i18n: rename document to documentation

docs: update link for enhance documentation
i18n: adjust translations to use proper english for plural tab titles
2026-08-16 13:13:16 +02:00 · 2024-07-14 21:40:10 +02:00 · 2024-07-14 21:31:59 +02:00 · 2024-07-14 21:07:12 +02:00 · 2024-07-14 21:06:59 +02:00 · 2024-07-14 20:35:39 +02:00
63 changed files with 3944 additions and 1102 deletions
@@ -1 +1,54 @@
-.idea
+__pycache__
+*.ckpt
+*.safetensors
+*.pth
+*.pt
+*.bin
+*.patch
+*.backup
+*.corrupted
+*.partial
+*.onnx
+sorted_styles.json
+/input
+/cache
+/language/default.json
+/test_imgs
+config.txt
+config_modification_tutorial.txt
+user_path_config.txt
+user_path_config-deprecated.txt
+/modules/*.png
+/repositories
+/fooocus_env
+/venv
+/tmp
+/ui-config.json
+/outputs
+/config.json
+/log
+/webui.settings.bat
+/embeddings
+/styles.csv
+/params.txt
+/styles.csv.bak
+/webui-user.bat
+/webui-user.sh
+/interrogate
+/user.css
+/.idea
+/notification.ogg
+/notification.mp3
+/SwinIR
+/textual_inversion
+.vscode
+/extensions
+/test/stdout.txt
+/test/stderr.txt
+/cache.json*
+/config_states/
+/node_modules
+/package-lock.json
+/.coverage*
+/auth.json
+.DS_Store
@@ -0,0 +1,3 @@
+# Ensure that shell scripts always use lf line endings, e.g. entrypoint.sh for docker
+* text=auto
+*.sh text eol=lf
@@ -1 +1 @@
-*       @lllyasviel
+*       @mashb1t
@@ -0,0 +1,77 @@
+name: Bug Report
+description: Describe a problem
+title: "[Bug]: "
+labels: ["bug", "triage"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for taking the time to fill out this bug report form!
+  - type: checkboxes
+    id: prerequisites
+    attributes:
+      label: Prerequisites
+      description: Please make sure to troubleshoot yourself before continuing.
+      options:
+        - label: I have read the [Troubleshooting Guide](https://github.com/lllyasviel/Fooocus/blob/main/troubleshoot.md)
+          required: true
+        - label: I have checked that this is not a duplicate of an already existing [issue](https://github.com/lllyasviel/Fooocus/issues)
+          required: true
+  - type: textarea
+    id: description
+    attributes:
+      label: Describe the problem
+      description: Also tell us, what did you expect to happen?
+      placeholder: "A clear and concise description of what the bug is."
+    validations:
+      required: true
+  - type: textarea
+    id: logs
+    attributes:
+      label: Full console log output
+      description: Please copy and paste the **full** console log here. You will make our job easier if you give a **full** log. This will be automatically formatted into code, so no need for backticks.
+      render: shell
+    validations:
+      required: true
+  - type: textarea
+    id: version
+    attributes:
+      label: Version
+      description: What version of Fooocus are you using? (see browser tab title or console log)
+      placeholder: "Example: Fooocus 2.1.855"
+    validations:
+      required: true
+  - type: dropdown
+    id: hosting
+    attributes:
+      label: Where are you running Fooocus?
+      multiple: false
+      options:
+        - Locally
+        - Locally with virtualisation (e.g. Docker)
+        - Cloud (Gradio)
+        - Cloud (other)
+    validations:
+      required: true
+  - type: input
+    id: operating-system
+    attributes:
+      label: Operating System
+      description: What operating system are you using?
+      placeholder: "Example: Windows 10"
+  - type: dropdown
+    id: browsers
+    attributes:
+      label: What browsers are you seeing the problem on?
+      multiple: true
+      options:
+        - Chrome
+        - Firefox
+        - Microsoft Edge
+        - Safari
+        - other
+    validations:
+      required: true
+  - type: markdown
+    attributes:
+      value: "Thank you for completing our form!"
@@ -0,0 +1,34 @@
+name: Feature request
+description: Suggest an idea for this project
+title: "[Feature]: "
+labels: ["enhancement"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thank you for taking the time to fill out this feature request form!
+  - type: checkboxes
+    id: prerequisites
+    attributes:
+      label: Prerequisites
+      options:
+        - label: I have checked that this is not a duplicate of an already existing [feature request](https://github.com/lllyasviel/Fooocus/issues)
+          required: true
+  - type: textarea
+    id: relation-to-problem
+    attributes:
+      label: Is your feature request related to a problem? Please describe.
+      placeholder: "A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+."
+    validations:
+      required: true
+  - type: textarea
+    id: description
+    attributes:
+      label: Describe the idea you'd like
+      placeholder: "A clear and concise description of what you want to happen."
+    validations:
+      required: true
+  - type: markdown
+    attributes:
+      value: "Thank you for completing our form!"
@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "monthly"
@@ -0,0 +1,47 @@
+name: Docker image build
+
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - v*
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/${{ github.repository_owner }}/${{ github.event.repository.name }}
+          tags: |
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{major}}
+            type=edge,branch=main
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
@@ -10,6 +10,7 @@ __pycache__
 *.partial
 *.onnx
 sorted_styles.json
+hash_cache.txt
 /input
 /cache
 /language/default.json
@@ -1,4 +1,4 @@
-FROM nvidia/cuda:12.3.1-base-ubuntu22.04
+FROM nvidia/cuda:12.4.1-base-ubuntu22.04
 ENV DEBIAN_FRONTEND noninteractive
 ENV CMDARGS --listen

@@ -23,7 +23,7 @@ RUN chown -R user:user /content
 WORKDIR /content
 USER user

-RUN git clone https://github.com/lllyasviel/Fooocus /content/app
+COPY --chown=user:user . /content/app
 RUN mv /content/app/models /content/app/models.org

 CMD [ "sh", "-c", "/content/entrypoint.sh ${CMDARGS}" ]
@@ -1,7 +1,4 @@
 import ldm_patched.modules.args_parser as args_parser
-import os
-
-from tempfile import gettempdir

 args_parser.parser.add_argument("--share", action='store_true', help="Set whether to share on Gradio.")

@@ -31,11 +28,14 @@ args_parser.parser.add_argument("--disable-metadata", action='store_true',
 args_parser.parser.add_argument("--disable-preset-download", action='store_true',
                                help="Disables downloading models for presets", default=False)

-args_parser.parser.add_argument("--enable-describe-uov-image", action='store_true',
-                                help="Disables automatic description of uov images when prompt is empty", default=False)
+args_parser.parser.add_argument("--enable-auto-describe-image", action='store_true',
+                                help="Enables automatic description of uov and enhance image when prompt is empty", default=False)

 args_parser.parser.add_argument("--always-download-new-model", action='store_true',
-                                help="Always download newer models ", default=False)
+                                help="Always download newer models", default=False)
+
+args_parser.parser.add_argument("--rebuild-hash-cache", help="Generates missing model and LoRA hashes.",
+                                type=int, nargs="?", metavar="CPU_NUM_THREADS", const=-1)

 args_parser.parser.set_defaults(
    disable_cuda_malloc=True,
@@ -27,6 +27,7 @@ progress {
  border-radius: 5px; /* Round the corners of the progress bar */
  background-color: #f3f3f3; /* Light grey background */
  width: 100%;
+  vertical-align: middle !important;
 }

 /* Style the progress bar container */
@@ -69,30 +70,39 @@ progress::after {
  height: 30px !important;
 }

-.type_row{
-  height: 80px !important;
+.progress-bar span {
+    text-align: right;
+    width: 215px;
+}
+div:has(> #positive_prompt) {
+    border: none;
 }

-.type_row_half{
-  height: 32px !important;
+#positive_prompt {
+    padding: 1px;
+    background: var(--background-fill-primary);
 }

-.scroll-hide{
-  resize: none !important;
+.type_row {
+  height: 84px !important;
 }

-.refresh_button{
+.type_row_half {
+  height: 34px !important;
+}
+
+.refresh_button {
  border: none !important;
  background: none !important;
  font-size: none !important;
  box-shadow: none !important;
 }

-.advanced_check_row{
-  width: 250px !important;
+.advanced_check_row {
+  width: 330px !important;
 }

-.min_check{
+.min_check {
  min-width: min(1px, 100%) !important;
 }

@@ -101,10 +111,14 @@ progress::after {
  overflow: auto !important;
 }

-.aspect_ratios label {
+.performance_selection label {
    width: 140px !important;
 }

+.aspect_ratios label {
+    flex: calc(50% - 5px) !important;
+}
+
 .aspect_ratios label span {
    white-space: nowrap !important;
 }
@@ -393,4 +407,12 @@ progress::after {
  text-align: center;
  border-radius: 5px 5px 0px 0px;
  display: none; /* remove this to enable tooltip in preview image */
+}
+
+#inpaint_canvas .canvas-tooltip-info {
+  top: 2px;
+}
+
+#inpaint_brush_color input[type=color]{
+  background: none;
 }
@@ -1,12 +1,10 @@
-version: '3.9'
-
 volumes:
  fooocus-data:

 services:
  app:
    build: .
-    image: fooocus
+    image: ghcr.io/lllyasviel/fooocus
    ports:
     - "7865:7865"
    environment:
@@ -1,35 +1,99 @@
 # Fooocus on Docker

-The docker image is based on NVIDIA CUDA 12.3 and PyTorch 2.0, see [Dockerfile](Dockerfile) and [requirements_docker.txt](requirements_docker.txt) for details.
+The docker image is based on NVIDIA CUDA 12.4 and PyTorch 2.1, see [Dockerfile](Dockerfile) and [requirements_docker.txt](requirements_docker.txt) for details.
+
+## Requirements
+
+- A computer with specs good enough to run Fooocus, and proprietary Nvidia drivers
+- Docker, Docker Compose, or Podman

 ## Quick start

-**This is just an easy way for testing. Please find more information in the [notes](#notes).**
+**More information in the [notes](#notes).**
+
+### Running with Docker Compose

 1. Clone this repository
-2. Build the image with `docker compose build`
-3. Run the docker container with `docker compose up`. Building the image takes some time.
+2. Run the docker container with `docker compose up`.
+
+### Running with Docker
+
+```sh
+docker run -p 7865:7865 -v fooocus-data:/content/data -it \
+--gpus all \
+-e CMDARGS=--listen \
+-e DATADIR=/content/data \
+-e config_path=/content/data/config.txt \
+-e config_example_path=/content/data/config_modification_tutorial.txt \
+-e path_checkpoints=/content/data/models/checkpoints/ \
+-e path_loras=/content/data/models/loras/ \
+-e path_embeddings=/content/data/models/embeddings/ \
+-e path_vae_approx=/content/data/models/vae_approx/ \
+-e path_upscale_models=/content/data/models/upscale_models/ \
+-e path_inpaint=/content/data/models/inpaint/ \
+-e path_controlnet=/content/data/models/controlnet/ \
+-e path_clip_vision=/content/data/models/clip_vision/ \
+-e path_fooocus_expansion=/content/data/models/prompt_expansion/fooocus_expansion/ \
+-e path_outputs=/content/app/outputs/ \
+ghcr.io/lllyasviel/fooocus
+```
+### Running with Podman
+
+```sh
+podman run -p 7865:7865 -v fooocus-data:/content/data -it \
+--security-opt=no-new-privileges --cap-drop=ALL --security-opt label=type:nvidia_container_t --device=nvidia.com/gpu=all \
+-e CMDARGS=--listen \
+-e DATADIR=/content/data \
+-e config_path=/content/data/config.txt \
+-e config_example_path=/content/data/config_modification_tutorial.txt \
+-e path_checkpoints=/content/data/models/checkpoints/ \
+-e path_loras=/content/data/models/loras/ \
+-e path_embeddings=/content/data/models/embeddings/ \
+-e path_vae_approx=/content/data/models/vae_approx/ \
+-e path_upscale_models=/content/data/models/upscale_models/ \
+-e path_inpaint=/content/data/models/inpaint/ \
+-e path_controlnet=/content/data/models/controlnet/ \
+-e path_clip_vision=/content/data/models/clip_vision/ \
+-e path_fooocus_expansion=/content/data/models/prompt_expansion/fooocus_expansion/ \
+-e path_outputs=/content/app/outputs/ \
+ghcr.io/lllyasviel/fooocus
+```

 When you see the message  `Use the app with http://0.0.0.0:7865/` in the console, you can access the URL in your browser.

-Your models and outputs are stored in the `fooocus-data` volume, which, depending on OS, is stored in `/var/lib/docker/volumes`.
+Your models and outputs are stored in the `fooocus-data` volume, which, depending on OS, is stored in `/var/lib/docker/volumes/` (or `~/.local/share/containers/storage/volumes/` when using `podman`).
+
+## Building the container locally
+
+Clone the repository first, and open a terminal in the folder.
+
+Build with `docker`:
+```sh
+docker build . -t fooocus
+```
+
+Build with `podman`:
+```sh
+podman build . -t fooocus
+```

 ## Details

-### Update the container manually
+### Update the container manually (`docker compose`)

 When you are using `docker compose up` continuously, the container is not updated to the latest version of Fooocus automatically.
 Run `git pull` before executing `docker compose build --no-cache` to build an image with the latest Fooocus version.
 You can then start it with `docker compose up`

 ### Import models, outputs
-If you want to import files from models or the outputs folder, you can uncomment the following settings in the [docker-compose.yml](docker-compose.yml):
+
+If you want to import files from models or the outputs folder, you can add the following bind mounts in the [docker-compose.yml](docker-compose.yml) or your preferred method of running the container:
 ```
 #- ./models:/import/models   # Once you import files, you don't need to mount again.
 #- ./outputs:/import/outputs  # Once you import files, you don't need to mount again.
 ```
-After running `docker compose up`, your files will be copied into `/content/data/models` and `/content/data/outputs`
-Since `/content/data` is a persistent volume folder, your files will be persisted even when you re-run `docker compose up --build` without above volume settings.
+After running the container, your files will be copied into `/content/data/models` and `/content/data/outputs`
+Since `/content/data` is a persistent volume folder, your files will be persisted even when you re-run the container without the above mounts.


