diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index 7d435297..3a8b9953 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -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: diff --git a/.github/workflows/on_pull_request.yaml b/.github/workflows/on_pull_request.yaml index a168be5b..d42965b1 100644 --- a/.github/workflows/on_pull_request.yaml +++ b/.github/workflows/on_pull_request.yaml @@ -18,22 +18,29 @@ jobs: 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 . + +# The rest are currently disabled pending fixing of e.g. installing the torch dependency. + +# - 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') diff --git a/.github/workflows/run_tests.yaml b/.github/workflows/run_tests.yaml index 9a0b8d22..0708398b 100644 --- a/.github/workflows/run_tests.yaml +++ b/.github/workflows/run_tests.yaml @@ -17,8 +17,14 @@ jobs: cache: pip cache-dependency-path: | **/requirements*txt + launch.py - name: Run tests run: python launch.py --tests test --no-half --disable-opt-split-attention --use-cpu all --skip-torch-cuda-test + 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" - name: Upload main app stdout-stderr uses: actions/upload-artifact@v3 if: always() diff --git a/.gitignore b/.gitignore index 0b1d17ca..7328401f 100644 --- a/.gitignore +++ b/.gitignore @@ -32,4 +32,5 @@ notification.mp3 /extensions /test/stdout.txt /test/stderr.txt -/cache.json +/cache.json* +/config_states/ diff --git a/CHANGELOG.md b/CHANGELOG.md new file mode 100644 index 00000000..8cf444ca --- /dev/null +++ b/CHANGELOG.md @@ -0,0 +1,120 @@ +## 1.2.1 + +### Features: + * 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 + * fix upscalers disappearing after the user reloads UI + * 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' + +## 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) + * 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 + * 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 + * 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 + +### Bug Fixes: + * 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 + * 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 + + +## 1.1.1 +### Bug Fixes: + * fix an error that prevents running webui on torch<2.0 without --disable-safe-unpickle + +## 1.1.0 +### Features: + * switch to torch 2.0.0 (except for AMD GPUs) + * visual improvements to custom code scripts + * 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 + * 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 + * embed model merge metadata in .safetensors file + * extension settings backup/restore feature #9169 + * add "resize by" and "resize to" tabs to img2img + * add option "keep original size" to textual inversion images preprocess + * image viewer scrolling via analog stick + * 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 + * 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) + * 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 + +### Extensions: + * Add reload callback + * add is_hr_pass field for processing + +### Bug Fixes: + * fix broken batch image processing on 'Extras/Batch Process' tab + * add "None" option to extra networks dropdowns + * fix FileExistsError for CLIP Interrogator + * fix /sdapi/v1/txt2img endpoint not working on Linux #9319 + * fix disappearing live previews and progressbar during slow tasks + * fix fullscreen image view not working properly in some cases + * prevent alwayson_scripts args param resizing script_arg list when they are inserted in it + * fix prompt schedule for second order samplers + * fix image mask/composite for weird resolutions #9628 + * use correct images for previews when using AND (see #9491) + * 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 + +## 1.0.0 + * everything diff --git a/README.md b/README.md index b67e2296..79089e52 100644 --- a/README.md +++ b/README.md @@ -99,8 +99,14 @@ 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/windows/), checking "Add Python to PATH". +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). 3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`. 4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user. @@ -115,11 +121,12 @@ sudo dnf install wget git python3 # Arch-based: sudo pacman -S wget git python3 ``` -2. To install in `/home/$(whoami)/stable-diffusion-webui/`, run: +2. Navigate to the directory you would like the webui to be installed and execute the following command: ```bash bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh) ``` 3. Run `webui.sh`. +4. Check `webui-user.sh` for options. ### Installation on Apple Silicon Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon). @@ -157,5 +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) \ No newline at end of file +- (You) diff --git a/environment-wsl2.yaml b/environment-wsl2.yaml index f8872750..0c4ae680 100644 --- a/environment-wsl2.yaml +++ b/environment-wsl2.yaml @@ -4,8 +4,8 @@ channels: - defaults dependencies: - python=3.10 - - pip=22.2.2 - - cudatoolkit=11.3 - - pytorch=1.12.1 - - torchvision=0.13.1 - - numpy=1.23.1 \ No newline at end of file + - pip=23.0 + - cudatoolkit=11.8 + - pytorch=2.0 + - torchvision=0.15 + - numpy=1.23 diff --git a/extensions-builtin/LDSR/ldsr_model_arch.py b/extensions-builtin/LDSR/ldsr_model_arch.py index bc11cc6e..7f450086 100644 --- a/extensions-builtin/LDSR/ldsr_model_arch.py +++ b/extensions-builtin/LDSR/ldsr_model_arch.py @@ -88,7 +88,7 @@ class LDSR: x_t = None logs = None - for n in range(n_runs): + for _ in range(n_runs): if custom_shape is not None: x_t = torch.randn(1, custom_shape[1], custom_shape[2], custom_shape[3]).to(model.device) x_t = repeat(x_t, '1 c h w -> b c h w', b=custom_shape[0]) @@ -110,7 +110,6 @@ class LDSR: diffusion_steps = int(steps) eta = 1.0 - down_sample_method = 'Lanczos' gc.collect() if torch.cuda.is_available: @@ -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 diff --git a/extensions-builtin/LDSR/scripts/ldsr_model.py b/extensions-builtin/LDSR/scripts/ldsr_model.py index b8cff29b..fbbe9005 100644 --- a/extensions-builtin/LDSR/scripts/ldsr_model.py +++ b/extensions-builtin/LDSR/scripts/ldsr_model.py @@ -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): @@ -25,22 +26,28 @@ class UpscalerLDSR(Upscaler): yaml_path = os.path.join(self.model_path, "project.yaml") old_model_path = os.path.join(self.model_path, "model.pth") new_model_path = os.path.join(self.model_path, "model.ckpt") - safetensors_model_path = os.path.join(self.model_path, "model.safetensors") + + local_model_paths = self.find_models(ext_filter=[".ckpt", ".safetensors"]) + local_ckpt_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("model.ckpt")]), None) + local_safetensors_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("model.safetensors")]), None) + local_yaml_path = next(iter([local_model for local_model in local_model_paths if local_model.endswith("project.yaml")]), None) + if os.path.exists(yaml_path): statinfo = os.stat(yaml_path) if statinfo.st_size >= 10485760: print("Removing invalid LDSR YAML file.") os.remove(yaml_path) + if os.path.exists(old_model_path): print("Renaming model from model.pth to model.ckpt") os.rename(old_model_path, new_model_path) - if os.path.exists(safetensors_model_path): - model = safetensors_model_path + + if local_safetensors_path is not None and os.path.exists(local_safetensors_path): + model = local_safetensors_path else: - model = load_file_from_url(url=self.model_url, model_dir=self.model_path, - file_name="model.ckpt", progress=True) - yaml = load_file_from_url(url=self.yaml_url, model_dir=self.model_path, - file_name="project.yaml", 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_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) try: return LDSR(model, yaml) diff --git a/extensions-builtin/LDSR/sd_hijack_autoencoder.py b/extensions-builtin/LDSR/sd_hijack_autoencoder.py index 8e03c7f8..81c5101b 100644 --- a/extensions-builtin/LDSR/sd_hijack_autoencoder.py +++ b/extensions-builtin/LDSR/sd_hijack_autoencoder.py @@ -1,16 +1,21 @@ # The content of this file comes from the ldm/models/autoencoder.py file of the compvis/stable-diffusion repo # The VQModel & VQModelInterface were subsequently removed from ldm/models/autoencoder.py when we moved to the stability-ai/stablediffusion repo # As the LDSR upscaler relies on VQModel & VQModelInterface, the hijack aims to put them back into the ldm.models.autoencoder - +import numpy as np import torch import pytorch_lightning as pl import torch.nn.functional as F from contextlib import contextmanager + +from 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 diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py index 5c0488e5..631a08ef 100644 --- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py +++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py @@ -48,7 +48,7 @@ class DDPMV1(pl.LightningModule): beta_schedule="linear", loss_type="l2", ckpt_path=None, - ignore_keys=[], + ignore_keys=None, load_only_unet=False, monitor="val/loss", use_ema=True, @@ -100,7 +100,7 @@ class DDPMV1(pl.LightningModule): if monitor is not None: self.monitor = monitor if ckpt_path is not None: - self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet) + self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [], only_model=load_only_unet) self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s) @@ -182,13 +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 diff --git a/extensions-builtin/Lora/extra_networks_lora.py b/extensions-builtin/Lora/extra_networks_lora.py index 6be6ef73..ccb249ac 100644 --- a/extensions-builtin/Lora/extra_networks_lora.py +++ b/extensions-builtin/Lora/extra_networks_lora.py @@ -1,6 +1,7 @@ from modules import extra_networks, shared import lora + class ExtraNetworkLora(extra_networks.ExtraNetwork): def __init__(self): super().__init__('lora') @@ -8,7 +9,7 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork): def activate(self, p, params_list): additional = shared.opts.sd_lora - if additional != "" and additional in lora.available_loras and len([x for x in params_list if x.items[0] == additional]) == 0: + if additional != "None" and additional in lora.available_loras and len([x for x in params_list if x.items[0] == additional]) == 0: p.all_prompts = [x + f"" for x in p.all_prompts] params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier])) diff --git a/extensions-builtin/Lora/lora.py b/extensions-builtin/Lora/lora.py index d3eb0d3b..1308c48b 100644 --- a/extensions-builtin/Lora/lora.py +++ b/extensions-builtin/Lora/lora.py @@ -1,10 +1,9 @@ -import glob import os import re import torch from typing import Union -from modules import shared, devices, sd_models, errors +from modules import shared, devices, sd_models, errors, scripts metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20} @@ -93,6 +92,7 @@ class LoraOnDisk: self.metadata = m 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) class LoraModule: @@ -132,6 +132,10 @@ def load_lora(name, filename): sd = sd_models.read_state_dict(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'): + assign_lora_names_to_compvis_modules(shared.sd_model) + keys_failed_to_match = {} is_sd2 = 'model_transformer_resblocks' in shared.sd_model.lora_layer_mapping @@ -165,12 +169,14 @@ def load_lora(name, filename): module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False) elif type(sd_module) == torch.nn.MultiheadAttention: module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False) - elif type(sd_module) == torch.nn.Conv2d: + elif type(sd_module) == torch.nn.Conv2d and weight.shape[2:] == (1, 1): module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False) + elif type(sd_module) == torch.nn.Conv2d and weight.shape[2:] == (3, 3): + module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (3, 3), bias=False) 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) @@ -182,7 +188,7 @@ 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}") @@ -199,11 +205,11 @@ def load_loras(names, multipliers=None): loaded_loras.clear() - loras_on_disk = [available_loras.get(name, None) for name in names] - if any([x is None for x in loras_on_disk]): + loras_on_disk = [available_lora_aliases.get(name, None) for name in names] + if any(x is None for x in loras_on_disk): list_available_loras() - loras_on_disk = [available_loras.get(name, None) for name in names] + loras_on_disk = [available_lora_aliases.get(name, None) for name in names] for i, name in enumerate(names): lora = already_loaded.get(name, None) @@ -211,7 +217,11 @@ def load_loras(names, multipliers=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: - lora = load_lora(name, lora_on_disk.filename) + try: + lora = load_lora(name, lora_on_disk.filename) + except Exception as e: + errors.display(e, f"loading Lora {lora_on_disk.filename}") + continue if lora is None: print(f"Couldn't find Lora with name {name}") @@ -228,6 +238,8 @@ def lora_calc_updown(lora, module, target): if up.shape[2:] == (1, 1) and down.shape[2:] == (1, 1): updown = (up.squeeze(2).squeeze(2) @ down.squeeze(2).squeeze(2)).unsqueeze(2).unsqueeze(3) + elif up.shape[2:] == (3, 3) or down.shape[2:] == (3, 3): + updown = torch.nn.functional.conv2d(down.permute(1, 0, 2, 3), up).permute(1, 0, 2, 3) else: updown = up @ down @@ -236,6 +248,19 @@ def lora_calc_updown(lora, module, target): return updown +def lora_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]): + weights_backup = getattr(self, "lora_weights_backup", None) + + if weights_backup is None: + return + + if isinstance(self, torch.nn.MultiheadAttention): + self.in_proj_weight.copy_(weights_backup[0]) + self.out_proj.weight.copy_(weights_backup[1]) + else: + self.weight.copy_(weights_backup) + + def lora_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]): """ Applies the currently selected set of Loras to the weights of torch layer self. @@ -260,12 +285,7 @@ def lora_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.Mu self.lora_weights_backup = weights_backup if current_names != wanted_names: - if weights_backup is not None: - if isinstance(self, torch.nn.MultiheadAttention): - self.in_proj_weight.copy_(weights_backup[0]) - self.out_proj.weight.copy_(weights_backup[1]) - else: - self.weight.copy_(weights_backup) + lora_restore_weights_from_backup(self) for lora in loaded_loras: module = lora.modules.get(lora_layer_name, None) @@ -293,15 +313,48 @@ 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): + """ + Old way of applying Lora by executing operations during layer's forward. + Stacking many loras this way results in big performance degradation. + """ + + if len(loaded_loras) == 0: + return original_forward(module, input) + + input = devices.cond_cast_unet(input) + + lora_restore_weights_from_backup(module) + lora_reset_cached_weight(module) + + res = original_forward(module, input) + + lora_layer_name = getattr(module, 'lora_layer_name', None) + for lora in loaded_loras: + module = lora.modules.get(lora_layer_name, None) + if module is None: + continue + + module.up.to(device=devices.device) + module.down.to(device=devices.device) + + res = res + module.up(module.down(input)) * lora.multiplier * (module.alpha / module.up.weight.shape[1] if module.alpha else 1.0) + + return res 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): + if shared.opts.lora_functional: + return lora_forward(self, input, torch.nn.Linear_forward_before_lora) + lora_apply_weights(self) return torch.nn.Linear_forward_before_lora(self, input) @@ -314,6 +367,9 @@ def lora_Linear_load_state_dict(self, *args, **kwargs): def lora_Conv2d_forward(self, input): + if shared.opts.lora_functional: + return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora) + lora_apply_weights(self) return torch.nn.Conv2d_forward_before_lora(self, input) @@ -339,24 +395,65 @@ def lora_MultiheadAttention_load_state_dict(self, *args, **kwargs): def list_available_loras(): available_loras.clear() + available_lora_aliases.clear() + forbidden_lora_aliases.clear() + forbidden_lora_aliases.update({"none": 1}) os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True) - candidates = \ - glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.pt'), recursive=True) + \ - glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.safetensors'), recursive=True) + \ - glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.ckpt'), recursive=True) - + candidates = list(shared.walk_files(shared.cmd_opts.lora_dir, allowed_extensions=[".pt", ".ckpt", ".safetensors"])) for filename in sorted(candidates, key=str.lower): if os.path.isdir(filename): continue name = os.path.splitext(os.path.basename(filename))[0] + entry = LoraOnDisk(name, filename) - available_loras[name] = LoraOnDisk(name, filename) + available_loras[name] = entry + if entry.alias in available_lora_aliases: + forbidden_lora_aliases[entry.alias.lower()] = 1 + + available_lora_aliases[name] = entry + available_lora_aliases[entry.alias] = entry + + +re_lora_name = re.compile(r"(.