Merge branch 'master' into racecond_fix

.github/workflows/run_tests.yaml

+name: Run basic features tests on CPU with empty SD model
+
+on:
+  - push
+  - pull_request
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.10.6
+      - uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
+          restore-keys: ${{ runner.os }}-pip-
+      - name: Run tests
+        run: python launch.py --tests basic_features --no-half --disable-opt-split-attention --use-cpu all --skip-torch-cuda-test
+      - name: Upload main app stdout-stderr
+        uses: actions/upload-artifact@v3
+        if: always()
+        with:
+          name: stdout-stderr
+          path: |
+            test/stdout.txt
+            test/stderr.txt

.gitignore

 __pycache__
 *.ckpt
+*.safetensors
 *.pth
 /ESRGAN/*
 /SwinIR/*

CODEOWNERS

 *       @AUTOMATIC1111
-/localizations/ar_AR.json   @xmodar @blackneoo
-/localizations/de_DE.json   @LunixWasTaken
-/localizations/es_ES.json   @innovaciones
-/localizations/fr_FR.json   @tumbly
-/localizations/it_IT.json   @EugenioBuffo
-/localizations/ja_JP.json   @yuuki76
-/localizations/ko_KR.json   @36DB
-/localizations/pt_BR.json   @M-art-ucci
-/localizations/ru_RU.json   @kabachuha
-/localizations/tr_TR.json   @camenduru
-/localizations/zh_CN.json   @dtlnor @bgluminous
-/localizations/zh_TW.json   @benlisquare
+
+# if you were managing a localization and were removed from this file, this is because
+# the intended way to do localizations now is via extensions. See:
+# https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Developing-extensions
+# Make a repo with your localization and since you are still listed as a collaborator
+# you can add it to the wiki page yourself. This change is because some people complained
+# the git commit log is cluttered with things unrelated to almost everyone and
+# because I believe this is the best overall for the project to handle localizations almost
+# entirely without my oversight.
+
+

README.md

@@ -70,7 +70,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
      - separate prompts using uppercase `AND`
      - also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
 - No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
-- DeepDanbooru integration, creates danbooru style tags for anime prompts (add --deepdanbooru to commandline args)
+- DeepDanbooru integration, creates danbooru style tags for anime prompts
 - [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args)
 - via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
 - Generate forever option
@@ -84,26 +84,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
 - API
 - Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML. 
 - via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
-
-## Where are Aesthetic Gradients?!?!
-Aesthetic Gradients are now an extension. You can install it using git:
-
-```commandline
-git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients extensions/aesthetic-gradients
-```
-
-After running this command, make sure that you have `aesthetic-gradients` dir in webui's `extensions` directory and restart
-the UI. The interface for Aesthetic Gradients should appear exactly the same as it was.
-
-## Where is History/Image browser?!?!
-Image browser is now an extension. You can install it using git:
-
-```commandline
-git clone https://github.com/yfszzx/stable-diffusion-webui-images-browser extensions/images-browser
-```
-
-After running this command, make sure that you have `images-browser` dir in webui's `extensions` directory and restart
-the UI. The interface for Image browser should appear exactly the same as it was.
+- [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
 
 ## Installation and Running
 Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
@@ -155,14 +136,15 @@ The documentation was moved from this README over to the project's [wiki](https:
 - Swin2SR - https://github.com/mv-lab/swin2sr
 - LDSR - https://github.com/Hafiidz/latent-diffusion
 - Ideas for optimizations - https://github.com/basujindal/stable-diffusion
-- Doggettx - Cross Attention layer optimization - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
-- InvokeAI, lstein - Cross Attention layer optimization - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
-- Rinon Gal - Textual Inversion - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
+- Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
+- Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
+- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
 - Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
 - Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
 - CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
 - Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
 - xformers - https://github.com/facebookresearch/xformers
 - DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
+- Security advice - RyotaK
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
 - (You)

javascript/edit-attention.js

 addEventListener('keydown', (event) => {
 	let target = event.originalTarget || event.composedPath()[0];
-	if (!target.hasAttribute("placeholder")) return;
-	if (!target.placeholder.toLowerCase().includes("prompt")) return;
+	if (!target.matches("#toprow textarea.gr-text-input[placeholder]")) return;
 	if (! (event.metaKey || event.ctrlKey)) return;
 