 ### Paths inside the container
@@ -0,0 +1,24 @@
+# https://github.com/sail-sg/EditAnything/blob/main/sam2groundingdino_edit.py
+
+import numpy as np
+from PIL import Image
+
+from extras.inpaint_mask import SAMOptions, generate_mask_from_image
+
+original_image = Image.open('cat.webp')
+image = np.array(original_image, dtype=np.uint8)
+
+sam_options = SAMOptions(
+    dino_prompt='eye',
+    dino_box_threshold=0.3,
+    dino_text_threshold=0.25,
+    dino_erode_or_dilate=0,
+    dino_debug=False,
+    max_detections=2,
+    model_type='vit_b'
+)
+
+mask_image, _, _, _ = generate_mask_from_image(image, sam_options=sam_options)
+
+merged_masks_img = Image.fromarray(mask_image)
+merged_masks_img.show()
@@ -0,0 +1,43 @@
+batch_size = 1
+modelname = "groundingdino"
+backbone = "swin_T_224_1k"
+position_embedding = "sine"
+pe_temperatureH = 20
+pe_temperatureW = 20
+return_interm_indices = [1, 2, 3]
+backbone_freeze_keywords = None
+enc_layers = 6
+dec_layers = 6
+pre_norm = False
+dim_feedforward = 2048
+hidden_dim = 256
+dropout = 0.0
+nheads = 8
+num_queries = 900
+query_dim = 4
+num_patterns = 0
+num_feature_levels = 4
+enc_n_points = 4
+dec_n_points = 4
+two_stage_type = "standard"
+two_stage_bbox_embed_share = False
+two_stage_class_embed_share = False
+transformer_activation = "relu"
+dec_pred_bbox_embed_share = True
+dn_box_noise_scale = 1.0
+dn_label_noise_ratio = 0.5
+dn_label_coef = 1.0
+dn_bbox_coef = 1.0
+embed_init_tgt = True
+dn_labelbook_size = 2000
+max_text_len = 256
+text_encoder_type = "bert-base-uncased"
+use_text_enhancer = True
+use_fusion_layer = True
+use_checkpoint = True
+use_transformer_ckpt = True
+use_text_cross_attention = True
+text_dropout = 0.0
+fusion_dropout = 0.0
+fusion_droppath = 0.1
+sub_sentence_present = True
@@ -0,0 +1,100 @@
+from typing import Tuple, List
+
+import ldm_patched.modules.model_management as model_management
+from ldm_patched.modules.model_patcher import ModelPatcher
+from modules.config import path_inpaint
+from modules.model_loader import load_file_from_url
+
+import numpy as np
+import supervision as sv
+import torch
+from groundingdino.util.inference import Model
+from groundingdino.util.inference import load_model, preprocess_caption, get_phrases_from_posmap
+
+
+class GroundingDinoModel(Model):
+    def __init__(self):
+        self.config_file = 'extras/GroundingDINO/config/GroundingDINO_SwinT_OGC.py'
+        self.model = None
+        self.load_device = torch.device('cpu')
+        self.offload_device = torch.device('cpu')
+
+    @torch.no_grad()
+    @torch.inference_mode()
+    def predict_with_caption(
+            self,
+            image: np.ndarray,
+            caption: str,
+            box_threshold: float = 0.35,
+            text_threshold: float = 0.25
+    ) -> Tuple[sv.Detections, torch.Tensor, torch.Tensor, List[str]]:
+        if self.model is None:
+            filename = load_file_from_url(
+                url="https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha/groundingdino_swint_ogc.pth",
+                file_name='groundingdino_swint_ogc.pth',
+                model_dir=path_inpaint)
+            model = load_model(model_config_path=self.config_file, model_checkpoint_path=filename)
+
+            self.load_device = model_management.text_encoder_device()
+            self.offload_device = model_management.text_encoder_offload_device()
+
+            model.to(self.offload_device)
+
+            self.model = ModelPatcher(model, load_device=self.load_device, offload_device=self.offload_device)
+
+        model_management.load_model_gpu(self.model)
+
+        processed_image = GroundingDinoModel.preprocess_image(image_bgr=image).to(self.load_device)
+        boxes, logits, phrases = predict(
+            model=self.model,
+            image=processed_image,
+            caption=caption,
+            box_threshold=box_threshold,
+            text_threshold=text_threshold,
+            device=self.load_device)
+        source_h, source_w, _ = image.shape
+        detections = GroundingDinoModel.post_process_result(
+            source_h=source_h,
+            source_w=source_w,
+            boxes=boxes,
+            logits=logits)
+        return detections, boxes, logits, phrases
+
+
+def predict(
+        model,
+        image: torch.Tensor,
+        caption: str,
+        box_threshold: float,
+        text_threshold: float,
+        device: str = "cuda"
+) -> Tuple[torch.Tensor, torch.Tensor, List[str]]:
+    caption = preprocess_caption(caption=caption)
+
+    # override to use model wrapped by patcher
+    model = model.model.to(device)
+    image = image.to(device)
+
+    with torch.no_grad():
+        outputs = model(image[None], captions=[caption])
+
+    prediction_logits = outputs["pred_logits"].cpu().sigmoid()[0]  # prediction_logits.shape = (nq, 256)
+    prediction_boxes = outputs["pred_boxes"].cpu()[0]  # prediction_boxes.shape = (nq, 4)
+
+    mask = prediction_logits.max(dim=1)[0] > box_threshold
+    logits = prediction_logits[mask]  # logits.shape = (n, 256)
+    boxes = prediction_boxes[mask]  # boxes.shape = (n, 4)
+
+    tokenizer = model.tokenizer
+    tokenized = tokenizer(caption)
+
+    phrases = [
+        get_phrases_from_posmap(logit > text_threshold, tokenized, tokenizer).replace('.', '')
+        for logit
+        in logits
+    ]
+
+    return boxes, logits.max(dim=1)[0], phrases
+
+
+default_groundingdino = GroundingDinoModel().predict_with_caption
@@ -41,7 +41,7 @@ class Censor:
        model_management.load_model_gpu(self.safety_checker_model)

        single = False
-        if not isinstance(images, list) or isinstance(images, np.ndarray):
+        if not isinstance(images, (list, np.ndarray)):
            images = [images]
            single = True

@@ -0,0 +1,130 @@
+import sys
+
+import modules.config
+import numpy as np
+import torch
+from extras.GroundingDINO.util.inference import default_groundingdino
+from extras.sam.predictor import SamPredictor
+from rembg import remove, new_session
+from segment_anything import sam_model_registry
+from segment_anything.utils.amg import remove_small_regions
+
+
+class SAMOptions:
+    def __init__(self,
+                 # GroundingDINO
+                 dino_prompt: str = '',
+                 dino_box_threshold=0.3,
+                 dino_text_threshold=0.25,
+                 dino_erode_or_dilate=0,
+                 dino_debug=False,
+
+                 # SAM
+                 max_detections=2,
+                 model_type='vit_b'
+                 ):
+        self.dino_prompt = dino_prompt
+        self.dino_box_threshold = dino_box_threshold
+        self.dino_text_threshold = dino_text_threshold
+        self.dino_erode_or_dilate = dino_erode_or_dilate
+        self.dino_debug = dino_debug
+        self.max_detections = max_detections
+        self.model_type = model_type
+
+
+def optimize_masks(masks: torch.Tensor) -> torch.Tensor:
+    """
+    removes small disconnected regions and holes
+    """
+    fine_masks = []
+    for mask in masks.to('cpu').numpy():  # masks: [num_masks, 1, h, w]
+        fine_masks.append(remove_small_regions(mask[0], 400, mode="holes")[0])
+    masks = np.stack(fine_masks, axis=0)[:, np.newaxis]
+    return torch.from_numpy(masks)
+
+
+def generate_mask_from_image(image: np.ndarray, mask_model: str = 'sam', extras=None,
+                             sam_options: SAMOptions | None = SAMOptions) -> tuple[np.ndarray | None, int | None, int | None, int | None]:
+    dino_detection_count = 0
+    sam_detection_count = 0
+    sam_detection_on_mask_count = 0
+
+    if image is None:
+        return None, dino_detection_count, sam_detection_count, sam_detection_on_mask_count
+
+    if extras is None:
+        extras = {}
+
+    if 'image' in image:
+        image = image['image']
+
+    if mask_model != 'sam' or sam_options is None:
+        result = remove(
+            image,
+            session=new_session(mask_model, **extras),
+            only_mask=True,
+            **extras
+        )
+
+        return result, dino_detection_count, sam_detection_count, sam_detection_on_mask_count
+
+    detections, boxes, logits, phrases = default_groundingdino(
+        image=image,
+        caption=sam_options.dino_prompt,
+        box_threshold=sam_options.dino_box_threshold,
+        text_threshold=sam_options.dino_text_threshold
+    )
+
+    H, W = image.shape[0], image.shape[1]
+    boxes = boxes * torch.Tensor([W, H, W, H])
+    boxes[:, :2] = boxes[:, :2] - boxes[:, 2:] / 2
+    boxes[:, 2:] = boxes[:, 2:] + boxes[:, :2]
+
+    sam_checkpoint = modules.config.download_sam_model(sam_options.model_type)
+    sam = sam_model_registry[sam_options.model_type](checkpoint=sam_checkpoint)
+
+    sam_predictor = SamPredictor(sam)
+    final_mask_tensor = torch.zeros((image.shape[0], image.shape[1]))
+    dino_detection_count = boxes.size(0)
+
+    if dino_detection_count > 0:
+        sam_predictor.set_image(image)
+
+        if sam_options.dino_erode_or_dilate != 0:
+            for index in range(boxes.size(0)):
+                assert boxes.size(1) == 4
+                boxes[index][0] -= sam_options.dino_erode_or_dilate
+                boxes[index][1] -= sam_options.dino_erode_or_dilate
+                boxes[index][2] += sam_options.dino_erode_or_dilate
+                boxes[index][3] += sam_options.dino_erode_or_dilate
+
+        if sam_options.dino_debug:
+            from PIL import ImageDraw, Image
+            debug_dino_image = Image.new("RGB", (image.shape[1], image.shape[0]), color="black")
+            draw = ImageDraw.Draw(debug_dino_image)
+            for box in boxes.numpy():
+                draw.rectangle(box.tolist(), fill="white")
+            return np.array(debug_dino_image), dino_detection_count, sam_detection_count, sam_detection_on_mask_count
+
+        transformed_boxes = sam_predictor.transform.apply_boxes_torch(boxes, image.shape[:2])
+        masks, _, _ = sam_predictor.predict_torch(
+            point_coords=None,
+            point_labels=None,
+            boxes=transformed_boxes,
+            multimask_output=False,
+        )
+
+        masks = optimize_masks(masks)
+        sam_detection_count = len(masks)
+        if sam_options.max_detections == 0:
+            sam_options.max_detections = sys.maxsize
+        sam_objects = min(len(logits), sam_options.max_detections)
+        for obj_ind in range(sam_objects):
+            mask_tensor = masks[obj_ind][0]
+            final_mask_tensor += mask_tensor
+            sam_detection_on_mask_count += 1
+
+    final_mask_tensor = (final_mask_tensor > 0).to('cpu').numpy()
+    mask_image = np.dstack((final_mask_tensor, final_mask_tensor, final_mask_tensor)) * 255
+    mask_image = np.array(mask_image, dtype=np.uint8)
+    return mask_image, dino_detection_count, sam_detection_count, sam_detection_on_mask_count
@@ -0,0 +1,288 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import numpy as np
+import torch
+from ldm_patched.modules import model_management
+from ldm_patched.modules.model_patcher import ModelPatcher
+
+from segment_anything.modeling import Sam
+
+from typing import Optional, Tuple
+
+from segment_anything.utils.transforms import ResizeLongestSide
+
+
+class SamPredictor:
+    def __init__(
+        self,
+        model: Sam,
+        load_device=model_management.text_encoder_device(),
+        offload_device=model_management.text_encoder_offload_device()
+    ) -> None:
+        """
+        Uses SAM to calculate the image embedding for an image, and then
+        allow repeated, efficient mask prediction given prompts.
+
+        Arguments:
+          model (Sam): The model to use for mask prediction.
+        """
+        super().__init__()
+
+        self.load_device = load_device
+        self.offload_device = offload_device
+        # can't use model.half() here as slow_conv2d_cpu is not implemented for half
+        model.to(self.offload_device)
+
+        self.patcher = ModelPatcher(model, load_device=self.load_device, offload_device=self.offload_device)
+
+        self.transform = ResizeLongestSide(model.image_encoder.img_size)
+        self.reset_image()
+
+    def set_image(
+        self,
+        image: np.ndarray,
+        image_format: str = "RGB",
+    ) -> None:
+        """
+        Calculates the image embeddings for the provided image, allowing
+        masks to be predicted with the 'predict' method.
+
+        Arguments:
+          image (np.ndarray): The image for calculating masks. Expects an
+            image in HWC uint8 format, with pixel values in [0, 255].
+          image_format (str): The color format of the image, in ['RGB', 'BGR'].
+        """
+        assert image_format in [
+            "RGB",
+            "BGR",
+        ], f"image_format must be in ['RGB', 'BGR'], is {image_format}."
+        if image_format != self.patcher.model.image_format:
+            image = image[..., ::-1]
+
+        # Transform the image to the form expected by the model
+        input_image = self.transform.apply_image(image)
+        input_image_torch = torch.as_tensor(input_image, device=self.load_device)
+        input_image_torch = input_image_torch.permute(2, 0, 1).contiguous()[None, :, :, :]
+
+        self.set_torch_image(input_image_torch, image.shape[:2])
+
+    @torch.no_grad()
+    def set_torch_image(
+        self,
+        transformed_image: torch.Tensor,
+        original_image_size: Tuple[int, ...],
+    ) -> None:
+        """
+        Calculates the image embeddings for the provided image, allowing
+        masks to be predicted with the 'predict' method. Expects the input
+        image to be already transformed to the format expected by the model.
+
+        Arguments:
+          transformed_image (torch.Tensor): The input image, with shape
+            1x3xHxW, which has been transformed with ResizeLongestSide.
+          original_image_size (tuple(int, int)): The size of the image
+            before transformation, in (H, W) format.
+        """
+        assert (
+            len(transformed_image.shape) == 4
+            and transformed_image.shape[1] == 3
+            and max(*transformed_image.shape[2:]) == self.patcher.model.image_encoder.img_size
+        ), f"set_torch_image input must be BCHW with long side {self.patcher.model.image_encoder.img_size}."
+        self.reset_image()
+
+        self.original_size = original_image_size
+        self.input_size = tuple(transformed_image.shape[-2:])
+        model_management.load_model_gpu(self.patcher)
+        input_image = self.patcher.model.preprocess(transformed_image.to(self.load_device))
+        self.features = self.patcher.model.image_encoder(input_image)
+        self.is_image_set = True
+
+    def predict(
+        self,
+        point_coords: Optional[np.ndarray] = None,
+        point_labels: Optional[np.ndarray] = None,
+        box: Optional[np.ndarray] = None,
+        mask_input: Optional[np.ndarray] = None,
+        multimask_output: bool = True,
+        return_logits: bool = False,
+    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        """
+        Predict masks for the given input prompts, using the currently set image.
+
+        Arguments:
+          point_coords (np.ndarray or None): A Nx2 array of point prompts to the
+            model. Each point is in (X,Y) in pixels.
+          point_labels (np.ndarray or None): A length N array of labels for the
+            point prompts. 1 indicates a foreground point and 0 indicates a
+            background point.
+          box (np.ndarray or None): A length 4 array given a box prompt to the
+            model, in XYXY format.
+          mask_input (np.ndarray): A low resolution mask input to the model, typically
+            coming from a previous prediction iteration. Has form 1xHxW, where
+            for SAM, H=W=256.
+          multimask_output (bool): If true, the model will return three masks.
+            For ambiguous input prompts (such as a single click), this will often
+            produce better masks than a single prediction. If only a single
+            mask is needed, the model's predicted quality score can be used
+            to select the best mask. For non-ambiguous prompts, such as multiple
+            input prompts, multimask_output=False can give better results.
+          return_logits (bool): If true, returns un-thresholded masks logits
+            instead of a binary mask.
+
+        Returns:
+          (np.ndarray): The output masks in CxHxW format, where C is the
+            number of masks, and (H, W) is the original image size.
+          (np.ndarray): An array of length C containing the model's
+            predictions for the quality of each mask.
+          (np.ndarray): An array of shape CxHxW, where C is the number
+            of masks and H=W=256. These low resolution logits can be passed to
+            a subsequent iteration as mask input.
+        """
+        if not self.is_image_set:
+            raise RuntimeError("An image must be set with .set_image(...) before mask prediction.")
+
+        # Transform input prompts
+        coords_torch, labels_torch, box_torch, mask_input_torch = None, None, None, None
+        if point_coords is not None:
+            assert (
+                point_labels is not None
+            ), "point_labels must be supplied if point_coords is supplied."
+            point_coords = self.transform.apply_coords(point_coords, self.original_size)
+            coords_torch = torch.as_tensor(point_coords, dtype=torch.float, device=self.load_device)
+            labels_torch = torch.as_tensor(point_labels, dtype=torch.int, device=self.load_device)
+            coords_torch, labels_torch = coords_torch[None, :, :], labels_torch[None, :]
+        if box is not None:
+            box = self.transform.apply_boxes(box, self.original_size)
+            box_torch = torch.as_tensor(box, dtype=torch.float, device=self.load_device)
+            box_torch = box_torch[None, :]
+        if mask_input is not None:
+            mask_input_torch = torch.as_tensor(mask_input, dtype=torch.float, device=self.load_device)
+            mask_input_torch = mask_input_torch[None, :, :, :]
+
+        masks, iou_predictions, low_res_masks = self.predict_torch(
+            coords_torch,
+            labels_torch,
+            box_torch,
+            mask_input_torch,
+            multimask_output,
+            return_logits=return_logits,
+        )
+
+        masks = masks[0].detach().cpu().numpy()
+        iou_predictions = iou_predictions[0].detach().cpu().numpy()
+        low_res_masks = low_res_masks[0].detach().cpu().numpy()
+        return masks, iou_predictions, low_res_masks
+
+    @torch.no_grad()
+    def predict_torch(
+        self,
+        point_coords: Optional[torch.Tensor],
+        point_labels: Optional[torch.Tensor],
+        boxes: Optional[torch.Tensor] = None,
+        mask_input: Optional[torch.Tensor] = None,
+        multimask_output: bool = True,
+        return_logits: bool = False,
+    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        """
+        Predict masks for the given input prompts, using the currently set image.
+        Input prompts are batched torch tensors and are expected to already be
+        transformed to the input frame using ResizeLongestSide.
+
+        Arguments:
+          point_coords (torch.Tensor or None): A BxNx2 array of point prompts to the
+            model. Each point is in (X,Y) in pixels.
+          point_labels (torch.Tensor or None): A BxN array of labels for the
+            point prompts. 1 indicates a foreground point and 0 indicates a
+            background point.
+          box (np.ndarray or None): A Bx4 array given a box prompt to the
+            model, in XYXY format.
+          mask_input (np.ndarray): A low resolution mask input to the model, typically
+            coming from a previous prediction iteration. Has form Bx1xHxW, where
+            for SAM, H=W=256. Masks returned by a previous iteration of the
+            predict method do not need further transformation.
+          multimask_output (bool): If true, the model will return three masks.
+            For ambiguous input prompts (such as a single click), this will often
+            produce better masks than a single prediction. If only a single
+            mask is needed, the model's predicted quality score can be used
+            to select the best mask. For non-ambiguous prompts, such as multiple
+            input prompts, multimask_output=False can give better results.
+          return_logits (bool): If true, returns un-thresholded masks logits
+            instead of a binary mask.
+
+        Returns:
+          (torch.Tensor): The output masks in BxCxHxW format, where C is the
+            number of masks, and (H, W) is the original image size.
+          (torch.Tensor): An array of shape BxC containing the model's
+            predictions for the quality of each mask.
+          (torch.Tensor): An array of shape BxCxHxW, where C is the number
+            of masks and H=W=256. These low res logits can be passed to
+            a subsequent iteration as mask input.
+        """
+        if not self.is_image_set:
+            raise RuntimeError("An image must be set with .set_image(...) before mask prediction.")
+
+        if point_coords is not None:
+            points = (point_coords.to(self.load_device), point_labels.to(self.load_device))
+        else:
+            points = None
+
+        # load
+        if boxes is not None:
+            boxes = boxes.to(self.load_device)
+        if mask_input is not None:
+            mask_input = mask_input.to(self.load_device)
+        model_management.load_model_gpu(self.patcher)
+
+        # Embed prompts
+        sparse_embeddings, dense_embeddings = self.patcher.model.prompt_encoder(
+            points=points,
+            boxes=boxes,
+            masks=mask_input,
+        )
+
+        # Predict masks
+        low_res_masks, iou_predictions = self.patcher.model.mask_decoder(
+            image_embeddings=self.features,
+            image_pe=self.patcher.model.prompt_encoder.get_dense_pe(),
+            sparse_prompt_embeddings=sparse_embeddings,
+            dense_prompt_embeddings=dense_embeddings,
+            multimask_output=multimask_output,
+        )
+
+        # Upscale the masks to the original image resolution
+        masks = self.patcher.model.postprocess_masks(low_res_masks, self.input_size, self.original_size)
+
+        if not return_logits:
+            masks = masks > self.patcher.model.mask_threshold
+
+        return masks, iou_predictions, low_res_masks
+
+    def get_image_embedding(self) -> torch.Tensor:
+        """
+        Returns the image embeddings for the currently set image, with
+        shape 1xCxHxW, where C is the embedding dimension and (H,W) are
+        the embedding spatial dimension of SAM (typically C=256, H=W=64).
+        """
+        if not self.is_image_set:
+            raise RuntimeError(
+                "An image must be set with .set_image(...) to generate an embedding."
+            )
+        assert self.features is not None, "Features must exist if an image has been set."
+        return self.features
+
+    @property
+    def device(self) -> torch.device:
+        return self.patcher.model.device
+
+    def reset_image(self) -> None:
+        """Resets the currently set image."""
+        self.is_image_set = False
+        self.features = None
+        self.orig_h = None
+        self.orig_w = None
+        self.input_h = None
+        self.input_w = None
@@ -1 +1 @@
-version = '2.4.0-rc2'
+version = '2.5.0-rc1'
@@ -80,6 +80,15 @@ function refresh_style_localization() {
    processNode(document.querySelector('.style_selections'));
 }