*)\s*\([0-9a-fA-F]+\)") + + +def infotext_pasted(infotext, params): + if "AddNet Module 1" in [x[1] for x in scripts.scripts_txt2img.infotext_fields]: + return # if the other extension is active, it will handle those fields, no need to do anything + + added = [] + + for k in params: + if not k.startswith("AddNet Model "): + continue + + num = k[13:] + + if params.get("AddNet Module " + num) != "LoRA": + continue + + name = params.get("AddNet Model " + num) + if name is None: + continue + + m = re_lora_name.match(name) + if m: + name = m.group(1) + + multiplier = params.get("AddNet Weight A " + num, "1.0") + + added.append(f"") + + if added: + params["Prompt"] += "\n" + "".join(added) available_loras = {} +available_lora_aliases = {} +forbidden_lora_aliases = {} loaded_loras = [] list_available_loras() diff --git a/extensions-builtin/Lora/scripts/lora_script.py b/extensions-builtin/Lora/scripts/lora_script.py index 0adab225..728e0b86 100644 --- a/extensions-builtin/Lora/scripts/lora_script.py +++ b/extensions-builtin/Lora/scripts/lora_script.py @@ -1,12 +1,12 @@ import torch import gradio as gr +from fastapi import FastAPI import lora import extra_networks_lora import ui_extra_networks_lora from modules import script_callbacks, ui_extra_networks, extra_networks, shared - def unload(): torch.nn.Linear.forward = torch.nn.Linear_forward_before_lora torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_lora @@ -49,8 +49,34 @@ torch.nn.MultiheadAttention._load_from_state_dict = lora.lora_MultiheadAttention script_callbacks.on_model_loaded(lora.assign_lora_names_to_compvis_modules) script_callbacks.on_script_unloaded(unload) script_callbacks.on_before_ui(before_ui) +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": [""] + [x for x in lora.available_loras]}, refresh=lora.list_available_loras), + "sd_lora": shared.OptionInfo("None", "Add Lora to prompt", gr.Dropdown, lambda: {"choices": ["None", *lora.available_loras]}, refresh=lora.list_available_loras), + "lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}), })) + + +shared.options_templates.update(shared.options_section(('compatibility', "Compatibility"), { + "lora_functional": shared.OptionInfo(False, "Lora: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension"), +})) + + +def create_lora_json(obj: lora.LoraOnDisk): + return { + "name": obj.name, + "alias": obj.alias, + "path": obj.filename, + "metadata": obj.metadata, + } + + +def api_loras(_: gr.Blocks, app: FastAPI): + @app.get("/sdapi/v1/loras") + async def get_loras(): + return [create_lora_json(obj) for obj in lora.available_loras.values()] + + +script_callbacks.on_app_started(api_loras) + diff --git a/extensions-builtin/Lora/ui_extra_networks_lora.py b/extensions-builtin/Lora/ui_extra_networks_lora.py index 68b11332..2050e3fa 100644 --- a/extensions-builtin/Lora/ui_extra_networks_lora.py +++ b/extensions-builtin/Lora/ui_extra_networks_lora.py @@ -15,13 +15,19 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): def list_items(self): 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 + yield { "name": name, "filename": path, "preview": self.find_preview(path), "description": self.find_description(path), "search_term": self.search_terms_from_path(lora_on_disk.filename), - "prompt": json.dumps(f""), + "prompt": json.dumps(f""), "local_preview": f"{path}.{shared.opts.samples_format}", "metadata": json.dumps(lora_on_disk.metadata, indent=4) if lora_on_disk.metadata else None, } diff --git a/extensions-builtin/ScuNET/scripts/scunet_model.py b/extensions-builtin/ScuNET/scripts/scunet_model.py index e0fbf3a3..cc2cbc6a 100644 --- a/extensions-builtin/ScuNET/scripts/scunet_model.py +++ b/extensions-builtin/ScuNET/scripts/scunet_model.py @@ -5,11 +5,14 @@ import traceback import PIL.Image import numpy as np import torch +from tqdm import tqdm + from basicsr.utils.download_util import load_file_from_url import modules.upscaler -from modules import devices, modelloader +from modules import devices, modelloader, script_callbacks from scunet_model_arch import SCUNet as net +from modules.shared import opts class UpscalerScuNET(modules.upscaler.Upscaler): @@ -42,28 +45,78 @@ class UpscalerScuNET(modules.upscaler.Upscaler): scalers.append(scaler_data2) self.scalers = scalers - def do_upscale(self, img: PIL.Image, selected_file): + @staticmethod + @torch.no_grad() + def tiled_inference(img, model): + # test the image tile by tile + h, w = img.shape[2:] + tile = opts.SCUNET_tile + tile_overlap = opts.SCUNET_tile_overlap + if tile == 0: + return model(img) + + device = devices.get_device_for('scunet') + assert tile % 8 == 0, "tile size should be a multiple of window_size" + sf = 1 + + stride = tile - tile_overlap + h_idx_list = list(range(0, h - tile, stride)) + [h - tile] + w_idx_list = list(range(0, w - tile, stride)) + [w - tile] + E = torch.zeros(1, 3, h * sf, w * sf, dtype=img.dtype, device=device) + W = torch.zeros_like(E, dtype=devices.dtype, device=device) + + with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="ScuNET tiles") as pbar: + for h_idx in h_idx_list: + + for w_idx in w_idx_list: + + 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) + + E[ + ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf + ].add_(out_patch) + W[ + ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf + ].add_(out_patch_mask) + pbar.update(1) + output = E.div_(W) + + return output + + def do_upscale(self, img: PIL.Image.Image, selected_file): + torch.cuda.empty_cache() model = self.load_model(selected_file) if model is None: + print(f"ScuNET: Unable to load model from {selected_file}", file=sys.stderr) return img device = devices.get_device_for('scunet') - img = np.array(img) - img = img[:, :, ::-1] - img = np.moveaxis(img, 2, 0) / 255 - img = torch.from_numpy(img).float() - img = img.unsqueeze(0).to(device) + tile = opts.SCUNET_tile + h, w = img.height, img.width + np_img = np.array(img) + np_img = np_img[:, :, ::-1] # RGB to BGR + np_img = np_img.transpose((2, 0, 1)) / 255 # HWC to CHW + torch_img = torch.from_numpy(np_img).float().unsqueeze(0).to(device) # type: ignore - with torch.no_grad(): - output = model(img) - output = output.squeeze().float().cpu().clamp_(0, 1).numpy() - output = 255. * np.moveaxis(output, 0, 2) - output = output.astype(np.uint8) - output = output[:, :, ::-1] + if tile > h or tile > w: + _img = torch.zeros(1, 3, max(h, tile), max(w, tile), dtype=torch_img.dtype, device=torch_img.device) + _img[:, :, :h, :w] = torch_img # pad image + torch_img = _img + + torch_output = self.tiled_inference(torch_img, model).squeeze(0) + torch_output = torch_output[:, :h * 1, :w * 1] # remove padding, if any + np_output: np.ndarray = torch_output.float().cpu().clamp_(0, 1).numpy() + del torch_img, torch_output torch.cuda.empty_cache() - return PIL.Image.fromarray(output, 'RGB') + + output = np_output.transpose((1, 2, 0)) # CHW to HWC + output = output[:, :, ::-1] # BGR to RGB + return PIL.Image.fromarray((output * 255).astype(np.uint8)) def load_model(self, path: str): device = devices.get_device_for('scunet') @@ -79,9 +132,19 @@ 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) diff --git a/extensions-builtin/ScuNET/scunet_model_arch.py b/extensions-builtin/ScuNET/scunet_model_arch.py index 43ca8d36..b51a8806 100644 --- a/extensions-builtin/ScuNET/scunet_model_arch.py +++ b/extensions-builtin/ScuNET/scunet_model_arch.py @@ -61,7 +61,9 @@ class WMSA(nn.Module): Returns: output: tensor shape [b h w c] """ - if self.type != 'W': x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2)) + if self.type != 'W': + x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2)) + x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size) h_windows = x.size(1) w_windows = x.size(2) @@ -85,8 +87,9 @@ class WMSA(nn.Module): output = self.linear(output) output = rearrange(output, 'b (w1 w2) (p1 p2) c -> b (w1 p1) (w2 p2) c', w1=h_windows, p1=self.window_size) - if self.type != 'W': output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), - 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) \ No newline at end of file + nn.init.constant_(m.weight, 1.0) diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py index e8783bca..0ba50487 100644 --- a/extensions-builtin/SwinIR/scripts/swinir_model.py +++ b/extensions-builtin/SwinIR/scripts/swinir_model.py @@ -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 @@ -45,7 +44,7 @@ class UpscalerSwinIR(Upscaler): img = upscale(img, model) try: torch.cuda.empty_cache() - except: + except Exception: pass return img @@ -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) diff --git a/extensions-builtin/SwinIR/swinir_model_arch.py b/extensions-builtin/SwinIR/swinir_model_arch.py index 863f42db..93b93274 100644 --- a/extensions-builtin/SwinIR/swinir_model_arch.py +++ b/extensions-builtin/SwinIR/swinir_model_arch.py @@ -644,7 +644,7 @@ class SwinIR(nn.Module): """ def __init__(self, img_size=64, patch_size=1, in_chans=3, - embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6], + embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6), window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None, drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1, norm_layer=nn.LayerNorm, ape=False, patch_norm=True, @@ -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() diff --git a/extensions-builtin/SwinIR/swinir_model_arch_v2.py b/extensions-builtin/SwinIR/swinir_model_arch_v2.py index 0e28ae6e..dad22cca 100644 --- a/extensions-builtin/SwinIR/swinir_model_arch_v2.py +++ b/extensions-builtin/SwinIR/swinir_model_arch_v2.py @@ -74,7 +74,7 @@ class WindowAttention(nn.Module): """ def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0., - pretrained_window_size=[0, 0]): + pretrained_window_size=(0, 0)): super().__init__() self.dim = dim @@ -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) \ No newline at end of file + print(x.shape) diff --git a/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js b/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js index f0918e26..5c7a836a 100644 --- a/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js +++ b/extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js @@ -1,103 +1,42 @@ // Stable Diffusion WebUI - Bracket checker -// Version 1.0 -// By Hingashi no Florin/Bwin4L +// By Hingashi no Florin/Bwin4L & @akx // Counts open and closed brackets (round, square, curly) in the prompt and negative prompt text boxes in the txt2img and img2img tabs. // 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(evt, textArea, counterElt) { - errorStringParen = '(...) - Different number of opening and closing parentheses detected.