizations():
ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
ldm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity
ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
@ -92,12 +97,12 @@ def fix_checkpoint():
def weighted_loss(sd_model, pred, target, mean=True):
#Calculate the weight normally, but ignore the mean
loss = sd_model._old_get_loss(pred, target, mean=False)
#Check if we have weights available
weight = getattr(sd_model, '_custom_loss_weight', None)
if weight is not None:
loss *= weight
#Return the loss, as mean if specified
return loss.mean() if mean else loss
@ -105,7 +110,7 @@ def weighted_forward(sd_model, x, c, w, *args, **kwargs):
try:
#Temporarily append weights to a place accessible during loss calc
sd_model._custom_loss_weight = w
#Replace 'get_loss' with a weight-aware one. Otherwise we need to reimplement 'forward' completely
#Keep 'get_loss', but don't overwrite the previous old_get_loss if it's already set
if not hasattr(sd_model, '_old_get_loss'):
@ -118,9 +123,9 @@ def weighted_forward(sd_model, x, c, w, *args, **kwargs):
try:
#Delete temporary weights if appended
del sd_model._custom_loss_weight
except AttributeError as e:
except AttributeError:
pass
#If we have an old loss function, reset the loss function to the original one
if hasattr(sd_model, '_old_get_loss'):
sd_model.get_loss = sd_model._old_get_loss
@ -133,7 +138,7 @@ def apply_weighted_forward(sd_model):
def undo_weighted_forward(sd_model):
try:
del sd_model.weighted_forward
except AttributeError as e:
except AttributeError:
pass
@ -150,6 +155,13 @@ class StableDiffusionModelHijack:
def __init__(self):
self.embedding_db.add_embedding_dir(cmd_opts.embeddings_dir)
def apply_optimizations(self):
try:
self.optimization_method = apply_optimizations()
except Exception as e:
errors.display(e, "applying cross attention optimization")
undo_optimizations()
def hijack(self, m):
if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
model_embeddings = m.cond_stage_model.roberta.embeddings
@ -169,7 +181,7 @@ class StableDiffusionModelHijack:
if m.cond_stage_key == "edit":
sd_hijack_unet.hijack_ddpm_edit()
self.optimization_method = apply_optimizations()
self.apply_optimizations()
self.clip = m.cond_stage_model
@ -184,7 +196,7 @@ class StableDiffusionModelHijack:
def undo_hijack(self, m):
if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
m.cond_stage_model = m.cond_stage_model.wrapped
m.cond_stage_model = m.cond_stage_model.wrapped
elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
m.cond_stage_model = m.cond_stage_model.wrapped
@ -216,10 +228,17 @@ class StableDiffusionModelHijack:
self.comments = []
def get_prompt_lengths(self, text):
if self.clip is None:
return "-", "-"
_, token_count = self.clip.process_texts([text])
return token_count, self.clip.get_target_prompt_token_count(token_count)
def redo_hijack(self, m):
self.undo_hijack(m)
self.hijack(m)
class EmbeddingsWithFixes(torch.nn.Module):
def __init__(self, wrapped, embeddings):

2
modules/sd_hijack_clip.py
View File

@ -223,7 +223,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module):
self.hijack.fixes = [x.fixes for x in batch_chunk]
for fixes in self.hijack.fixes:
for position, embedding in fixes:
for _position, embedding in fixes:
used_embeddings[embedding.name] = embedding
z = self.process_tokens(tokens, multipliers)

10
modules/sd_hijack_inpainting.py
View File

@ -1,16 +1,10 @@
import os
import torch
from einops import repeat
from omegaconf import ListConfig
import ldm.models.diffusion.ddpm
import ldm.models.diffusion.ddim
import ldm.models.diffusion.plms
from ldm.models.diffusion.ddpm import LatentDiffusion
from ldm.models.diffusion.plms import PLMSSampler
from ldm.models.diffusion.ddim import DDIMSampler, noise_like
from ldm.models.diffusion.ddim import noise_like
from ldm.models.diffusion.sampling_util import norm_thresholding
@ -29,7 +23,7 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F
if isinstance(c, dict):
assert isinstance(unconditional_conditioning, dict)
c_in = dict()
c_in = {}
for k in c:
if isinstance(c[k], list):
c_in[k] = [

7
modules/sd_hijack_ip2p.py
View File

@ -1,8 +1,5 @@
import collections
import os.path
import sys
import gc
import time
def should_hijack_ip2p(checkpoint_info):
from modules import sd_models_config
@ -10,4 +7,4 @@ def should_hijack_ip2p(checkpoint_info):
ckpt_basename = os.path.basename(checkpoint_info.filename).lower()
cfg_basename = os.path.basename(sd_models_config.find_checkpoint_config_near_filename(checkpoint_info)).lower()
return "pix2pix" in ckpt_basename and not "pix2pix" in cfg_basename
return "pix2pix" in ckpt_basename and "pix2pix" not in cfg_basename