+function refresh_aspect_ratios_label(value) {
+    label = document.querySelector('#aspect_ratios_accordion div span');
+    translation = getTranslation("Aspect Ratios");
+    if (typeof translation == "undefined") {
+        translation = "Aspect Ratios";
+    }
+    label.textContent = translation + " " + htmlDecode(value);
+}
+
 function localizeWholePage() {
    processNode(gradioApp());

@@ -256,3 +256,8 @@ function set_theme(theme) {
        window.location.replace(gradioURL + '?__theme=' + theme);
    }
 }
+
+function htmlDecode(input) {
+  var doc = new DOMParser().parseFromString(input, "text/html");
+  return doc.documentElement.textContent;
+}
@@ -642,4 +642,5 @@ onUiLoaded(async() => {
    }

    applyZoomAndPan("#inpaint_canvas");
+    applyZoomAndPan("#inpaint_mask_canvas");
 });
@@ -9,8 +9,16 @@
    "Advanced": "Advanced",
    "Upscale or Variation": "Upscale or Variation",
    "Image Prompt": "Image Prompt",
-    "Inpaint or Outpaint (beta)": "Inpaint or Outpaint (beta)",
-    "Drag above image to here": "Drag above image to here",
+    "Inpaint or Outpaint": "Inpaint or Outpaint",
+    "Outpaint Direction": "Outpaint Direction",
+    "Enable Advanced Masking Features": "Enable Advanced Masking Features",
+    "Method": "Method",
+    "Describe": "Describe",
+    "Content Type": "Content Type",
+    "Photograph": "Photograph",
+    "Art/Anime": "Art/Anime",
+    "Describe this Image into Prompt": "Describe this Image into Prompt",
+    "Image Size and Recommended Size": "Image Size and Recommended Size",
    "Upscale or Variation:": "Upscale or Variation:",
    "Disabled": "Disabled",
    "Vary (Subtle)": "Vary (Subtle)",
@@ -18,7 +26,7 @@
    "Upscale (1.5x)": "Upscale (1.5x)",
    "Upscale (2x)": "Upscale (2x)",
    "Upscale (Fast 2x)": "Upscale (Fast 2x)",
-    "\ud83d\udcd4 Document": "\uD83D\uDCD4 Document",
+    "\ud83d\udcd4 Documentation": "\uD83D\uDCD4 Documentation",
    "Image": "Image",
    "Stop At": "Stop At",
    "Weight": "Weight",
@@ -37,8 +45,11 @@
    "Top": "Top",
    "Bottom": "Bottom",
    "* \"Inpaint or Outpaint\" is powered by the sampler \"DPMPP Fooocus Seamless 2M SDE Karras Inpaint Sampler\" (beta)": "* \"Inpaint or Outpaint\" is powered by the sampler \"DPMPP Fooocus Seamless 2M SDE Karras Inpaint Sampler\" (beta)",
-    "Setting": "Setting",
+    "Advanced options": "Advanced options",
+    "Generate mask from image": "Generate mask from image",
+    "Settings": "Settings",
    "Style": "Style",
+    "Styles": "Styles",
    "Preset": "Preset",
    "Performance": "Performance",
    "Speed": "Speed",
@@ -272,7 +283,7 @@
    "Volumetric Lighting": "Volumetric Lighting",
    "Watercolor 2": "Watercolor 2",
    "Whimsical And Playful": "Whimsical And Playful",
-    "Model": "Model",
+    "Models": "Models",
    "Base Model (SDXL only)": "Base Model (SDXL only)",
    "sd_xl_base_1.0_0.9vae.safetensors": "sd_xl_base_1.0_0.9vae.safetensors",
    "bluePencilXL_v009.safetensors": "bluePencilXL_v009.safetensors",
@@ -313,6 +324,8 @@
    "vae": "vae",
    "CFG Mimicking from TSNR": "CFG Mimicking from TSNR",
    "Enabling Fooocus's implementation of CFG mimicking for TSNR (effective when real CFG > mimicked CFG).": "Enabling Fooocus's implementation of CFG mimicking for TSNR (effective when real CFG > mimicked CFG).",
+    "CLIP Skip": "CLIP Skip",
+    "Bypass CLIP layers to avoid overfitting (use 1 to not skip any layers, 2 is recommended).": "Bypass CLIP layers to avoid overfitting (use 1 to not skip any layers, 2 is recommended).",
    "Sampler": "Sampler",
    "dpmpp_2m_sde_gpu": "dpmpp_2m_sde_gpu",
    "Only effective in non-inpaint mode.": "Only effective in non-inpaint mode.",
@@ -358,10 +371,14 @@
    "Disable preview during generation.": "Disable preview during generation.",
    "Disable Intermediate Results": "Disable Intermediate Results",
    "Disable intermediate results during generation, only show final gallery.": "Disable intermediate results during generation, only show final gallery.",
+    "Debug Inpaint Preprocessing": "Debug Inpaint Preprocessing",
+    "Debug GroundingDINO": "Debug GroundingDINO",
+    "Used for SAM object detection and box generation": "Used for SAM object detection and box generation",
+    "GroundingDINO Box Erode or Dilate": "GroundingDINO Box Erode or Dilate",
    "Inpaint Engine": "Inpaint Engine",
    "v1": "v1",
-    "Version of Fooocus inpaint model": "Version of Fooocus inpaint model",
    "v2.5": "v2.5",
+    "v2.6": "v2.6",
    "Control Debug": "Control Debug",
    "Debug Preprocessors": "Debug Preprocessors",
    "Mixing Image Prompt and Vary/Upscale": "Mixing Image Prompt and Vary/Upscale",
@@ -384,12 +401,81 @@
    "Fooocus Enhance": "Fooocus Enhance",
    "Fooocus Cinematic": "Fooocus Cinematic",
    "Fooocus Sharp": "Fooocus Sharp",
-    "Drag any image generated by Fooocus here": "Drag any image generated by Fooocus here",
+    "For images created by Fooocus": "For images created by Fooocus",
    "Metadata": "Metadata",
    "Apply Metadata": "Apply Metadata",
    "Metadata Scheme": "Metadata Scheme",
    "Image Prompt parameters are not included. Use png and a1111 for compatibility with Civitai.": "Image Prompt parameters are not included. Use png and a1111 for compatibility with Civitai.",
    "fooocus (json)": "fooocus (json)",
    "a1111 (plain text)": "a1111 (plain text)",
-    "Unsupported image type in input": "Unsupported image type in input"
+    "Unsupported image type in input": "Unsupported image type in input",
+    "Enhance": "Enhance",
+    "Detection prompt": "Detection prompt",
+    "Detection Prompt Quick List": "Detection Prompt Quick List",
+    "Maximum number of detections": "Maximum number of detections",
+    "Use with Enhance, skips image generation": "Use with Enhance, skips image generation",
+    "Order of Processing": "Order of Processing",
+    "Use before to enhance small details and after to enhance large areas.": "Use before to enhance small details and after to enhance large areas.",
+    "Before First Enhancement": "Before First Enhancement",
+    "After Last Enhancement": "After Last Enhancement",
+    "Prompt Type": "Prompt Type",
+    "Choose which prompt to use for Upscale or Variation.": "Choose which prompt to use for Upscale or Variation.",
+    "Original Prompts": "Original Prompts",
+    "Last Filled Enhancement Prompts": "Last Filled Enhancement Prompts",
+    "Enable": "Enable",
+    "Describe what you want to detect.": "Describe what you want to detect.",
+    "Enhancement positive prompt": "Enhancement positive prompt",
+    "Uses original prompt instead if empty.": "Uses original prompt instead if empty.",
+    "Enhancement negative prompt": "Enhancement negative prompt",
+    "Uses original negative prompt instead if empty.": "Uses original negative prompt instead if empty.",
+    "Detection": "Detection",
+    "u2net": "u2net",
+    "u2netp": "u2netp",
+    "u2net_human_seg": "u2net_human_seg",
+    "u2net_cloth_seg": "u2net_cloth_seg",
+    "silueta": "silueta",
+    "isnet-general-use": "isnet-general-use",
+    "isnet-anime": "isnet-anime",
+    "sam": "sam",
+    "Mask generation model": "Mask generation model",
+    "Cloth category": "Cloth category",
+    "Use singular whenever possible": "Use singular whenever possible",
+    "full": "full",
+    "upper": "upper",
+    "lower": "lower",
+    "SAM Options": "SAM Options",
+    "SAM model": "SAM model",
+    "vit_b": "vit_b",
+    "vit_l": "vit_l",
+    "vit_h": "vit_h",
+    "Box Threshold": "Box Threshold",
+    "Text Threshold": "Text Threshold",
+    "Set to 0 to detect all": "Set to 0 to detect all",
+    "Inpaint": "Inpaint",
+    "Inpaint or Outpaint (default)": "Inpaint or Outpaint (default)",
+    "Improve Detail (face, hand, eyes, etc.)": "Improve Detail (face, hand, eyes, etc.)",
+    "Modify Content (add objects, change background, etc.)": "Modify Content (add objects, change background, etc.)",
+    "Disable initial latent in inpaint": "Disable initial latent in inpaint",
+    "Version of Fooocus inpaint model. If set, use performance Quality or Speed (no performance LoRAs) for best results.": "Version of Fooocus inpaint model. If set, use performance Quality or Speed (no performance LoRAs) for best results.",
+    "Inpaint Denoising Strength": "Inpaint Denoising Strength",
+    "Same as the denoising strength in A1111 inpaint. Only used in inpaint, not used in outpaint. (Outpaint always use 1.0)": "Same as the denoising strength in A1111 inpaint. Only used in inpaint, not used in outpaint. (Outpaint always use 1.0)",
+    "Inpaint Respective Field": "Inpaint Respective Field",
+    "The area to inpaint. Value 0 is same as \"Only Masked\" in A1111. Value 1 is same as \"Whole Image\" in A1111. Only used in inpaint, not used in outpaint. (Outpaint always use 1.0)": "The area to inpaint. Value 0 is same as \"Only Masked\" in A1111. Value 1 is same as \"Whole Image\" in A1111. Only used in inpaint, not used in outpaint. (Outpaint always use 1.0)",
+    "Mask Erode or Dilate": "Mask Erode or Dilate",
+    "Positive value will make white area in the mask larger, negative value will make white area smaller. (default is 0, always processed before any mask invert)": "Positive value will make white area in the mask larger, negative value will make white area smaller. (default is 0, always processed before any mask invert)",
+    "Invert Mask When Generating": "Invert Mask When Generating",
+    "Debug Enhance Masks": "Debug Enhance Masks",
+    "Show enhance masks in preview and final results": "Show enhance masks in preview and final results",
+    "Use GroundingDINO boxes instead of more detailed SAM masks": "Use GroundingDINO boxes instead of more detailed SAM masks",
+    "highly detailed face": "highly detailed face",
+    "detailed girl face": "detailed girl face",
+    "detailed man face": "detailed man face",
+    "detailed hand": "detailed hand",
+    "beautiful eyes": "beautiful eyes",
+    "face": "face",
+    "eye": "eye",
+    "mouth": "mouth",
+    "hair": "hair",
+    "hand": "hand",
+    "body": "body"
 }
@@ -21,6 +21,7 @@ import fooocus_version
 from build_launcher import build_launcher
 from modules.launch_util import is_installed, run, python, run_pip, requirements_met, delete_folder_content
 from modules.model_loader import load_file_from_url
+from modules import config