 

javascript/generationParams.js

+// 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'] });
+	}
+});
+
+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()
+	});
+});
+
+function attachGalleryListeners(tab_name) {
+	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;
+}

javascript/hints.js

@@ -62,8 +62,8 @@ 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], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
-    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
+    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [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]; leave empty for default.",
+    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [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]; 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": "Process an image, use it as an input, repeat.",
@@ -94,6 +94,8 @@ titles = {
     "Add difference": "Result = A + (B - C) * M",
 
     "Learning rate": "how fast should the 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."
 }
 
 

javascript/progressbar.js

@@ -23,7 +23,7 @@ function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip
     
     if(opts.show_progress_in_title && progressbar && progressbar.offsetParent){
         if(progressbar.innerText){
-            let newtitle = 'Stable Diffusion - ' + progressbar.innerText
+            let newtitle = '[' + progressbar.innerText.trim() + '] Stable Diffusion';
             if(document.title != newtitle){
                 document.title =  newtitle;          
             }

javascript/ui.js

@@ -8,8 +8,8 @@ function set_theme(theme){
 }
 
 function selected_gallery_index(){
-    var buttons = gradioApp().querySelectorAll('[style="display: block;"].tabitem .gallery-item')
-    var button = gradioApp().querySelector('[style="display: block;"].tabitem .gallery-item.\\!ring-2')
+    var buttons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery] .gallery-item')
+    var button = gradioApp().querySelector('[style="display: block;"].tabitem div[id$=_gallery] .gallery-item.\\!ring-2')
 
     var result = -1
     buttons.forEach(function(v, i){ if(v==button) { result = i } })
@@ -208,4 +208,6 @@ function update_token_counter(button_id) {
 function restart_reload(){
     document.body.innerHTML='<h1 style="font-family:monospace;margin-top:20%;color:lightgray;text-align:center;">Reloading...</h1>';
     setTimeout(function(){location.reload()},2000)
+
+    return []
 }

launch.py

@@ -5,6 +5,8 @@ import sys
 import importlib.util
 import shlex
 import platform
+import argparse
+import json
 
 dir_repos = "repositories"
 dir_extensions = "extensions"
@@ -17,6 +19,19 @@ def extract_arg(args, name):
     return [x for x in args if x != name], name in args
 
 
+def extract_opt(args, name):
+    opt = None
+    is_present = False
+    if name in args:
+        is_present = True
+        idx = args.index(name)
+        del args[idx]
+        if idx < len(args) and args[idx][0] != "-":
+            opt = args[idx]
+            del args[idx]
+    return args, is_present, opt
+
+
 def run(command, desc=None, errdesc=None, custom_env=None):
     if desc is not None:
         print(desc)
@@ -105,23 +120,42 @@ def version_check(commit):
         print("version check failed", e)
 
 
-def run_extensions_installers():
-    if not os.path.isdir(dir_extensions):
-        return
-
-    for dirname_extension in os.listdir(dir_extensions):
-        path_installer = os.path.join(dir_extensions, dirname_extension, "install.py")
+def run_extension_installer(extension_dir):
+    path_installer = os.path.join(extension_dir, "install.py")
     if not os.path.isfile(path_installer):
-            continue
+        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 {dirname_extension}", custom_env=env))
+        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', []))
+
+    return [x for x in os.listdir(dir_extensions) if x not in disabled_extensions]
+
+
+def run_extensions_installers(settings_file):
+    if not os.path.isdir(dir_extensions):
+        return
+
+    for dirname_extension in list_extensions(settings_file):
+        run_extension_installer(os.path.join(dir_extensions, dirname_extension))
+
 
 def prepare_enviroment():
     torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113")
@@ -130,31 +164,33 @@ def prepare_enviroment():
 
     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")
-    deepdanbooru_package = os.environ.get('DEEPDANBOORU_PACKAGE', "git+https://github.com/KichangKim/DeepDanbooru.git@d91a2963bf87c6a770d74894667e9ffa9f6de7ff")
+    openclip_package = os.environ.get('OPENCLIP_PACKAGE', "git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b")
 
     xformers_windows_package = os.environ.get('XFORMERS_WINDOWS_PACKAGE', 'https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl')
 