173
modules/sd_hijack_optimizations.py
View File

@ -1,3 +1,4 @@
from __future__ import annotations
import math
import sys
import traceback
@ -9,10 +10,129 @@ from torch import einsum
from ldm.util import default
from einops import rearrange
from modules import shared, errors, devices
from modules import shared, errors, devices, sub_quadratic_attention
from modules.hypernetworks import hypernetwork
from .sub_quadratic_attention import efficient_dot_product_attention
import ldm.modules.attention
import ldm.modules.diffusionmodules.model
diffusionmodules_model_AttnBlock_forward = ldm.modules.diffusionmodules.model.AttnBlock.forward
class SdOptimization:
name: str = None
label: str | None = None
cmd_opt: str | None = None
priority: int = 0
def title(self):
if self.label is None:
return self.name
return f"{self.name} - {self.label}"
def is_available(self):
return True
def apply(self):
pass
def undo(self):
ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
class SdOptimizationXformers(SdOptimization):
name = "xformers"
cmd_opt = "xformers"
priority = 100
def is_available(self):
return shared.cmd_opts.force_enable_xformers or (shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0))
def apply(self):
ldm.modules.attention.CrossAttention.forward = xformers_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = xformers_attnblock_forward
class SdOptimizationSdpNoMem(SdOptimization):
name = "sdp-no-mem"
label = "scaled dot product without memory efficient attention"
cmd_opt = "opt_sdp_no_mem_attention"
priority = 90
def is_available(self):
return hasattr(torch.nn.functional, "scaled_dot_product_attention") and callable(torch.nn.functional.scaled_dot_product_attention)
def apply(self):
ldm.modules.attention.CrossAttention.forward = scaled_dot_product_no_mem_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sdp_no_mem_attnblock_forward
class SdOptimizationSdp(SdOptimizationSdpNoMem):
name = "sdp"
label = "scaled dot product"
cmd_opt = "opt_sdp_attention"
priority = 80
def apply(self):
ldm.modules.attention.CrossAttention.forward = scaled_dot_product_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sdp_attnblock_forward
class SdOptimizationSubQuad(SdOptimization):
name = "sub-quadratic"
cmd_opt = "opt_sub_quad_attention"
priority = 10
def apply(self):
ldm.modules.attention.CrossAttention.forward = sub_quad_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sub_quad_attnblock_forward
class SdOptimizationV1(SdOptimization):
name = "V1"
label = "original v1"
cmd_opt = "opt_split_attention_v1"
priority = 10
def apply(self):
ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward_v1
class SdOptimizationInvokeAI(SdOptimization):
name = "InvokeAI"
cmd_opt = "opt_split_attention_invokeai"
@property
def priority(self):
return 1000 if not torch.cuda.is_available() else 10
def apply(self):
ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward_invokeAI
class SdOptimizationDoggettx(SdOptimization):
name = "Doggettx"
cmd_opt = "opt_split_attention"
priority = 20
def apply(self):
ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = cross_attention_attnblock_forward
def list_optimizers(res):
res.extend([
SdOptimizationXformers(),
SdOptimizationSdpNoMem(),
SdOptimizationSdp(),
SdOptimizationSubQuad(),
SdOptimizationV1(),
SdOptimizationInvokeAI(),
SdOptimizationDoggettx(),
])
if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers:
@ -49,7 +169,7 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
v_in = self.to_v(context_v)
del context, context_k, context_v, x
q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q_in, k_in, v_in))
q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q_in, k_in, v_in))
del q_in, k_in, v_in
dtype = q.dtype
@ -62,10 +182,10 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
end = i + 2
s1 = einsum('b i d, b j d -> b i j', q[i:end], k[i:end])
s1 *= self.scale
s2 = s1.softmax(dim=-1)
del s1
r1[i:end] = einsum('b i j, b j d -> b i d', s2, v[i:end])
del s2
del q, k, v
@ -95,43 +215,43 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
with devices.without_autocast(disable=not shared.opts.upcast_attn):
k_in = k_in * self.scale
del context, x