 REINSTALL_ALL = False
 TRY_INSTALL_XFORMERS = False
@@ -85,6 +86,7 @@ if args.hf_mirror is not None :
    print("Set hf_mirror to:", args.hf_mirror)

 from modules import config
+os.environ["U2NET_HOME"] = config.path_inpaint

 os.environ['GRADIO_TEMP_DIR'] = config.temp_path

@@ -97,7 +99,7 @@ if config.temp_path_cleanup_on_launch:
        print(f"[Cleanup] Failed to delete content of temp dir.")


-def download_models(default_model, previous_default_models, checkpoint_downloads, embeddings_downloads, lora_downloads):
+def download_models(default_model, previous_default_models, checkpoint_downloads, embeddings_downloads, lora_downloads, vae_downloads):
    for file_name, url in vae_approx_filenames:
        load_file_from_url(url=url, model_dir=config.path_vae_approx, file_name=file_name)

@@ -129,12 +131,14 @@ def download_models(default_model, previous_default_models, checkpoint_downloads
        load_file_from_url(url=url, model_dir=config.path_embeddings, file_name=file_name)
    for file_name, url in lora_downloads.items():
        load_file_from_url(url=url, model_dir=config.paths_loras[0], file_name=file_name)
+    for file_name, url in vae_downloads.items():
+        load_file_from_url(url=url, model_dir=config.path_vae, file_name=file_name)

    return default_model, checkpoint_downloads


 config.default_base_model_name, config.checkpoint_downloads = download_models(
    config.default_base_model_name, config.previous_default_models, config.checkpoint_downloads,
-    config.embeddings_downloads, config.lora_downloads)
+    config.embeddings_downloads, config.lora_downloads, config.vae_downloads)

 from webui import *
@@ -107,8 +107,7 @@ class SDTurboScheduler:
    def get_sigmas(self, model, steps, denoise):
        start_step = 10 - int(10 * denoise)
        timesteps = torch.flip(torch.arange(1, 11) * 100 - 1, (0,))[start_step:start_step + steps]
-        ldm_patched.modules.model_management.load_models_gpu([model])
-        sigmas = model.model.model_sampling.sigma(timesteps)
+        sigmas = model.model_sampling.sigma(timesteps)
        sigmas = torch.cat([sigmas, sigmas.new_zeros([1])])
        return (sigmas, )

@@ -108,7 +108,7 @@ class ModelSamplingContinuousEDM:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
-                              "sampling": (["v_prediction", "eps"],),
+                              "sampling": (["v_prediction", "edm_playground_v2.5", "eps"],),
                              "sigma_max": ("FLOAT", {"default": 120.0, "min": 0.0, "max": 1000.0, "step":0.001, "round": False}),
                              "sigma_min": ("FLOAT", {"default": 0.002, "min": 0.0, "max": 1000.0, "step":0.001, "round": False}),
                              }}
@@ -121,17 +121,25 @@ class ModelSamplingContinuousEDM:
    def patch(self, model, sampling, sigma_max, sigma_min):
        m = model.clone()

+        latent_format = None
+        sigma_data = 1.0
        if sampling == "eps":
            sampling_type = ldm_patched.modules.model_sampling.EPS
        elif sampling == "v_prediction":
            sampling_type = ldm_patched.modules.model_sampling.V_PREDICTION
+        elif sampling == "edm_playground_v2.5":
+            sampling_type = ldm_patched.modules.model_sampling.EDM
+            sigma_data = 0.5
+            latent_format = ldm_patched.modules.latent_formats.SDXL_Playground_2_5()

        class ModelSamplingAdvanced(ldm_patched.modules.model_sampling.ModelSamplingContinuousEDM, sampling_type):
            pass

        model_sampling = ModelSamplingAdvanced(model.model.model_config)
-        model_sampling.set_sigma_range(sigma_min, sigma_max)
+        model_sampling.set_parameters(sigma_min, sigma_max, sigma_data)
        m.add_object_patch("model_sampling", model_sampling)
+        if latent_format is not None:
+            m.add_object_patch("latent_format", latent_format)
        return (m, )

 class RescaleCFG:
@@ -832,5 +832,77 @@ def sample_tcd(model, x, sigmas, extra_args=None, callback=None, disable=None, n
        if eta > 0 and sigmas[i + 1] > 0:
            noise = noise_sampler(sigmas[i], sigmas[i + 1])
            x = x / alpha_prod_s[i+1].sqrt() + noise * (sigmas[i+1]**2 + 1 - 1/alpha_prod_s[i+1]).sqrt()
+        else:
+            x *= torch.sqrt(1.0 + sigmas[i + 1] ** 2)
+
+    return x
+
+
+@torch.no_grad()
+def sample_restart(model, x, sigmas, extra_args=None, callback=None, disable=None, s_noise=1., restart_list=None):
+    """Implements restart sampling in Restart Sampling for Improving Generative Processes (2023)
+    Restart_list format: {min_sigma: [ restart_steps, restart_times, max_sigma]}
+    If restart_list is None: will choose restart_list automatically, otherwise will use the given restart_list
+    """
+    extra_args = {} if extra_args is None else extra_args
+    s_in = x.new_ones([x.shape[0]])
+    step_id = 0
+
+    def heun_step(x, old_sigma, new_sigma, second_order=True):
+        nonlocal step_id
+        denoised = model(x, old_sigma * s_in, **extra_args)
+        d = to_d(x, old_sigma, denoised)
+        if callback is not None:
+            callback({'x': x, 'i': step_id, 'sigma': new_sigma, 'sigma_hat': old_sigma, 'denoised': denoised})
+        dt = new_sigma - old_sigma
+        if new_sigma == 0 or not second_order:
+            # Euler method
+            x = x + d * dt
+        else:
+            # Heun's method
+            x_2 = x + d * dt
+            denoised_2 = model(x_2, new_sigma * s_in, **extra_args)
+            d_2 = to_d(x_2, new_sigma, denoised_2)
+            d_prime = (d + d_2) / 2
+            x = x + d_prime * dt
+        step_id += 1
+        return x
+
+    steps = sigmas.shape[0] - 1
+    if restart_list is None:
+        if steps >= 20:
+            restart_steps = 9
+            restart_times = 1
+            if steps >= 36:
+                restart_steps = steps // 4
+                restart_times = 2
+            sigmas = get_sigmas_karras(steps - restart_steps * restart_times, sigmas[-2].item(), sigmas[0].item(), device=sigmas.device)
+            restart_list = {0.1: [restart_steps + 1, restart_times, 2]}
+        else:
+            restart_list = {}
+
+    restart_list = {int(torch.argmin(abs(sigmas - key), dim=0)): value for key, value in restart_list.items()}
+
+    step_list = []
+    for i in range(len(sigmas) - 1):
+        step_list.append((sigmas[i], sigmas[i + 1]))
+        if i + 1 in restart_list:
+            restart_steps, restart_times, restart_max = restart_list[i + 1]
+            min_idx = i + 1
+            max_idx = int(torch.argmin(abs(sigmas - restart_max), dim=0))
+            if max_idx < min_idx:
+                sigma_restart = get_sigmas_karras(restart_steps, sigmas[min_idx].item(), sigmas[max_idx].item(), device=sigmas.device)[:-1]
+                while restart_times > 0:
+                    restart_times -= 1
+                    step_list.extend(zip(sigma_restart[:-1], sigma_restart[1:]))
+
+    last_sigma = None
+    for old_sigma, new_sigma in tqdm(step_list, disable=disable):
+        if last_sigma is None:
+            last_sigma = old_sigma
+        elif last_sigma < old_sigma:
+            x = x + torch.randn_like(x) * s_noise * (old_sigma ** 2 - last_sigma ** 2) ** 0.5
+        x = heun_step(x, old_sigma, new_sigma)
+        last_sigma = new_sigma

    return x
@@ -1,3 +1,4 @@
+import torch

 class LatentFormat:
    scale_factor = 1.0
@@ -34,6 +35,70 @@ class SDXL(LatentFormat):
                ]
        self.taesd_decoder_name = "taesdxl_decoder"