-    stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/CompVis/stable-diffusion.git")
-    taming_transformers_repo = os.environ.get('TAMING_REANSFORMERS_REPO', "https://github.com/CompVis/taming-transformers.git")
+    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('CODEFORMET_REPO', 'https://github.com/sczhou/CodeFormer.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', "69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc")
+    stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "47b6b607fdd31875c9279cd2f4f16b92e4ea958e")
     taming_transformers_commit_hash = os.environ.get('TAMING_TRANSFORMERS_COMMIT_HASH', "24268930bf1dce879235a7fddd0b2355b84d7ea6")
-    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "f4e99857772fc3a126ba886aadf795a332774878")
+    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")
 
     sys.argv += shlex.split(commandline_args)
-    test_argv = [x for x in sys.argv if x != '--tests']
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default='config.json')
+    args, _ = parser.parse_known_args(sys.argv)
 
     sys.argv, skip_torch_cuda_test = extract_arg(sys.argv, '--skip-torch-cuda-test')
     sys.argv, reinstall_xformers = extract_arg(sys.argv, '--reinstall-xformers')
     sys.argv, update_check = extract_arg(sys.argv, '--update-check')
-    sys.argv, run_tests = extract_arg(sys.argv, '--tests')
+    sys.argv, run_tests, test_dir = extract_opt(sys.argv, '--tests')
     xformers = '--xformers' in sys.argv
-    deepdanbooru = '--deepdanbooru' in sys.argv
     ngrok = '--ngrok' in sys.argv
 
     try:
@@ -177,6 +213,9 @@ def prepare_enviroment():
     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 reinstall_xformers) and xformers:
         if platform.system() == "Windows":
             if platform.python_version().startswith("3.10"):
@@ -189,15 +228,12 @@ def prepare_enviroment():
         elif platform.system() == "Linux":
             run_pip("install xformers", "xformers")
 
-    if not is_installed("deepdanbooru") and deepdanbooru:
-        run_pip(f"install {deepdanbooru_package}#egg=deepdanbooru[tensorflow] tensorflow==2.10.0 tensorflow-io==0.27.0", "deepdanbooru")
-
     if not is_installed("pyngrok") and ngrok:
         run_pip("install pyngrok", "ngrok")
 
     os.makedirs(dir_repos, exist_ok=True)
 
-    git_clone(stable_diffusion_repo, repo_dir('stable-diffusion'), "Stable Diffusion", stable_diffusion_commit_hash)
+    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)
@@ -208,7 +244,7 @@ def prepare_enviroment():
 
     run_pip(f"install -r {requirements_file}", "requirements for Web UI")
 
-    run_extensions_installers()
+    run_extensions_installers(settings_file=args.ui_settings_file)
 
     if update_check:
         version_check(commit)
@@ -218,32 +254,41 @@ def prepare_enviroment():
         exit(0)
 
     if run_tests:
-        tests(test_argv)
-        exit(0)
+        exitcode = tests(test_dir)
+        exit(exitcode)
 
 
-def tests(argv):
-    if "--api" not in argv:
-        argv.append("--api")
+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("./test/test_files/empty.pt")
+    if "--skip-torch-cuda-test" not in sys.argv:
+        sys.argv.append("--skip-torch-cuda-test")
 
-    print(f"Launching Web UI in another process for testing with arguments: {' '.join(argv[1:])}")
+    print(f"Launching Web UI in another process for testing with arguments: {' '.join(sys.argv[1:])}")
 
     with open('test/stdout.txt', "w", encoding="utf8") as stdout, open('test/stderr.txt', "w", encoding="utf8") as stderr:
-        proc = subprocess.Popen([sys.executable, *argv], stdout=stdout, stderr=stderr)
+        proc = subprocess.Popen([sys.executable, *sys.argv], stdout=stdout, stderr=stderr)
 
     import test.server_poll
-    test.server_poll.run_tests()
+    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_webui():
-    print(f"Launching Web UI with arguments: {' '.join(sys.argv[1:])}")
+def start():
+    print(f"Launching {'API server' if '--nowebui' in sys.argv else 'Web UI'} with arguments: {' '.join(sys.argv[1:])}")
     import webui
+    if '--nowebui' in sys.argv:
+        webui.api_only()
+    else:
         webui.webui()
 
 
 if __name__ == "__main__":
     prepare_enviroment()
-    start_webui()
+    start()

modules/api/models.py

 import inspect
-from click import prompt
 from pydantic import BaseModel, Field, create_model
 from typing import Any, Optional
 from typing_extensions import Literal
 from inflection import underscore
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
-from modules.shared import sd_upscalers
+from modules.shared import sd_upscalers, opts, parser
+from typing import Dict, List
 