q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q_in, k_in, v_in))
q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q_in, k_in, v_in))
del q_in, k_in, v_in
r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
mem_free_total = get_available_vram()
gb = 1024 ** 3
tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * q.element_size()
modifier = 3 if q.element_size() == 2 else 2.5
mem_required = tensor_size * modifier
steps = 1
if mem_required > mem_free_total:
steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2)))
# print(f"Expected tensor size:{tensor_size/gb:0.1f}GB, cuda free:{mem_free_cuda/gb:0.1f}GB "
# f"torch free:{mem_free_torch/gb:0.1f} total:{mem_free_total/gb:0.1f} steps:{steps}")
if steps > 64:
max_res = math.floor(math.sqrt(math.sqrt(mem_free_total / 2.5)) / 8) * 64
raise RuntimeError(f'Not enough memory, use lower resolution (max approx. {max_res}x{max_res}). '
f'Need: {mem_required / 64 / gb:0.1f}GB free, Have:{mem_free_total / gb:0.1f}GB free')
slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
for i in range(0, q.shape[1], slice_size):
end = i + slice_size
s1 = einsum('b i d, b j d -> b i j', q[:, i:end], k)
s2 = s1.softmax(dim=-1, dtype=q.dtype)
del s1
r1[:, i:end] = einsum('b i j, b j d -> b i d', s2, v)
del s2
del q, k, v
r1 = r1.to(dtype)
@ -228,8 +348,8 @@ def split_cross_attention_forward_invokeAI(self, x, context=None, mask=None):
with devices.without_autocast(disable=not shared.opts.upcast_attn):
k = k * self.scale
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))
r = einsum_op(q, k, v)
r = r.to(dtype)
return self.to_out(rearrange(r, '(b h) n d -> b n (h d)', h=h))
@ -296,11 +416,10 @@ def sub_quad_attention(q, k, v, q_chunk_size=1024, kv_chunk_size=None, kv_chunk_
if chunk_threshold_bytes is not None and qk_matmul_size_bytes <= chunk_threshold_bytes:
# the big matmul fits into our memory limit; do everything in 1 chunk,
# i.e. send it down the unchunked fast-path
query_chunk_size = q_tokens
kv_chunk_size = k_tokens
with devices.without_autocast(disable=q.dtype == v.dtype):
return efficient_dot_product_attention(
return sub_quadratic_attention.efficient_dot_product_attention(
q,
k,
v,
@ -335,7 +454,7 @@ def xformers_attention_forward(self, x, context=None, mask=None):
k_in = self.to_k(context_k)
v_in = self.to_v(context_v)
q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b n h d', h=h), (q_in, k_in, v_in))
q, k, v = (rearrange(t, 'b n (h d) -> b n h d', h=h) for t in (q_in, k_in, v_in))
del q_in, k_in, v_in
dtype = q.dtype
@ -370,7 +489,7 @@ def scaled_dot_product_attention_forward(self, x, context=None, mask=None):
q = q_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
k = k_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
v = v_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
del q_in, k_in, v_in
dtype = q.dtype
@ -452,7 +571,7 @@ def cross_attention_attnblock_forward(self, x):
h3 += x
return h3
def xformers_attnblock_forward(self, x):
try:
h_ = x
@ -461,7 +580,7 @@ def xformers_attnblock_forward(self, x):
k = self.k(h_)
v = self.v(h_)
b, c, h, w = q.shape
q, k, v = map(lambda t: rearrange(t, 'b c h w -> b (h w) c'), (q, k, v))
q, k, v = (rearrange(t, 'b c h w -> b (h w) c') for t in (q, k, v))
dtype = q.dtype
if shared.opts.upcast_attn:
q, k = q.float(), k.float()
@ -483,7 +602,7 @@ def sdp_attnblock_forward(self, x):
k = self.k(h_)
v = self.v(h_)
b, c, h, w = q.shape
q, k, v = map(lambda t: rearrange(t, 'b c h w -> b (h w) c'), (q, k, v))
q, k, v = (rearrange(t, 'b c h w -> b (h w) c') for t in (q, k, v))
dtype = q.dtype
if shared.opts.upcast_attn:
q, k = q.float(), k.float()
@ -507,7 +626,7 @@ def sub_quad_attnblock_forward(self, x):
k = self.k(h_)
v = self.v(h_)
b, c, h, w = q.shape
q, k, v = map(lambda t: rearrange(t, 'b c h w -> b (h w) c'), (q, k, v))
q, k, v = (rearrange(t, 'b c h w -> b (h w) c') for t in (q, k, v))
q = q.contiguous()
k = k.contiguous()
v = v.contiguous()

2
modules/sd_hijack_xlmr.py
View File

@ -1,8 +1,6 @@
import open_clip.tokenizer
import torch
from modules import sd_hijack_clip, devices
from modules.shared import opts
class FrozenXLMREmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords):