+class SDXL_Playground_2_5(LatentFormat):
+    def __init__(self):
+        self.scale_factor = 0.5
+        self.latents_mean = torch.tensor([-1.6574, 1.886, -1.383, 2.5155]).view(1, 4, 1, 1)
+        self.latents_std = torch.tensor([8.4927, 5.9022, 6.5498, 5.2299]).view(1, 4, 1, 1)
+
+        self.latent_rgb_factors = [
+                    #   R        G        B
+                    [ 0.3920,  0.4054,  0.4549],
+                    [-0.2634, -0.0196,  0.0653],
+                    [ 0.0568,  0.1687, -0.0755],
+                    [-0.3112, -0.2359, -0.2076]
+                ]
+        self.taesd_decoder_name = "taesdxl_decoder"
+
+    def process_in(self, latent):
+        latents_mean = self.latents_mean.to(latent.device, latent.dtype)
+        latents_std = self.latents_std.to(latent.device, latent.dtype)
+        return (latent - latents_mean) * self.scale_factor / latents_std
+
+    def process_out(self, latent):
+        latents_mean = self.latents_mean.to(latent.device, latent.dtype)
+        latents_std = self.latents_std.to(latent.device, latent.dtype)
+        return latent * latents_std / self.scale_factor + latents_mean
+
+
 class SD_X4(LatentFormat):
    def __init__(self):
        self.scale_factor = 0.08333
+        self.latent_rgb_factors = [
+            [-0.2340, -0.3863, -0.3257],
+            [ 0.0994,  0.0885, -0.0908],
+            [-0.2833, -0.2349, -0.3741],
+            [ 0.2523, -0.0055, -0.1651]
+        ]
+
+class SC_Prior(LatentFormat):
+    def __init__(self):
+        self.scale_factor = 1.0
+        self.latent_rgb_factors = [
+            [-0.0326, -0.0204, -0.0127],
+            [-0.1592, -0.0427,  0.0216],
+            [ 0.0873,  0.0638, -0.0020],
+            [-0.0602,  0.0442,  0.1304],
+            [ 0.0800, -0.0313, -0.1796],
+            [-0.0810, -0.0638, -0.1581],
+            [ 0.1791,  0.1180,  0.0967],
+            [ 0.0740,  0.1416,  0.0432],
+            [-0.1745, -0.1888, -0.1373],
+            [ 0.2412,  0.1577,  0.0928],
+            [ 0.1908,  0.0998,  0.0682],
+            [ 0.0209,  0.0365, -0.0092],
+            [ 0.0448, -0.0650, -0.1728],
+            [-0.1658, -0.1045, -0.1308],
+            [ 0.0542,  0.1545,  0.1325],
+            [-0.0352, -0.1672, -0.2541]
+        ]
+
+class SC_B(LatentFormat):
+    def __init__(self):
+        self.scale_factor = 1.0 / 0.43
+        self.latent_rgb_factors = [
+            [ 0.1121,  0.2006,  0.1023],
+            [-0.2093, -0.0222, -0.0195],
+            [-0.3087, -0.1535,  0.0366],
+            [ 0.0290, -0.1574, -0.4078]
+        ]
@@ -1,7 +1,7 @@
 import torch
-import numpy as np
 from ldm_patched.ldm.modules.diffusionmodules.util import make_beta_schedule
 import math
+import numpy as np

 class EPS:
    def calculate_input(self, sigma, noise):
@@ -12,12 +12,28 @@ class EPS:
        sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1))
        return model_input - model_output * sigma

+    def noise_scaling(self, sigma, noise, latent_image, max_denoise=False):
+        if max_denoise:
+            noise = noise * torch.sqrt(1.0 + sigma ** 2.0)
+        else:
+            noise = noise * sigma
+
+        noise += latent_image
+        return noise
+
+    def inverse_noise_scaling(self, sigma, latent):
+        return latent

 class V_PREDICTION(EPS):
    def calculate_denoised(self, sigma, model_output, model_input):
        sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1))
        return model_input * self.sigma_data ** 2 / (sigma ** 2 + self.sigma_data ** 2) - model_output * sigma * self.sigma_data / (sigma ** 2 + self.sigma_data ** 2) ** 0.5

+class EDM(V_PREDICTION):
+    def calculate_denoised(self, sigma, model_output, model_input):
+        sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1))
+        return model_input * self.sigma_data ** 2 / (sigma ** 2 + self.sigma_data ** 2) + model_output * sigma * self.sigma_data / (sigma ** 2 + self.sigma_data ** 2) ** 0.5
+

 class ModelSamplingDiscrete(torch.nn.Module):
    def __init__(self, model_config=None):
@@ -42,21 +58,25 @@ class ModelSamplingDiscrete(torch.nn.Module):
        else:
            betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
        alphas = 1. - betas
-        alphas_cumprod = torch.tensor(np.cumprod(alphas, axis=0), dtype=torch.float32)
-        # alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])
+        alphas_cumprod = torch.cumprod(alphas, dim=0)

        timesteps, = betas.shape
        self.num_timesteps = int(timesteps)
        self.linear_start = linear_start
        self.linear_end = linear_end

+        # self.register_buffer('betas', torch.tensor(betas, dtype=torch.float32))
+        # self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32))
+        # self.register_buffer('alphas_cumprod_prev', torch.tensor(alphas_cumprod_prev, dtype=torch.float32))
+
        sigmas = ((1 - alphas_cumprod) / alphas_cumprod) ** 0.5
+        alphas_cumprod = torch.tensor(np.cumprod(alphas, axis=0), dtype=torch.float32)
        self.set_sigmas(sigmas)
        self.set_alphas_cumprod(alphas_cumprod.float())

    def set_sigmas(self, sigmas):
-        self.register_buffer('sigmas', sigmas)
-        self.register_buffer('log_sigmas', sigmas.log())
+        self.register_buffer('sigmas', sigmas.float())
+        self.register_buffer('log_sigmas', sigmas.log().float())

    def set_alphas_cumprod(self, alphas_cumprod):
        self.register_buffer("alphas_cumprod", alphas_cumprod.float())
@@ -94,8 +114,6 @@ class ModelSamplingDiscrete(torch.nn.Module):
 class ModelSamplingContinuousEDM(torch.nn.Module):
    def __init__(self, model_config=None):
        super().__init__()
-        self.sigma_data = 1.0
-
        if model_config is not None:
            sampling_settings = model_config.sampling_settings
        else:
@@ -103,9 +121,11 @@ class ModelSamplingContinuousEDM(torch.nn.Module):

        sigma_min = sampling_settings.get("sigma_min", 0.002)
        sigma_max = sampling_settings.get("sigma_max", 120.0)
-        self.set_sigma_range(sigma_min, sigma_max)
+        sigma_data = sampling_settings.get("sigma_data", 1.0)
+        self.set_parameters(sigma_min, sigma_max, sigma_data)

-    def set_sigma_range(self, sigma_min, sigma_max):
+    def set_parameters(self, sigma_min, sigma_max, sigma_data):
+        self.sigma_data = sigma_data
        sigmas = torch.linspace(math.log(sigma_min), math.log(sigma_max), 1000).exp()

        self.register_buffer('sigmas', sigmas) #for compatibility with some schedulers
@@ -134,3 +154,56 @@ class ModelSamplingContinuousEDM(torch.nn.Module):

        log_sigma_min = math.log(self.sigma_min)
        return math.exp((math.log(self.sigma_max) - log_sigma_min) * percent + log_sigma_min)
+
+class StableCascadeSampling(ModelSamplingDiscrete):
+    def __init__(self, model_config=None):
+        super().__init__()
+
+        if model_config is not None:
+            sampling_settings = model_config.sampling_settings
+        else:
+            sampling_settings = {}
+
+        self.set_parameters(sampling_settings.get("shift", 1.0))
+
+    def set_parameters(self, shift=1.0, cosine_s=8e-3):
+        self.shift = shift
+        self.cosine_s = torch.tensor(cosine_s)
+        self._init_alpha_cumprod = torch.cos(self.cosine_s / (1 + self.cosine_s) * torch.pi * 0.5) ** 2
+
+        #This part is just for compatibility with some schedulers in the codebase
+        self.num_timesteps = 10000
+        sigmas = torch.empty((self.num_timesteps), dtype=torch.float32)
+        for x in range(self.num_timesteps):
+            t = (x + 1) / self.num_timesteps
+            sigmas[x] = self.sigma(t)
+
+        self.set_sigmas(sigmas)
+
+    def sigma(self, timestep):
+        alpha_cumprod = (torch.cos((timestep + self.cosine_s) / (1 + self.cosine_s) * torch.pi * 0.5) ** 2 / self._init_alpha_cumprod)
+
+        if self.shift != 1.0:
+            var = alpha_cumprod
+            logSNR = (var/(1-var)).log()
+            logSNR += 2 * torch.log(1.0 / torch.tensor(self.shift))
+            alpha_cumprod = logSNR.sigmoid()
+
+        alpha_cumprod = alpha_cumprod.clamp(0.0001, 0.9999)
+        return ((1 - alpha_cumprod) / alpha_cumprod) ** 0.5
+
+    def timestep(self, sigma):
+        var = 1 / ((sigma * sigma) + 1)
+        var = var.clamp(0, 1.0)
+        s, min_var = self.cosine_s.to(var.device), self._init_alpha_cumprod.to(var.device)
+        t = (((var * min_var) ** 0.5).acos() / (torch.pi * 0.5)) * (1 + s) - s
+        return t
+
+    def percent_to_sigma(self, percent):
+        if percent <= 0.0:
+            return 999999999.9
+        if percent >= 1.0:
+            return 0.0
+
+        percent = 1.0 - percent
+        return self.sigma(torch.tensor(percent))
@@ -523,7 +523,7 @@ class UNIPCBH2(Sampler):

 KSAMPLER_NAMES = ["euler", "euler_ancestral", "heun", "heunpp2","dpm_2", "dpm_2_ancestral",
                  "lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_sde", "dpmpp_sde_gpu",
-                  "dpmpp_2m", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm", "lcm", "tcd"]
+                  "dpmpp_2m", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm", "lcm", "tcd", "edm_playground_v2.5", "restart"]

 class KSAMPLER(Sampler):
    def __init__(self, sampler_function, extra_options={}, inpaint_options={}):
@@ -2,14 +2,15 @@ import os
 import json
 import math
 import numbers
+
 import args_manager
 import tempfile
 import modules.flags
 import modules.sdxl_styles
+from modules.hash_cache import init_cache

 from modules.model_loader import load_file_from_url
-from modules.util import makedirs_with_log
-from modules.extra_utils import get_files_from_folder
+from modules.extra_utils import makedirs_with_log, get_files_from_folder, try_eval_env_var
 from modules.flags import OutputFormat, Performance, MetadataScheme


@@ -98,7 +99,6 @@ def try_load_deprecated_user_path_config():

 try_load_deprecated_user_path_config()

-
 def get_presets():
    preset_folder = 'presets'
    presets = ['initial']
@@ -106,8 +106,11 @@ def get_presets():
        print('No presets found.')
        return presets

-    return presets + [f[:f.index('.json')] for f in os.listdir(preset_folder) if f.endswith('.json')]
+    return presets + [f[:f.index(".json")] for f in os.listdir(preset_folder) if f.endswith('.json')]

+def update_presets():
+    global available_presets
+    available_presets = get_presets()

 def try_get_preset_content(preset):
    if isinstance(preset, str):
@@ -198,10 +201,11 @@ path_clip_vision = get_dir_or_set_default('path_clip_vision', '../models/clip_vi
 path_fooocus_expansion = get_dir_or_set_default('path_fooocus_expansion', '../models/prompt_expansion/fooocus_expansion')
 path_wildcards = get_dir_or_set_default('path_wildcards', '../wildcards/')
 path_safety_checker = get_dir_or_set_default('path_safety_checker', '../models/safety_checker/')
+path_sam = get_dir_or_set_default('path_sam', '../models/sam/')
 path_outputs = get_path_output()


-def get_config_item_or_set_default(key, default_value, validator, disable_empty_as_none=False):
+def get_config_item_or_set_default(key, default_value, validator, disable_empty_as_none=False, expected_type=None):
    global config_dict, visited_keys

    if key not in visited_keys:
@@ -209,6 +213,7 @@ def get_config_item_or_set_default(key, default_value, validator, disable_empty_
    
    v = os.getenv(key)
    if v is not None:
+        v = try_eval_env_var(v, expected_type)
        print(f"Environment: {key} = {v}")
        config_dict[key] = v