 API_NOT_ALLOWED = [
     "self",
@@ -65,6 +65,7 @@ class PydanticModelGenerator:
 
         self._model_name = model_name
         self._class_data = merge_class_params(class_instance)
+
         self._model_def = [
             ModelDef(
                 field=underscore(k),
@@ -109,12 +110,12 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
 ).generate_model()
 
 class TextToImageResponse(BaseModel):
-    images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
     parameters: dict
     info: str
 
 class ImageToImageResponse(BaseModel):
-    images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
     parameters: dict
     info: str
 
@@ -147,10 +148,10 @@ class FileData(BaseModel):
     name: str = Field(title="File name")
 
 class ExtrasBatchImagesRequest(ExtrasBaseRequest):
-    imageList: list[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
+    imageList: List[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
 
 class ExtrasBatchImagesResponse(ExtraBaseResponse):
-    images: list[str] = Field(title="Images", description="The generated images in base64 format.")
+    images: List[str] = Field(title="Images", description="The generated images in base64 format.")
 
 class PNGInfoRequest(BaseModel):
     image: str = Field(title="Image", description="The base64 encoded PNG image")
@@ -166,3 +167,76 @@ class ProgressResponse(BaseModel):
     eta_relative: float = Field(title="ETA in secs")
     state: dict = Field(title="State", description="The current state snapshot")
     current_image: str = Field(default=None, title="Current image", description="The current image in base64 format. opts.show_progress_every_n_steps is required for this to work.")
+
+class InterrogateRequest(BaseModel):
+    image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.")
+    model: str = Field(default="clip", title="Model", description="The interrogate model used.")
+
+class InterrogateResponse(BaseModel):
+    caption: str = Field(default=None, title="Caption", description="The generated caption for the image.")
+
+fields = {}
+for key, metadata in opts.data_labels.items():
+    value = opts.data.get(key)
+    optType = opts.typemap.get(type(metadata.default), type(value))
+
+    if (metadata is not None):
+        fields.update({key: (Optional[optType], Field(
+            default=metadata.default ,description=metadata.label))})
+    else:
+        fields.update({key: (Optional[optType], Field())})
+
+OptionsModel = create_model("Options", **fields)
+
+flags = {}
+_options = vars(parser)['_option_string_actions']
+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))})
+
+FlagsModel = create_model("Flags", **flags)
+
+class SamplerItem(BaseModel):
+    name: str = Field(title="Name")
+    aliases: List[str] = Field(title="Aliases")
+    options: Dict[str, str] = Field(title="Options")
+
+class UpscalerItem(BaseModel):
+    name: str = Field(title="Name")
+    model_name: Optional[str] = Field(title="Model Name")
+    model_path: Optional[str] = Field(title="Path")
+    model_url: Optional[str] = Field(title="URL")
+
+class SDModelItem(BaseModel):
+    title: str = Field(title="Title")
+    model_name: str = Field(title="Model Name")
+    hash: str = Field(title="Hash")
+    filename: str = Field(title="Filename")
+    config: str = Field(title="Config file")
+
+class HypernetworkItem(BaseModel):
+    name: str = Field(title="Name")
+    path: Optional[str] = Field(title="Path")
+
+class FaceRestorerItem(BaseModel):
+    name: str = Field(title="Name")
+    cmd_dir: Optional[str] = Field(title="Path")
+
+class RealesrganItem(BaseModel):
+    name: str = Field(title="Name")
+    path: Optional[str] = Field(title="Path")
+    scale: Optional[int] = Field(title="Scale")
+
+class PromptStyleItem(BaseModel):
+    name: str = Field(title="Name")
+    prompt: Optional[str] = Field(title="Prompt")
+    negative_prompt: Optional[str] = Field(title="Negative Prompt")
+
+class ArtistItem(BaseModel):
+    name: str = Field(title="Name")
+    score: float = Field(title="Score")
+    category: str = Field(title="Category")
+

modules/codeformer_model.py

@@ -36,6 +36,7 @@ def setup_model(dirname):
         from basicsr.utils.download_util import load_file_from_url
         from basicsr.utils import imwrite, img2tensor, tensor2img
         from facelib.utils.face_restoration_helper import FaceRestoreHelper
+        from facelib.detection.retinaface import retinaface
         from modules.shared import cmd_opts
 
         net_class = CodeFormer
@@ -65,6 +66,8 @@ def setup_model(dirname):
                 net.load_state_dict(checkpoint)
                 net.eval()
 