53
modules/sd_models.py
View File

@ -15,9 +15,9 @@ import ldm.modules.midas as midas
from ldm.util import instantiate_from_config
from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config
from modules.paths import models_path
from modules.sd_hijack_inpainting import do_inpainting_hijack
from modules.timer import Timer
import tomesd
model_dir = "Stable-diffusion"
model_path = os.path.abspath(os.path.join(paths.models_path, model_dir))
@ -87,8 +87,7 @@ class CheckpointInfo:
try:
# this silences the annoying "Some weights of the model checkpoint were not used when initializing..." message at start.
from transformers import logging, CLIPModel
from transformers import logging, CLIPModel # noqa: F401
logging.set_verbosity_error()
except Exception:
@ -99,7 +98,6 @@ def setup_model():
if not os.path.exists(model_path):
os.makedirs(model_path)
list_models()
enable_midas_autodownload()
@ -167,7 +165,7 @@ def model_hash(filename):
def select_checkpoint():
model_checkpoint = shared.opts.sd_model_checkpoint
checkpoint_info = checkpoint_alisases.get(model_checkpoint, None)
if checkpoint_info is not None:
return checkpoint_info
@ -239,7 +237,7 @@ def read_metadata_from_safetensors(filename):
if isinstance(v, str) and v[0:1] == '{':
try:
res[k] = json.loads(v)
except Exception as e:
except Exception:
pass
return res
@ -374,7 +372,7 @@ def enable_midas_autodownload():
if not os.path.exists(path):
if not os.path.exists(midas_path):
mkdir(midas_path)
print(f"Downloading midas model weights for {model_type} to {path}")
request.urlretrieve(midas_urls[model_type], path)
print(f"{model_type} downloaded")
@ -410,11 +408,18 @@ sd2_clip_weight = 'cond_stage_model.model.transformer.resblocks.0.attn.in_proj_w
class SdModelData:
def __init__(self):
self.sd_model = None
self.was_loaded_at_least_once = False
self.lock = threading.Lock()
def get_sd_model(self):
if self.was_loaded_at_least_once:
return self.sd_model
if self.sd_model is None:
with self.lock:
if self.sd_model is not None or self.was_loaded_at_least_once:
return self.sd_model
try:
load_model()
except Exception as e:
@ -467,7 +472,7 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None):
try:
with sd_disable_initialization.DisableInitialization(disable_clip=clip_is_included_into_sd):
sd_model = instantiate_from_config(sd_config.model)
except Exception as e:
except Exception:
pass
if sd_model is None:
@ -493,6 +498,7 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None):
sd_model.eval()
model_data.sd_model = sd_model
model_data.was_loaded_at_least_once = True
sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True) # Reload embeddings after model load as they may or may not fit the model
@ -538,13 +544,12 @@ def reload_model_weights(sd_model=None, info=None):
if sd_model is None or checkpoint_config != sd_model.used_config:
del sd_model
checkpoints_loaded.clear()
load_model(checkpoint_info, already_loaded_state_dict=state_dict)
return model_data.sd_model
try:
load_model_weights(sd_model, checkpoint_info, state_dict, timer)
except Exception as e:
except Exception:
print("Failed to load checkpoint, restoring previous")
load_model_weights(sd_model, current_checkpoint_info, None, timer)
raise
@ -565,7 +570,7 @@ def reload_model_weights(sd_model=None, info=None):
def unload_model_weights(sd_model=None, info=None):
from modules import lowvram, devices, sd_hijack
from modules import devices, sd_hijack
timer = Timer()
if model_data.sd_model:
@ -580,3 +585,29 @@ def unload_model_weights(sd_model=None, info=None):
print(f"Unloaded weights {timer.summary()}.")
return sd_model
def apply_token_merging(sd_model, token_merging_ratio):
"""
Applies speed and memory optimizations from tomesd.
"""
current_token_merging_ratio = getattr(sd_model, 'applied_token_merged_ratio', 0)
if current_token_merging_ratio == token_merging_ratio:
return
if current_token_merging_ratio > 0:
tomesd.remove_patch(sd_model)
if token_merging_ratio > 0:
tomesd.apply_patch(
sd_model,
ratio=token_merging_ratio,
use_rand=False, # can cause issues with some samplers
merge_attn=True,
merge_crossattn=False,
merge_mlp=False
)
sd_model.applied_token_merged_ratio = token_merging_ratio

1
modules/sd_models_config.py
View File

@ -1,4 +1,3 @@
import re
import os
import torch

Some files were not shown because too many files have changed in this diff Show More