@@ -253,41 +258,49 @@ temp_path = init_temp_path(get_config_item_or_set_default(
    key='temp_path',
    default_value=default_temp_path,
    validator=lambda x: isinstance(x, str),
+    expected_type=str
 ), default_temp_path)
 temp_path_cleanup_on_launch = get_config_item_or_set_default(
    key='temp_path_cleanup_on_launch',
    default_value=True,
-    validator=lambda x: isinstance(x, bool)
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
 )
 default_base_model_name = default_model = get_config_item_or_set_default(
    key='default_model',
    default_value='model.safetensors',
-    validator=lambda x: isinstance(x, str)
+    validator=lambda x: isinstance(x, str),
+    expected_type=str
 )
 previous_default_models = get_config_item_or_set_default(
    key='previous_default_models',
    default_value=[],
-    validator=lambda x: isinstance(x, list) and all(isinstance(k, str) for k in x)
+    validator=lambda x: isinstance(x, list) and all(isinstance(k, str) for k in x),
+    expected_type=list
 )
 default_refiner_model_name = default_refiner = get_config_item_or_set_default(
    key='default_refiner',
    default_value='None',
-    validator=lambda x: isinstance(x, str)
+    validator=lambda x: isinstance(x, str),
+    expected_type=str
 )
 default_refiner_switch = get_config_item_or_set_default(
    key='default_refiner_switch',
    default_value=0.8,
-    validator=lambda x: isinstance(x, numbers.Number) and 0 <= x <= 1
+    validator=lambda x: isinstance(x, numbers.Number) and 0 <= x <= 1,
+    expected_type=numbers.Number
 )
 default_loras_min_weight = get_config_item_or_set_default(
    key='default_loras_min_weight',
    default_value=-2,
-    validator=lambda x: isinstance(x, numbers.Number) and -10 <= x <= 10
+    validator=lambda x: isinstance(x, numbers.Number) and -10 <= x <= 10,
+    expected_type=numbers.Number
 )
 default_loras_max_weight = get_config_item_or_set_default(
    key='default_loras_max_weight',
    default_value=2,
-    validator=lambda x: isinstance(x, numbers.Number) and -10 <= x <= 10
+    validator=lambda x: isinstance(x, numbers.Number) and -10 <= x <= 10,
+    expected_type=numbers.Number
 )
 default_loras = get_config_item_or_set_default(
    key='default_loras',
@@ -321,38 +334,45 @@ default_loras = get_config_item_or_set_default(
    validator=lambda x: isinstance(x, list) and all(
        len(y) == 3 and isinstance(y[0], bool) and isinstance(y[1], str) and isinstance(y[2], numbers.Number)
        or len(y) == 2 and isinstance(y[0], str) and isinstance(y[1], numbers.Number)
-        for y in x)
+        for y in x),
+    expected_type=list
 )
 default_loras = [(y[0], y[1], y[2]) if len(y) == 3 else (True, y[0], y[1]) for y in default_loras]
 default_max_lora_number = get_config_item_or_set_default(
    key='default_max_lora_number',
    default_value=len(default_loras) if isinstance(default_loras, list) and len(default_loras) > 0 else 5,
-    validator=lambda x: isinstance(x, int) and x >= 1
+    validator=lambda x: isinstance(x, int) and x >= 1,
+    expected_type=int
 )
 default_cfg_scale = get_config_item_or_set_default(
    key='default_cfg_scale',
    default_value=7.0,
-    validator=lambda x: isinstance(x, numbers.Number)
+    validator=lambda x: isinstance(x, numbers.Number),
+    expected_type=numbers.Number
 )
 default_sample_sharpness = get_config_item_or_set_default(
    key='default_sample_sharpness',
    default_value=2.0,
-    validator=lambda x: isinstance(x, numbers.Number)
+    validator=lambda x: isinstance(x, numbers.Number),
+    expected_type=numbers.Number
 )
 default_sampler = get_config_item_or_set_default(
    key='default_sampler',
    default_value='dpmpp_2m_sde_gpu',
-    validator=lambda x: x in modules.flags.sampler_list
+    validator=lambda x: x in modules.flags.sampler_list,
+    expected_type=str
 )
 default_scheduler = get_config_item_or_set_default(
    key='default_scheduler',
    default_value='karras',
-    validator=lambda x: x in modules.flags.scheduler_list
+    validator=lambda x: x in modules.flags.scheduler_list,
+    expected_type=str
 )
 default_vae = get_config_item_or_set_default(
    key='default_vae',
    default_value=modules.flags.default_vae,
-    validator=lambda x: isinstance(x, str)
+    validator=lambda x: isinstance(x, str),
+    expected_type=str
 )
 default_styles = get_config_item_or_set_default(
    key='default_styles',
@@ -361,129 +381,241 @@ default_styles = get_config_item_or_set_default(
        "Fooocus Enhance",
        "Fooocus Sharp"
    ],
-    validator=lambda x: isinstance(x, list) and all(y in modules.sdxl_styles.legal_style_names for y in x)
+    validator=lambda x: isinstance(x, list) and all(y in modules.sdxl_styles.legal_style_names for y in x),
+    expected_type=list
 )
 default_prompt_negative = get_config_item_or_set_default(
    key='default_prompt_negative',
    default_value='',
    validator=lambda x: isinstance(x, str),
-    disable_empty_as_none=True
+    disable_empty_as_none=True,
+    expected_type=str
 )
 default_prompt = get_config_item_or_set_default(
    key='default_prompt',
    default_value='',
    validator=lambda x: isinstance(x, str),
-    disable_empty_as_none=True
+    disable_empty_as_none=True,
+    expected_type=str
 )
 default_performance = get_config_item_or_set_default(
    key='default_performance',
    default_value=Performance.SPEED.value,
-    validator=lambda x: x in Performance.list()
+    validator=lambda x: x in Performance.values(),
+    expected_type=str
 )
 default_advanced_checkbox = get_config_item_or_set_default(
    key='default_advanced_checkbox',
    default_value=False,
-    validator=lambda x: isinstance(x, bool)
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
 )
 default_max_image_number = get_config_item_or_set_default(
    key='default_max_image_number',
    default_value=32,
-    validator=lambda x: isinstance(x, int) and x >= 1
+    validator=lambda x: isinstance(x, int) and x >= 1,
+    expected_type=int
 )
 default_output_format = get_config_item_or_set_default(
    key='default_output_format',
    default_value='png',
-    validator=lambda x: x in OutputFormat.list()
+    validator=lambda x: x in OutputFormat.list(),
+    expected_type=str
 )
 default_image_number = get_config_item_or_set_default(
    key='default_image_number',
    default_value=2,
-    validator=lambda x: isinstance(x, int) and 1 <= x <= default_max_image_number
+    validator=lambda x: isinstance(x, int) and 1 <= x <= default_max_image_number,
+    expected_type=int
 )
 checkpoint_downloads = get_config_item_or_set_default(
    key='checkpoint_downloads',
    default_value={},
-    validator=lambda x: isinstance(x, dict) and all(isinstance(k, str) and isinstance(v, str) for k, v in x.items())
+    validator=lambda x: isinstance(x, dict) and all(isinstance(k, str) and isinstance(v, str) for k, v in x.items()),
+    expected_type=dict
 )
 lora_downloads = get_config_item_or_set_default(
    key='lora_downloads',
    default_value={},
-    validator=lambda x: isinstance(x, dict) and all(isinstance(k, str) and isinstance(v, str) for k, v in x.items())
+    validator=lambda x: isinstance(x, dict) and all(isinstance(k, str) and isinstance(v, str) for k, v in x.items()),
+    expected_type=dict
 )
 embeddings_downloads = get_config_item_or_set_default(
    key='embeddings_downloads',
    default_value={},
-    validator=lambda x: isinstance(x, dict) and all(isinstance(k, str) and isinstance(v, str) for k, v in x.items())
+    validator=lambda x: isinstance(x, dict) and all(isinstance(k, str) and isinstance(v, str) for k, v in x.items()),
+    expected_type=dict
+)
+vae_downloads = get_config_item_or_set_default(
+    key='vae_downloads',
+    default_value={},
+    validator=lambda x: isinstance(x, dict) and all(isinstance(k, str) and isinstance(v, str) for k, v in x.items()),
+    expected_type=dict
 )
 available_aspect_ratios = get_config_item_or_set_default(
    key='available_aspect_ratios',
-    default_value=[
-        '704*1408', '704*1344', '768*1344', '768*1280', '832*1216', '832*1152',
-        '896*1152', '896*1088', '960*1088', '960*1024', '1024*1024', '1024*960',
-        '1088*960', '1088*896', '1152*896', '1152*832', '1216*832', '1280*768',
-        '1344*768', '1344*704', '1408*704', '1472*704', '1536*640', '1600*640',
-        '1664*576', '1728*576'
-    ],
-    validator=lambda x: isinstance(x, list) and all('*' in v for v in x) and len(x) > 1
+    default_value=modules.flags.sdxl_aspect_ratios,
+    validator=lambda x: isinstance(x, list) and all('*' in v for v in x) and len(x) > 1,
+    expected_type=list
 )
 default_aspect_ratio = get_config_item_or_set_default(
    key='default_aspect_ratio',
    default_value='1152*896' if '1152*896' in available_aspect_ratios else available_aspect_ratios[0],
-    validator=lambda x: x in available_aspect_ratios
+    validator=lambda x: x in available_aspect_ratios,
+    expected_type=str
 )
 default_inpaint_engine_version = get_config_item_or_set_default(
    key='default_inpaint_engine_version',
    default_value='v2.6',
-    validator=lambda x: x in modules.flags.inpaint_engine_versions
+    validator=lambda x: x in modules.flags.inpaint_engine_versions,
+    expected_type=str
+)
+default_inpaint_method = get_config_item_or_set_default(
+    key='default_inpaint_method',
+    default_value=modules.flags.inpaint_option_default,
+    validator=lambda x: x in modules.flags.inpaint_options,
+    expected_type=str
 )
 default_cfg_tsnr = get_config_item_or_set_default(
    key='default_cfg_tsnr',
    default_value=7.0,
-    validator=lambda x: isinstance(x, numbers.Number)
+    validator=lambda x: isinstance(x, numbers.Number),
+    expected_type=numbers.Number
+)
+default_clip_skip = get_config_item_or_set_default(
+    key='default_clip_skip',
+    default_value=2,
+    validator=lambda x: isinstance(x, int) and 1 <= x <= modules.flags.clip_skip_max,
+    expected_type=int
 )
 default_overwrite_step = get_config_item_or_set_default(
    key='default_overwrite_step',
    default_value=-1,
-    validator=lambda x: isinstance(x, int)
+    validator=lambda x: isinstance(x, int),
+    expected_type=int
 )
 default_overwrite_switch = get_config_item_or_set_default(
    key='default_overwrite_switch',
    default_value=-1,
-    validator=lambda x: isinstance(x, int)
+    validator=lambda x: isinstance(x, int),
+    expected_type=int
+)
+default_overwrite_upscale = get_config_item_or_set_default(
+    key='default_overwrite_upscale',
+    default_value=-1,
+    validator=lambda x: isinstance(x, numbers.Number)
 )
 example_inpaint_prompts = get_config_item_or_set_default(
    key='example_inpaint_prompts',
    default_value=[
        'highly detailed face', 'detailed girl face', 'detailed man face', 'detailed hand', 'beautiful eyes'
    ],
-    validator=lambda x: isinstance(x, list) and all(isinstance(v, str) for v in x)
+    validator=lambda x: isinstance(x, list) and all(isinstance(v, str) for v in x),
+    expected_type=list
+)
+example_enhance_detection_prompts = get_config_item_or_set_default(
+    key='example_enhance_detection_prompts',
+    default_value=[
+        'face', 'eye', 'mouth', 'hair', 'hand', 'body'
+    ],
+    validator=lambda x: isinstance(x, list) and all(isinstance(v, str) for v in x),
+    expected_type=list
+)
+default_enhance_tabs = get_config_item_or_set_default(
+    key='default_enhance_tabs',
+    default_value=3,
+    validator=lambda x: isinstance(x, int) and 1 <= x <= 5,
+    expected_type=int
+)
+default_enhance_checkbox = get_config_item_or_set_default(
+    key='default_enhance_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
+default_enhance_uov_method = get_config_item_or_set_default(
+    key='default_enhance_uov_method',
+    default_value=modules.flags.disabled,
+    validator=lambda x: x in modules.flags.uov_list,
+    expected_type=int
+)
+default_enhance_uov_processing_order = get_config_item_or_set_default(
+    key='default_enhance_uov_processing_order',
+    default_value=modules.flags.enhancement_uov_before,
+    validator=lambda x: x in modules.flags.enhancement_uov_processing_order,
+    expected_type=int
+)
+default_enhance_uov_prompt_type = get_config_item_or_set_default(
+    key='default_enhance_uov_prompt_type',
+    default_value=modules.flags.enhancement_uov_prompt_type_original,
+    validator=lambda x: x in modules.flags.enhancement_uov_prompt_types,
+    expected_type=int
+)
+default_sam_max_detections = get_config_item_or_set_default(
+    key='default_sam_max_detections',
+    default_value=0,
+    validator=lambda x: isinstance(x, int) and 0 <= x <= 10,
+    expected_type=int
 )
 default_black_out_nsfw = get_config_item_or_set_default(
    key='default_black_out_nsfw',
    default_value=False,
-    validator=lambda x: isinstance(x, bool)
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
 )
 default_save_metadata_to_images = get_config_item_or_set_default(
    key='default_save_metadata_to_images',
    default_value=False,
-    validator=lambda x: isinstance(x, bool)
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
 )
 default_metadata_scheme = get_config_item_or_set_default(
    key='default_metadata_scheme',
    default_value=MetadataScheme.FOOOCUS.value,
-    validator=lambda x: x in [y[1] for y in modules.flags.metadata_scheme if y[1] == x]
+    validator=lambda x: x in [y[1] for y in modules.flags.metadata_scheme if y[1] == x],
+    expected_type=str
 )
 metadata_created_by = get_config_item_or_set_default(
    key='metadata_created_by',
    default_value='',
-    validator=lambda x: isinstance(x, str)
+    validator=lambda x: isinstance(x, str),
+    expected_type=str
 )

 example_inpaint_prompts = [[x] for x in example_inpaint_prompts]
+example_enhance_detection_prompts = [[x] for x in example_enhance_detection_prompts]
+
+default_inpaint_mask_model = get_config_item_or_set_default(
+    key='default_inpaint_mask_model',
+    default_value='isnet-general-use',
+    validator=lambda x: x in modules.flags.inpaint_mask_models,
+    expected_type=str
+)
+
+default_enhance_inpaint_mask_model = get_config_item_or_set_default(
+    key='default_enhance_inpaint_mask_model',
+    default_value='sam',
+    validator=lambda x: x in modules.flags.inpaint_mask_models,
+    expected_type=str
+)
+
+default_inpaint_mask_cloth_category = get_config_item_or_set_default(
+    key='default_inpaint_mask_cloth_category',
+    default_value='full',
+    validator=lambda x: x in modules.flags.inpaint_mask_cloth_category,
+    expected_type=str
+)
+
+default_inpaint_mask_sam_model = get_config_item_or_set_default(
+    key='default_inpaint_mask_sam_model',
+    default_value='vit_b',
+    validator=lambda x: x in [y[1] for y in modules.flags.inpaint_mask_sam_model if y[1] == x],
+    expected_type=str
+)

 config_dict["default_loras"] = default_loras = default_loras[:default_max_lora_number] + [[True, 'None', 1.0] for _ in range(default_max_lora_number - len(default_loras))]

-# mapping config to meta parameter 
+# mapping config to meta parameter
 possible_preset_keys = {
    "default_model": "base_model",
    "default_refiner": "refiner_model",
@@ -494,9 +626,12 @@ possible_preset_keys = {
    "default_loras": "<processed>",
    "default_cfg_scale": "guidance_scale",
    "default_sample_sharpness": "sharpness",
+    "default_cfg_tsnr": "adaptive_cfg",
+    "default_clip_skip": "clip_skip",
    "default_sampler": "sampler",
    "default_scheduler": "scheduler",
    "default_overwrite_step": "steps",
+    "default_overwrite_switch": "overwrite_switch",
    "default_performance": "performance",
    "default_image_number": "image_number",
    "default_prompt": "prompt",
@@ -506,7 +641,11 @@ possible_preset_keys = {
    "default_save_metadata_to_images": "default_save_metadata_to_images",
    "checkpoint_downloads": "checkpoint_downloads",
    "embeddings_downloads": "embeddings_downloads",
-    "lora_downloads": "lora_downloads"
+    "lora_downloads": "lora_downloads",
+    "vae_downloads": "vae_downloads",
+    "default_vae": "vae",
+    # "default_inpaint_method": "inpaint_method", # disabled so inpaint mode doesn't refresh after every preset change
+    "default_inpaint_engine_version": "inpaint_engine_version",
 }

 REWRITE_PRESET = False
@@ -527,7 +666,7 @@ def add_ratio(x):


 default_aspect_ratio = add_ratio(default_aspect_ratio)
-available_aspect_ratios = [add_ratio(x) for x in available_aspect_ratios]
+available_aspect_ratios_labels = [add_ratio(x) for x in available_aspect_ratios]


 # Only write config in the first launch.
@@ -551,11 +690,6 @@ lora_filenames = []
 vae_filenames = []
 wildcard_filenames = []