\n'; - errorStringSquare = '[...] - Different number of opening and closing square brackets detected.\n'; - errorStringCurly = '{...} - Different number of opening and closing curly brackets detected.\n'; +function checkBrackets(textArea, counterElt) { + var counts = {}; + (textArea.value.match(/[(){}\[\]]/g) || []).forEach(bracket => { + counts[bracket] = (counts[bracket] || 0) + 1; + }); + var errors = []; - openBracketRegExp = /\(/g; - closeBracketRegExp = /\)/g; - - openSquareBracketRegExp = /\[/g; - closeSquareBracketRegExp = /\]/g; - - openCurlyBracketRegExp = /\{/g; - closeCurlyBracketRegExp = /\}/g; - - totalOpenBracketMatches = 0; - totalCloseBracketMatches = 0; - totalOpenSquareBracketMatches = 0; - totalCloseSquareBracketMatches = 0; - totalOpenCurlyBracketMatches = 0; - totalCloseCurlyBracketMatches = 0; - - openBracketMatches = textArea.value.match(openBracketRegExp); - if(openBracketMatches) { - totalOpenBracketMatches = openBracketMatches.length; - } - - closeBracketMatches = textArea.value.match(closeBracketRegExp); - if(closeBracketMatches) { - totalCloseBracketMatches = closeBracketMatches.length; - } - - openSquareBracketMatches = textArea.value.match(openSquareBracketRegExp); - if(openSquareBracketMatches) { - totalOpenSquareBracketMatches = openSquareBracketMatches.length; - } - - closeSquareBracketMatches = textArea.value.match(closeSquareBracketRegExp); - if(closeSquareBracketMatches) { - totalCloseSquareBracketMatches = closeSquareBracketMatches.length; - } - - openCurlyBracketMatches = textArea.value.match(openCurlyBracketRegExp); - if(openCurlyBracketMatches) { - totalOpenCurlyBracketMatches = openCurlyBracketMatches.length; - } - - closeCurlyBracketMatches = textArea.value.match(closeCurlyBracketRegExp); - if(closeCurlyBracketMatches) { - totalCloseCurlyBracketMatches = closeCurlyBracketMatches.length; - } - - if(totalOpenBracketMatches != totalCloseBracketMatches) { - if(!counterElt.title.includes(errorStringParen)) { - counterElt.title += errorStringParen; + 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}.` + ); } - } else { - counterElt.title = counterElt.title.replace(errorStringParen, ''); } - if(totalOpenSquareBracketMatches != totalCloseSquareBracketMatches) { - if(!counterElt.title.includes(errorStringSquare)) { - counterElt.title += errorStringSquare; - } - } else { - counterElt.title = counterElt.title.replace(errorStringSquare, ''); - } + checkPair('(', ')', 'round brackets'); + checkPair('[', ']', 'square brackets'); + checkPair('{', '}', 'curly brackets'); + counterElt.title = errors.join('\n'); + counterElt.classList.toggle('error', errors.length !== 0); +} - if(totalOpenCurlyBracketMatches != totalCloseCurlyBracketMatches) { - if(!counterElt.title.includes(errorStringCurly)) { - counterElt.title += errorStringCurly; - } - } else { - counterElt.title = counterElt.title.replace(errorStringCurly, ''); - } +function setupBracketChecking(id_prompt, id_counter) { + var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea"); + var counter = gradioApp().getElementById(id_counter) - if(counterElt.title != '') { - counterElt.classList.add('error'); - } else { - counterElt.classList.remove('error'); + if (textarea && counter) { + textarea.addEventListener("input", () => checkBrackets(textarea, counter)); } } -function setupBracketChecking(id_prompt, id_counter){ - var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea"); - var counter = gradioApp().getElementById(id_counter) - - textarea.addEventListener("input", function(evt){ - checkBrackets(evt, 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') -}) \ No newline at end of file +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'); +}); diff --git a/html/extra-networks-card.html b/html/extra-networks-card.html index ef4b613a..6853b14f 100644 --- a/html/extra-networks-card.html +++ b/html/extra-networks-card.html @@ -6,7 +6,7 @@ - + {name} {description} diff --git a/html/licenses.html b/html/licenses.html index bc995aa0..ef6f2c0a 100644 --- a/html/licenses.html +++ b/html/licenses.html @@ -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. + + +

TAESD

+Tiny AutoEncoder for Stable Diffusion option for live previews +
+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.
\ No newline at end of file diff --git a/javascript/aspectRatioOverlay.js b/javascript/aspectRatioOverlay.js index a8278cca..5160081d 100644 --- a/javascript/aspectRatioOverlay.js +++ b/javascript/aspectRatioOverlay.js @@ -45,29 +45,24 @@ function dimensionChange(e, is_width, is_height){ var viewportOffset = targetElement.getBoundingClientRect(); - viewportscale = Math.min( targetElement.clientWidth/targetElement.naturalWidth, targetElement.clientHeight/targetElement.naturalHeight ) + var viewportscale = Math.min( targetElement.clientWidth/targetElement.naturalWidth, targetElement.clientHeight/targetElement.naturalHeight ) - scaledx = targetElement.naturalWidth*viewportscale - scaledy = targetElement.naturalHeight*viewportscale + var scaledx = targetElement.naturalWidth*viewportscale + var scaledy = targetElement.naturalHeight*viewportscale - cleintRectTop = (viewportOffset.top+window.scrollY) - cleintRectLeft = (viewportOffset.left+window.scrollX) - cleintRectCentreY = cleintRectTop + (targetElement.clientHeight/2) - cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth/2) + var cleintRectTop = (viewportOffset.top+window.scrollY) + var cleintRectLeft = (viewportOffset.left+window.scrollX) + var cleintRectCentreY = cleintRectTop + (targetElement.clientHeight/2) + var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth/2) - viewRectTop = cleintRectCentreY-(scaledy/2) - viewRectLeft = cleintRectCentreX-(scaledx/2) - arRectWidth = scaledx - arRectHeight = scaledy + var arscale = Math.min( scaledx/currentWidth, scaledy/currentHeight ) + var arscaledx = currentWidth*arscale + var arscaledy = currentHeight*arscale - arscale = Math.min( arRectWidth/currentWidth, arRectHeight/currentHeight ) - arscaledx = currentWidth*arscale - arscaledy = currentHeight*arscale - - arRectTop = cleintRectCentreY-(arscaledy/2) - arRectLeft = cleintRectCentreX-(arscaledx/2) - arRectWidth = arscaledx - arRectHeight = arscaledy + 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'; diff --git a/javascript/contextMenus.js b/javascript/contextMenus.js index 06f505b0..b2bdf053 100644 --- a/javascript/contextMenus.js +++ b/javascript/contextMenus.js @@ -4,7 +4,7 @@ contextMenuInit = function(){ let menuSpecs = new Map(); const uid = function(){ - return Date.now().toString(36) + Math.random().toString(36).substr(2); + return Date.now().toString(36) + Math.random().toString(36).substring(2); } function showContextMenu(event,element,menuEntries){ @@ -16,8 +16,7 @@ contextMenuInit = function(){ oldMenu.remove() } - let tabButton = uiCurrentTab - let baseStyle = window.getComputedStyle(tabButton) + let baseStyle = window.getComputedStyle(uiCurrentTab) const contextMenu = document.createElement('nav') contextMenu.id = "context-menu" @@ -36,7 +35,7 @@ contextMenuInit = function(){ menuEntries.forEach(function(entry){ let contextMenuEntry = document.createElement('a') contextMenuEntry.innerHTML = entry['name'] - contextMenuEntry.addEventListener("click", function(e) { + contextMenuEntry.addEventListener("click", function() { entry['func'](); }) contextMenuList.append(contextMenuEntry); @@ -63,7 +62,7 @@ contextMenuInit = function(){ function appendContextMenuOption(targetElementSelector,entryName,entryFunction){ - currentItems = menuSpecs.get(targetElementSelector) + var currentItems = menuSpecs.get(targetElementSelector) if(!currentItems){ currentItems = [] @@ -79,7 +78,7 @@ contextMenuInit = function(){ } function removeContextMenuOption(uid){ - menuSpecs.forEach(function(v,k) { + menuSpecs.forEach(function(v) { let index = -1 v.forEach(function(e,ei){if(e['id']==uid){index=ei}}) if(index>=0){ @@ -93,8 +92,7 @@ contextMenuInit = function(){ return; } gradioApp().addEventListener("click", function(e) { - let source = e.composedPath()[0] - if(source.id && source.id.indexOf('check_progress')>-1){ + if(! e.isTrusted){ return } @@ -112,7 +110,6 @@ contextMenuInit = function(){ if(e.composedPath()[0].matches(k)){ showContextMenu(e,e.composedPath()[0],v) e.preventDefault() - return } }) }); @@ -161,14 +158,6 @@ addContextMenuEventListener = initResponse[2]; appendContextMenuOption('#img2img_interrupt','Cancel generate forever',cancelGenerateForever) appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever) - appendContextMenuOption('#roll','Roll three', - function(){ - let rollbutton = get_uiCurrentTabContent().querySelector('#roll'); - setTimeout(function(){rollbutton.click()},100) - setTimeout(function(){rollbutton.click()},200) - setTimeout(function(){rollbutton.click()},300) - } - ) })(); //End example Context Menu Items diff --git a/javascript/edit-attention.js b/javascript/edit-attention.js index 20a5aadf..d2c2f190 100644 --- a/javascript/edit-attention.js +++ b/javascript/edit-attention.js @@ -17,7 +17,7 @@ function keyupEditAttention(event){ // Find opening parenthesis around current cursor const before = text.substring(0, selectionStart); let beforeParen = before.lastIndexOf(OPEN); - if (beforeParen == -1) return false; + if (beforeParen == -1) return false; let beforeParenClose = before.lastIndexOf(CLOSE); while (beforeParenClose !== -1 && beforeParenClose > beforeParen) { beforeParen = before.lastIndexOf(OPEN, beforeParen - 1); @@ -27,7 +27,7 @@ function keyupEditAttention(event){ // Find closing parenthesis around current cursor const after = text.substring(selectionStart); let afterParen = after.indexOf(CLOSE); - if (afterParen == -1) return false; + if (afterParen == -1) return false; let afterParenOpen = after.indexOf(OPEN); while (afterParenOpen !== -1 && afterParen > afterParenOpen) { afterParen = after.indexOf(CLOSE, afterParen + 1); @@ -43,16 +43,34 @@ function keyupEditAttention(event){ 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++; + } - // If the user hasn't selected anything, let's select their current parenthesis block - if(! selectCurrentParenthesisBlock('<', '>')){ - selectCurrentParenthesisBlock('(', ')') + 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(); - closeCharacter = ')' - delta = opts.keyedit_precision_attention + var closeCharacter = ')' + var delta = opts.keyedit_precision_attention if (selectionStart > 0 && text[selectionStart - 1] == '<'){ closeCharacter = '>' @@ -73,15 +91,21 @@ function keyupEditAttention(event){ selectionEnd += 1; } - end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1; - weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + 1 + end)); + 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" - text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1); + 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; @@ -93,4 +117,4 @@ function keyupEditAttention(event){ addEventListener('keydown', (event) => { keyupEditAttention(event); -}); \ No newline at end of file +}); diff --git a/javascript/extensions.js b/javascript/extensions.js index 72924a28..2a2d2f8e 100644 --- a/javascript/extensions.js +++ b/javascript/extensions.js @@ -1,14 +1,14 @@ -function extensions_apply(_, _, disable_all){ +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.substr(7)) + disable.push(x.name.substring(7)) if(x.name.startsWith("update_") && x.checked) - update.push(x.name.substr(7)) + update.push(x.name.substring(7)) }) restart_reload() @@ -16,12 +16,12 @@ function extensions_apply(_, _, disable_all){ return [JSON.stringify(disable), JSON.stringify(update), disable_all] } -function extensions_check(_, _){ +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.substr(7)) + disable.push(x.name.substring(7)) }) gradioApp().querySelectorAll('#extensions .extension_status').forEach(function(x){ @@ -41,9 +41,31 @@ function install_extension_from_index(button, url){ button.disabled = "disabled" button.value = "Installing..." - textarea = gradioApp().querySelector('#extension_to_install textarea') + 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]; +} diff --git a/javascript/extraNetworks.js b/javascript/extraNetworks.js index 25322138..4d9a522c 100644 --- a/javascript/extraNetworks.js +++ b/javascript/extraNetworks.js @@ -1,4 +1,3 @@ - function setupExtraNetworksForTab(tabname){ gradioApp().querySelector('#'+tabname+'_extra_tabs').classList.add('extra-networks') @@ -10,16 +9,34 @@ function setupExtraNetworksForTab(tabname){ tabs.appendChild(search) tabs.appendChild(refresh) - search.addEventListener("input", function(evt){ - searchTerm = search.value.toLowerCase() + var applyFilter = function(){ + var searchTerm = search.value.toLowerCase() gradioApp().querySelectorAll('#'+tabname+'_extra_tabs div.card').forEach(function(elem){ - text = elem.querySelector('.name').textContent.toLowerCase() + " " + elem.querySelector('.search_term').textContent.toLowerCase() - elem.style.display = text.indexOf(searchTerm) == -1 ? "none" : "" + 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(){ @@ -51,18 +68,27 @@ 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, index){ - m = found.match(re_extranet); - if(m[1] == partToSearch){ - replaced = true; - return "" - } - return found; - }) + 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 @@ -96,9 +122,9 @@ function saveCardPreview(event, tabname, filename){ } function extraNetworksSearchButton(tabs_id, event){ - searchTextarea = gradioApp().querySelector("#" + tabs_id + ' > div > textarea') - button = event.target - text = button.classList.contains("search-all") ? "" : button.textContent.trim() + 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) @@ -133,7 +159,7 @@ function popup(contents){ } function extraNetworksShowMetadata(text){ - elem = document.createElement('pre') + var elem = document.createElement('pre') elem.classList.add('popup-metadata'); elem.textContent = text; @@ -165,7 +191,7 @@ function requestGet(url, data, handler, errorHandler){ } function extraNetworksRequestMetadata(event, extraPage, cardName){ - showError = function(){ extraNetworksShowMetadata("there was an error getting metadata"); } + var showError = function(){ extraNetworksShowMetadata("there was an error getting metadata"); } requestGet("./sd_extra_networks/metadata", {"page": extraPage, "item": cardName}, function(data){ if(data && data.metadata){ diff --git a/javascript/generationParams.js b/javascript/generationParams.js index 95f05093..ef64ee2e 100644 --- a/javascript/generationParams.js +++ b/javascript/generationParams.js @@ -16,14 +16,14 @@ onUiUpdate(function(){ let modalObserver = new MutationObserver(function(mutations) { mutations.forEach(function(mutationRecord) { - let selectedTab = gradioApp().querySelector('#tabs div button.bg-white')?.innerText - if (mutationRecord.target.style.display === 'none' && selectedTab === 'txt2img' || selectedTab === 'img2img') - gradioApp().getElementById(selectedTab+"_generation_info_button").click() + 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) { - gallery = gradioApp().querySelector('#'+tab_name+'_gallery') + var gallery = gradioApp().querySelector('#'+tab_name+'_gallery') gallery?.addEventListener('click', () => gradioApp().getElementById(tab_name+"_generation_info_button").click()); gallery?.addEventListener('keydown', (e) => { if (e.keyCode == 37 || e.keyCode == 39) // left or right arrow diff --git a/javascript/hints.js b/javascript/hints.js index f48a0eb6..7b6f37ad 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -22,6 +22,7 @@ titles = { "\u{1f4cb}": "Apply selected styles to current prompt", "\u{1f4d2}": "Paste available values into the field", "\u{1f3b4}": "Show/hide extra networks", + "\u{1f300}": "Restore progress", "Inpaint a part of image": "Draw a mask over an image, and the script will regenerate the masked area with content according to prompt", "SD upscale": "Upscale image normally, split result into tiles, improve each tile using img2img, merge whole image back", @@ -65,8 +66,8 @@ 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], [prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime], [datetime