+                if hasattr(retinaface, 'device'):
+                    retinaface.device = devices.device_codeformer
                 face_helper = FaceRestoreHelper(1, face_size=512, crop_ratio=(1, 1), det_model='retinaface_resnet50', save_ext='png', use_parse=True, device=devices.device_codeformer)
 
                 self.net = net

modules/esrgan_model.py

@@ -199,7 +199,7 @@ def upscale_without_tiling(model, img):
     img = img[:, :, ::-1]
     img = np.ascontiguousarray(np.transpose(img, (2, 0, 1))) / 255
     img = torch.from_numpy(img).float()
-    img = devices.mps_contiguous_to(img.unsqueeze(0), devices.device_esrgan)
+    img = img.unsqueeze(0).to(devices.device_esrgan)
     with torch.no_grad():
         output = model(img)
     output = output.squeeze().float().cpu().clamp_(0, 1).numpy()

modules/extensions.py

@@ -6,7 +6,6 @@ import git
 
 from modules import paths, shared
 
-
 extensions = []
 extensions_dir = os.path.join(paths.script_path, "extensions")
 
@@ -34,8 +33,11 @@ class Extension:
         if repo is None or repo.bare:
             self.remote = None
         else:
+            try:
                 self.remote = next(repo.remote().urls, None)
                 self.status = 'unknown'
+            except Exception:
+                self.remote = None
 
     def list_files(self, subdir, extension):
         from modules import scripts
@@ -63,9 +65,12 @@ class Extension:
         self.can_update = False
         self.status = "latest"
 
-    def pull(self):
+    def fetch_and_reset_hard(self):
         repo = git.Repo(self.path)
-        repo.remotes.origin.pull()
+        # Fix: `error: Your local changes to the following files would be overwritten by merge`,
+        # because WSL2 Docker set 755 file permissions instead of 644, this results to the error.
+        repo.git.fetch('--all')
+        repo.git.reset('--hard', 'origin')
 
 
 def list_extensions():
@@ -81,3 +86,4 @@ def list_extensions():
 
         extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions)
         extensions.append(extension)
+

modules/gfpgan_model.py

@@ -36,7 +36,9 @@ def gfpgann():
     else:
         print("Unable to load gfpgan model!")
         return None
-    model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None)
+    if hasattr(facexlib.detection.retinaface, 'device'):
+        facexlib.detection.retinaface.device = devices.device_gfpgan
+    model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=devices.device_gfpgan)
     loaded_gfpgan_model = model
 
     return model

modules/hypernetworks/ui.py

@@ -9,7 +9,7 @@ from modules import devices, sd_hijack, shared
 from modules.hypernetworks import hypernetwork
 
 not_available = ["hardswish", "multiheadattention"]
-keys = ["linear"] + list(x for x in hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available)
+keys = list(x for x in hypernetwork.HypernetworkModule.activation_dict.keys() 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):
     # Remove illegal characters from name.

modules/interrogate.py

@@ -148,8 +148,7 @@ class InterrogateModels:
 
             clip_image = self.clip_preprocess(pil_image).unsqueeze(0).type(self.dtype).to(devices.device_interrogate)
 
-            precision_scope = torch.autocast if shared.cmd_opts.precision == "autocast" else contextlib.nullcontext
-            with torch.no_grad(), precision_scope("cuda"):
+            with torch.no_grad(), devices.autocast():
                 image_features = self.clip_model.encode_image(clip_image).type(self.dtype)
 
                 image_features /= image_features.norm(dim=-1, keepdim=True)

modules/modelloader.py

@@ -82,6 +82,7 @@ def cleanup_models():
     src_path = models_path
     dest_path = os.path.join(models_path, "Stable-diffusion")
     move_files(src_path, dest_path, ".ckpt")
+    move_files(src_path, dest_path, ".safetensors")
     src_path = os.path.join(root_path, "ESRGAN")
     dest_path = os.path.join(models_path, "ESRGAN")
     move_files(src_path, dest_path)