-sdxl_lcm_lora = 'sdxl_lcm_lora.safetensors'
-sdxl_lightning_lora = 'sdxl_lightning_4step_lora.safetensors'
-sdxl_hyper_sd_lora = 'sdxl_hyper_sd_4step_lora.safetensors'
-loras_metadata_remove = [sdxl_lcm_lora, sdxl_lightning_lora, sdxl_hyper_sd_lora]
-

 def get_model_filenames(folder_paths, extensions=None, name_filter=None):
    if extensions is None:
@@ -622,26 +756,27 @@ def downloading_sdxl_lcm_lora():
    load_file_from_url(
        url='https://huggingface.co/lllyasviel/misc/resolve/main/sdxl_lcm_lora.safetensors',
        model_dir=paths_loras[0],
-        file_name=sdxl_lcm_lora
+        file_name=modules.flags.PerformanceLoRA.EXTREME_SPEED.value
    )
-    return sdxl_lcm_lora
+    return modules.flags.PerformanceLoRA.EXTREME_SPEED.value
+

 def downloading_sdxl_lightning_lora():
    load_file_from_url(
        url='https://huggingface.co/mashb1t/misc/resolve/main/sdxl_lightning_4step_lora.safetensors',
        model_dir=paths_loras[0],
-        file_name=sdxl_lightning_lora
+        file_name=modules.flags.PerformanceLoRA.LIGHTNING.value
    )
-    return sdxl_lightning_lora
+    return modules.flags.PerformanceLoRA.LIGHTNING.value


 def downloading_sdxl_hyper_sd_lora():
    load_file_from_url(
        url='https://huggingface.co/mashb1t/misc/resolve/main/sdxl_hyper_sd_4step_lora.safetensors',
        model_dir=paths_loras[0],
-        file_name=sdxl_hyper_sd_lora
+        file_name=modules.flags.PerformanceLoRA.HYPER_SD.value
    )
-    return sdxl_hyper_sd_lora
+    return modules.flags.PerformanceLoRA.HYPER_SD.value


 def downloading_controlnet_canny():
@@ -717,4 +852,44 @@ def downloading_safety_checker_model():
    return os.path.join(path_safety_checker, 'stable-diffusion-safety-checker.bin')


+def download_sam_model(sam_model: str) -> str:
+    match sam_model:
+        case 'vit_b':
+            return downloading_sam_vit_b()
+        case 'vit_l':
+            return downloading_sam_vit_l()
+        case 'vit_h':
+            return downloading_sam_vit_h()
+        case _:
+            raise ValueError(f"sam model {sam_model} does not exist.")
+
+
+def downloading_sam_vit_b():
+    load_file_from_url(
+        url='https://huggingface.co/mashb1t/misc/resolve/main/sam_vit_b_01ec64.pth',
+        model_dir=path_sam,
+        file_name='sam_vit_b_01ec64.pth'
+    )
+    return os.path.join(path_sam, 'sam_vit_b_01ec64.pth')
+
+
+def downloading_sam_vit_l():
+    load_file_from_url(
+        url='https://huggingface.co/mashb1t/misc/resolve/main/sam_vit_l_0b3195.pth',
+        model_dir=path_sam,
+        file_name='sam_vit_l_0b3195.pth'
+    )
+    return os.path.join(path_sam, 'sam_vit_l_0b3195.pth')
+
+
+def downloading_sam_vit_h():
+    load_file_from_url(
+        url='https://huggingface.co/mashb1t/misc/resolve/main/sam_vit_h_4b8939.pth',
+        model_dir=path_sam,
+        file_name='sam_vit_h_4b8939.pth'
+    )
+    return os.path.join(path_sam, 'sam_vit_h_4b8939.pth')
+
+
 update_files()
+init_cache(model_filenames, paths_checkpoints, lora_filenames, paths_loras)
@@ -21,8 +21,7 @@ from modules.lora import match_lora
 from modules.util import get_file_from_folder_list
 from ldm_patched.modules.lora import model_lora_keys_unet, model_lora_keys_clip
 from modules.config import path_embeddings
-from ldm_patched.contrib.external_model_advanced import ModelSamplingDiscrete
-
+from ldm_patched.contrib.external_model_advanced import ModelSamplingDiscrete, ModelSamplingContinuousEDM

 opEmptyLatentImage = EmptyLatentImage()
 opVAEDecode = VAEDecode()
@@ -32,6 +31,7 @@ opVAEEncodeTiled = VAEEncodeTiled()
 opControlNetApplyAdvanced = ControlNetApplyAdvanced()
 opFreeU = FreeU_V2()
 opModelSamplingDiscrete = ModelSamplingDiscrete()
+opModelSamplingContinuousEDM = ModelSamplingContinuousEDM()


 class StableDiffusionModel:
@@ -201,6 +201,17 @@ def clip_encode(texts, pool_top_k=1):
    return [[torch.cat(cond_list, dim=1), {"pooled_output": pooled_acc}]]


+@torch.no_grad()
+@torch.inference_mode()
+def set_clip_skip(clip_skip: int):
+    global final_clip
+
+    if final_clip is None:
+        return
+
+    final_clip.clip_layer(-abs(clip_skip))
+    return
+
@torch.no_grad()
@torch.inference_mode()
 def clear_all_caches():
@@ -1,4 +1,12 @@
 import os
+from ast import literal_eval
+
+
+def makedirs_with_log(path):
+    try:
+        os.makedirs(path, exist_ok=True)
+    except OSError as error:
+        print(f'Directory {path} could not be created, reason: {error}')


 def get_files_from_folder(folder_path, extensions=None, name_filter=None):
@@ -18,3 +26,16 @@ def get_files_from_folder(folder_path, extensions=None, name_filter=None):
                filenames.append(path)

    return filenames
+
+
+def try_eval_env_var(value: str, expected_type=None):
+    try:
+        value_eval = value
+        if expected_type is bool:
+            value_eval = value.title()
+        value_eval = literal_eval(value_eval)
+        if expected_type is not None and not isinstance(value_eval, expected_type):
+            return value
+        return value_eval
+    except:
+        return value
@@ -8,9 +8,15 @@ upscale_15 = 'Upscale (1.5x)'
 upscale_2 = 'Upscale (2x)'
 upscale_fast = 'Upscale (Fast 2x)'

-uov_list = [
-    disabled, subtle_variation, strong_variation, upscale_15, upscale_2, upscale_fast
-]
+uov_list = [disabled, subtle_variation, strong_variation, upscale_15, upscale_2, upscale_fast]
+
+enhancement_uov_before = "Before First Enhancement"
+enhancement_uov_after = "After Last Enhancement"
+enhancement_uov_processing_order = [enhancement_uov_before, enhancement_uov_after]
+
+enhancement_uov_prompt_type_original = 'Original Prompts'
+enhancement_uov_prompt_type_last_filled = 'Last Filled Enhancement Prompts'
+enhancement_uov_prompt_types = [enhancement_uov_prompt_type_original, enhancement_uov_prompt_type_last_filled]

 CIVITAI_NO_KARRAS = ["euler", "euler_ancestral", "heun", "dpm_fast", "dpm_adaptive", "ddim", "uni_pc"]

@@ -35,7 +41,8 @@ KSAMPLER = {
    "dpmpp_3m_sde_gpu": "",
    "ddpm": "",
    "lcm": "LCM",
-    "tcd": "TCD"
+    "tcd": "TCD",
+    "restart": "Restart"
 }

 SAMPLER_EXTRA = {
@@ -48,12 +55,14 @@ SAMPLERS = KSAMPLER | SAMPLER_EXTRA

 KSAMPLER_NAMES = list(KSAMPLER.keys())

-SCHEDULER_NAMES = ["normal", "karras", "exponential", "sgm_uniform", "simple", "ddim_uniform", "lcm", "turbo", "align_your_steps", "tcd"]
+SCHEDULER_NAMES = ["normal", "karras", "exponential", "sgm_uniform", "simple", "ddim_uniform", "lcm", "turbo", "align_your_steps", "tcd", "edm_playground_v2.5"]
 SAMPLER_NAMES = KSAMPLER_NAMES + list(SAMPLER_EXTRA.keys())

 sampler_list = SAMPLER_NAMES
 scheduler_list = SCHEDULER_NAMES

+clip_skip_max = 12
+
 default_vae = 'Default (model)'

 refiner_swap_method = 'joint'
@@ -72,6 +81,10 @@ default_parameters = {

 output_formats = ['png', 'jpeg', 'webp']

+inpaint_mask_models = ['u2net', 'u2netp', 'u2net_human_seg', 'u2net_cloth_seg', 'silueta', 'isnet-general-use', 'isnet-anime', 'sam']
+inpaint_mask_cloth_category = ['full', 'upper', 'lower']
+inpaint_mask_sam_model = ['vit_b', 'vit_l', 'vit_h']
+
 inpaint_engine_versions = ['None', 'v1', 'v2.5', 'v2.6']
 inpaint_option_default = 'Inpaint or Outpaint (default)'
 inpaint_option_detail = 'Improve Detail (face, hand, eyes, etc.)'
@@ -81,6 +94,14 @@ inpaint_options = [inpaint_option_default, inpaint_option_detail, inpaint_option
 desc_type_photo = 'Photograph'
 desc_type_anime = 'Art/Anime'

+sdxl_aspect_ratios = [
+    '704*1408', '704*1344', '768*1344', '768*1280', '832*1216', '832*1152',
+    '896*1152', '896*1088', '960*1088', '960*1024', '1024*1024', '1024*960',
+    '1088*960', '1088*896', '1152*896', '1152*832', '1216*832', '1280*768',
+    '1344*768', '1344*704', '1408*704', '1472*704', '1536*640', '1600*640',
+    '1664*576', '1728*576'
+]
+

 class MetadataScheme(Enum):
    FOOOCUS = 'fooocus'
@@ -105,6 +126,14 @@ class OutputFormat(Enum):
        return list(map(lambda c: c.value, cls))


+class PerformanceLoRA(Enum):
+    QUALITY = None
+    SPEED = None
+    EXTREME_SPEED = 'sdxl_lcm_lora.safetensors'
+    LIGHTNING = 'sdxl_lightning_4step_lora.safetensors'
+    HYPER_SD = 'sdxl_hyper_sd_4step_lora.safetensors'
+
+
 class Steps(IntEnum):
    QUALITY = 60
    SPEED = 30
@@ -112,6 +141,10 @@ class Steps(IntEnum):
    LIGHTNING = 4
    HYPER_SD = 4

+    @classmethod
+    def keys(cls) -> list:
+        return list(map(lambda c: c, Steps.__members__))
+

 class StepsUOV(IntEnum):
    QUALITY = 36
@@ -130,8 +163,16 @@ class Performance(Enum):

    @classmethod
    def list(cls) -> list:
+        return list(map(lambda c: (c.name, c.value), cls))
+
+    @classmethod
+    def values(cls) -> list:
        return list(map(lambda c: c.value, cls))

+    @classmethod
+    def by_steps(cls, steps: int | str):
+        return cls[Steps(int(steps)).name]
+
    @classmethod
    def has_restricted_features(cls, x) -> bool:
        if isinstance(x, Performance):
@@ -139,7 +180,10 @@ class Performance(Enum):
        return x in [cls.EXTREME_SPEED.value, cls.LIGHTNING.value, cls.HYPER_SD.value]

    def steps(self) -> int | None:
-        return Steps[self.name].value if Steps[self.name] else None
+        return Steps[self.name].value if self.name in Steps.__members__ else None

    def steps_uov(self) -> int | None:
-        return StepsUOV[self.name].value if Steps[self.name] else None
+        return StepsUOV[self.name].value if self.name in StepsUOV.__members__ else None
+
+    def lora_filename(self) -> str | None:
+        return PerformanceLoRA[self.name].value if self.name in PerformanceLoRA.__members__ else None
@@ -0,0 +1,84 @@
+import json
+import os
+from concurrent.futures import ThreadPoolExecutor
+from multiprocessing import cpu_count
+
+import args_manager
+from modules.util import get_file_from_folder_list
+from modules.util import sha256, HASH_SHA256_LENGTH
+
+hash_cache_filename = 'hash_cache.txt'
+hash_cache = {}
+
+
+def sha256_from_cache(filepath):
+    global hash_cache
+    if filepath not in hash_cache:
+        print(f"[Cache] Calculating sha256 for {filepath}")
+        hash_value = sha256(filepath)
+        print(f"[Cache] sha256 for {filepath}: {hash_value}")
+        hash_cache[filepath] = hash_value
+        save_cache_to_file(filepath, hash_value)
+
+    return hash_cache[filepath]
+
+
+def load_cache_from_file():
+    global hash_cache
+
+    try:
+        if os.path.exists(hash_cache_filename):
+            with open(hash_cache_filename, 'rt', encoding='utf-8') as fp:
+                for line in fp:
+                    entry = json.loads(line)
+                    for filepath, hash_value in entry.items():
+                        if not os.path.exists(filepath) or not isinstance(hash_value, str) and len(hash_value) != HASH_SHA256_LENGTH:
+                            print(f'[Cache] Skipping invalid cache entry: {filepath}')
+                            continue
+                        hash_cache[filepath] = hash_value
+    except Exception as e:
+        print(f'[Cache] Loading failed: {e}')
+
+
+def save_cache_to_file(filename=None, hash_value=None):
+    global hash_cache
+
+    if filename is not None and hash_value is not None:
+        items = [(filename, hash_value)]
+        mode = 'at'
+    else:
+        items = sorted(hash_cache.items())
+        mode = 'wt'
+
+    try:
+        with open(hash_cache_filename, mode, encoding='utf-8') as fp:
+            for filepath, hash_value in items:
+                json.dump({filepath: hash_value}, fp)
+                fp.write('\n')
+    except Exception as e:
+        print(f'[Cache] Saving failed: {e}')
+
+
+def init_cache(model_filenames, paths_checkpoints, lora_filenames, paths_loras):
+    load_cache_from_file()
+
+    if args_manager.args.rebuild_hash_cache:
+        max_workers = args_manager.args.rebuild_hash_cache if args_manager.args.rebuild_hash_cache > 0 else cpu_count()
+        rebuild_cache(lora_filenames, model_filenames, paths_checkpoints, paths_loras, max_workers)
+
+    # write cache to file again for sorting and cleanup of invalid cache entries
+    save_cache_to_file()
+
+
+def rebuild_cache(lora_filenames, model_filenames, paths_checkpoints, paths_loras, max_workers=cpu_count()):
+    def thread(filename, paths):
+        filepath = get_file_from_folder_list(filename, paths)
+        sha256_from_cache(filepath)
+
+    print('[Cache] Rebuilding hash cache')
+    with ThreadPoolExecutor(max_workers=max_workers) as executor:
+        for model_filename in model_filenames:
+            executor.submit(thread, model_filename, paths_checkpoints)
+        for lora_filename in lora_filenames:
+            executor.submit(thread, lora_filename, paths_loras)
+    print('[Cache] Done')
@@ -9,18 +9,18 @@ from PIL import Image
 import fooocus_version
 import modules.config
 import modules.sdxl_styles
+from modules import hash_cache
 from modules.flags import MetadataScheme, Performance, Steps
 from modules.flags import SAMPLERS, CIVITAI_NO_KARRAS
-from modules.util import quote, unquote, extract_styles_from_prompt, is_json, get_file_from_folder_list, sha256
+from modules.hash_cache import sha256_from_cache
+from modules.util import quote, unquote, extract_styles_from_prompt, is_json, get_file_from_folder_list

 re_param_code = r'\s*(\w[\w \-/]+):\s*("(?:\\.|[^\\"])+"|[^,]*)(?:,|$)'
 re_param = re.compile(re_param_code)
 re_imagesize = re.compile(r"^(\d+)x(\d+)$")

-hash_cache = {}

-
-def load_parameter_button_click(raw_metadata: dict | str, is_generating: bool):
+def load_parameter_button_click(raw_metadata: dict | str, is_generating: bool, inpaint_mode: str):
    loaded_parameter_dict = raw_metadata
    if isinstance(raw_metadata, str):
        loaded_parameter_dict = json.loads(raw_metadata)
@@ -32,22 +32,25 @@ def load_parameter_button_click(raw_metadata: dict | str, is_generating: bool):
    get_str('prompt', 'Prompt', loaded_parameter_dict, results)
    get_str('negative_prompt', 'Negative Prompt', loaded_parameter_dict, results)
    get_list('styles', 'Styles', loaded_parameter_dict, results)
-    get_str('performance', 'Performance', loaded_parameter_dict, results)
+    performance = get_str('performance', 'Performance', loaded_parameter_dict, results)
    get_steps('steps', 'Steps', loaded_parameter_dict, results)
-    get_float('overwrite_switch', 'Overwrite Switch', loaded_parameter_dict, results)
+    get_number('overwrite_switch', 'Overwrite Switch', loaded_parameter_dict, results)
    get_resolution('resolution', 'Resolution', loaded_parameter_dict, results)
-    get_float('guidance_scale', 'Guidance Scale', loaded_parameter_dict, results)
-    get_float('sharpness', 'Sharpness', loaded_parameter_dict, results)
+    get_number('guidance_scale', 'Guidance Scale', loaded_parameter_dict, results)
+    get_number('sharpness', 'Sharpness', loaded_parameter_dict, results)
    get_adm_guidance('adm_guidance', 'ADM Guidance', loaded_parameter_dict, results)
    get_str('refiner_swap_method', 'Refiner Swap Method', loaded_parameter_dict, results)
-    get_float('adaptive_cfg', 'CFG Mimicking from TSNR', loaded_parameter_dict, results)
+    get_number('adaptive_cfg', 'CFG Mimicking from TSNR', loaded_parameter_dict, results)
+    get_number('clip_skip', 'CLIP Skip', loaded_parameter_dict, results, cast_type=int)
    get_str('base_model', 'Base Model', loaded_parameter_dict, results)
    get_str('refiner_model', 'Refiner Model', loaded_parameter_dict, results)
-    get_float('refiner_switch', 'Refiner Switch', loaded_parameter_dict, results)
+    get_number('refiner_switch', 'Refiner Switch', loaded_parameter_dict, results)
    get_str('sampler', 'Sampler', loaded_parameter_dict, results)
    get_str('scheduler', 'Scheduler', loaded_parameter_dict, results)
    get_str('vae', 'VAE', loaded_parameter_dict, results)
    get_seed('seed', 'Seed', loaded_parameter_dict, results)
+    get_inpaint_engine_version('inpaint_engine_version', 'Inpaint Engine Version', loaded_parameter_dict, results, inpaint_mode)
+    get_inpaint_method('inpaint_method', 'Inpaint Mode', loaded_parameter_dict, results)

    if is_generating:
        results.append(gr.update())
@@ -58,19 +61,27 @@ def load_parameter_button_click(raw_metadata: dict | str, is_generating: bool):

    get_freeu('freeu', 'FreeU', loaded_parameter_dict, results)

+    # prevent performance LoRAs to be added twice, by performance and by lora
+    performance_filename = None
+    if performance is not None and performance in Performance.values():
+        performance = Performance(performance)
+        performance_filename = performance.lora_filename()
+
    for i in range(modules.config.default_max_lora_number):
-        get_lora(f'lora_combined_{i + 1}', f'LoRA {i + 1}', loaded_parameter_dict, results)
+        get_lora(f'lora_combined_{i + 1}', f'LoRA {i + 1}', loaded_parameter_dict, results, performance_filename)

    return results


-def get_str(key: str, fallback: str | None, source_dict: dict, results: list, default=None):
+def get_str(key: str, fallback: str | None, source_dict: dict, results: list, default=None) -> str | None:
    try:
        h = source_dict.get(key, source_dict.get(fallback, default))
        assert isinstance(h, str)
        results.append(h)
+        return h
    except:
        results.append(gr.update())
+        return None


 def get_list(key: str, fallback: str | None, source_dict: dict, results: list, default=None):
@@ -83,11 +94,11 @@ def get_list(key: str, fallback: str | None, source_dict: dict, results: list, d
        results.append(gr.update())


-def get_float(key: str, fallback: str | None, source_dict: dict, results: list, default=None):
+def get_number(key: str, fallback: str | None, source_dict: dict, results: list, default=None, cast_type=float):
    try:
        h = source_dict.get(key, source_dict.get(fallback, default))
        assert h is not None
-        h = float(h)
+        h = cast_type(h)
        results.append(h)
    except:
        results.append(gr.update())
@@ -110,8 +121,9 @@ def get_steps(key: str, fallback: str | None, source_dict: dict, results: list,
        assert h is not None
        h = int(h)
        # if not in steps or in steps and performance is not the same
-        if h not in iter(Steps) or Steps(h).name.casefold() != source_dict.get('performance', '').replace(' ',
-                                                                                                          '_').casefold():
+        performance_name = source_dict.get('performance', '').replace(' ', '_').replace('-', '_').casefold()
+        performance_candidates = [key for key in Steps.keys() if key.casefold() == performance_name and Steps[key] == h]
+        if len(performance_candidates) == 0:
            results.append(h)
            return
        results.append(-1)
@@ -124,7 +136,7 @@ def get_resolution(key: str, fallback: str | None, source_dict: dict, results: l
        h = source_dict.get(key, source_dict.get(fallback, default))
        width, height = eval(h)
        formatted = modules.config.add_ratio(f'{width}*{height}')
-        if formatted in modules.config.available_aspect_ratios:
+        if formatted in modules.config.available_aspect_ratios_labels:
            results.append(formatted)
            results.append(-1)
            results.append(-1)
@@ -150,6 +162,36 @@ def get_seed(key: str, fallback: str | None, source_dict: dict, results: list, d
        results.append(gr.update())


+def get_inpaint_engine_version(key: str, fallback: str | None, source_dict: dict, results: list, inpaint_mode: str, default=None) -> str | None:
+    try:
+        h = source_dict.get(key, source_dict.get(fallback, default))
+        assert isinstance(h, str) and h in modules.flags.inpaint_engine_versions
+        if inpaint_mode != modules.flags.inpaint_option_detail:
+            results.append(h)
+        else:
+            results.append(gr.update())
+        results.append(h)
+        return h
+    except:
+        results.append(gr.update())
+        results.append('empty')
+        return None
+
+
+def get_inpaint_method(key: str, fallback: str | None, source_dict: dict, results: list, default=None) -> str | None:
+    try:
+        h = source_dict.get(key, source_dict.get(fallback, default))
+        assert isinstance(h, str) and h in modules.flags.inpaint_options
+        results.append(h)
+        for i in range(modules.config.default_enhance_tabs):
+            results.append(h)
+        return h
+    except:
+        results.append(gr.update())
+        for i in range(modules.config.default_enhance_tabs):
+            results.append(gr.update())
+
+
 def get_adm_guidance(key: str, fallback: str | None, source_dict: dict, results: list, default=None):
    try:
        h = source_dict.get(key, source_dict.get(fallback, default))
@@ -180,7 +222,7 @@ def get_freeu(key: str, fallback: str | None, source_dict: dict, results: list,
        results.append(gr.update())


-def get_lora(key: str, fallback: str | None, source_dict: dict, results: list):
+def get_lora(key: str, fallback: str | None, source_dict: dict, results: list, performance_filename: str | None):
    try:
        split_data = source_dict.get(key, source_dict.get(fallback)).split(' : ')
        enabled = True
@@ -192,6 +234,9 @@ def get_lora(key: str, fallback: str | None, source_dict: dict, results: list):
            name = split_data[1]
            weight = split_data[2]

+        if name == performance_filename:
+            raise Exception
+
        weight = float(weight)
        results.append(enabled)
        results.append(name)
@@ -202,15 +247,6 @@ def get_lora(key: str, fallback: str | None, source_dict: dict, results: list):
        results.append(1)


-def get_sha256(filepath):
-    global hash_cache
-    if filepath not in hash_cache:
-        # is_safetensors = os.path.splitext(filepath)[1].lower() == '.safetensors'
-        hash_cache[filepath] = sha256(filepath)
-
-    return hash_cache[filepath]
-
-
 def parse_meta_from_preset(preset_content):
    assert isinstance(preset_content, dict)
    preset_prepared = {}
@@ -221,7 +257,7 @@ def parse_meta_from_preset(preset_content):
            loras = getattr(modules.config, settings_key)
            if settings_key in items:
                loras = items[settings_key]
-            for index, lora in enumerate(loras[:5]):
+            for index, lora in enumerate(loras[:modules.config.default_max_lora_number]):
                preset_prepared[f'lora_combined_{index + 1}'] = ' : '.join(map(str, lora))
        elif settings_key == "default_aspect_ratio":
            if settings_key in items and items[settings_key] is not None:
@@ -233,8 +269,7 @@ def parse_meta_from_preset(preset_content):
                height = height[:height.index(" ")]
            preset_prepared[meta_key] = (width, height)
        else:
-            preset_prepared[meta_key] = items[settings_key] if settings_key in items and items[
-                settings_key] is not None else getattr(modules.config, settings_key)
+            preset_prepared[meta_key] = items[settings_key] if settings_key in items and items[settings_key] is not None else getattr(modules.config, settings_key)

        if settings_key == "default_styles" or settings_key == "default_aspect_ratio":
            preset_prepared[meta_key] = str(preset_prepared[meta_key])
@@ -248,7 +283,7 @@ class MetadataParser(ABC):
        self.full_prompt: str = ''
        self.raw_negative_prompt: str = ''
        self.full_negative_prompt: str = ''
-        self.steps: int = 30
+        self.steps: int = Steps.SPEED.value
        self.base_model_name: str = ''
        self.base_model_hash: str = ''
        self.refiner_model_name: str = ''
@@ -261,11 +296,11 @@ class MetadataParser(ABC):
        raise NotImplementedError

    @abstractmethod
-    def parse_json(self, metadata: dict | str) -> dict:
+    def to_json(self, metadata: dict | str) -> dict:
        raise NotImplementedError

    @abstractmethod
-    def parse_string(self, metadata: dict) -> str:
+    def to_string(self, metadata: dict) -> str:
        raise NotImplementedError

    def set_data(self, raw_prompt, full_prompt, raw_negative_prompt, full_negative_prompt, steps, base_model_name,
@@ -278,27 +313,21 @@ class MetadataParser(ABC):
        self.base_model_name = Path(base_model_name).stem

        base_model_path = get_file_from_folder_list(base_model_name, modules.config.paths_checkpoints)
-        self.base_model_hash = get_sha256(base_model_path)
+        self.base_model_hash = sha256_from_cache(base_model_path)

        if refiner_model_name not in ['', 'None']:
            self.refiner_model_name = Path(refiner_model_name).stem
            refiner_model_path = get_file_from_folder_list(refiner_model_name, modules.config.paths_checkpoints)
-            self.refiner_model_hash = get_sha256(refiner_model_path)
+            self.refiner_model_hash = sha256_from_cache(refiner_model_path)

        self.loras = []
        for (lora_name, lora_weight) in loras:
            if lora_name != 'None':
                lora_path = get_file_from_folder_list(lora_name, modules.config.paths_loras)
-                lora_hash = get_sha256(lora_path)
+                lora_hash = sha256_from_cache(lora_path)
                self.loras.append((Path(lora_name).stem, lora_weight, lora_hash))
        self.vae_name = Path(vae_name).stem

-    @staticmethod
-    def remove_special_loras(lora_filenames):
-        for lora_to_remove in modules.config.loras_metadata_remove:
-            if lora_to_remove in lora_filenames:
-                lora_filenames.remove(lora_to_remove)
-

 class A1111MetadataParser(MetadataParser):
    def get_scheme(self) -> MetadataScheme:
@@ -321,6 +350,7 @@ class A1111MetadataParser(MetadataParser):
        'adm_guidance': 'ADM Guidance',
        'refiner_swap_method': 'Refiner Swap Method',
        'adaptive_cfg': 'Adaptive CFG',
+        'clip_skip': 'Clip skip',
        'overwrite_switch': 'Overwrite Switch',
        'freeu': 'FreeU',
        'base_model': 'Model',
@@ -333,7 +363,7 @@ class A1111MetadataParser(MetadataParser):
        'version': 'Version'
    }

-    def parse_json(self, metadata: str) -> dict:
+    def to_json(self, metadata: str) -> dict:
        metadata_prompt = ''
        metadata_negative_prompt = ''

@@ -387,9 +417,9 @@ class A1111MetadataParser(MetadataParser):
        data['styles'] = str(found_styles)

        # try to load performance based on steps, fallback for direct A1111 imports
-        if 'steps' in data and 'performance' not in data:
+        if 'steps' in data and 'performance' in data is None:
            try:
-                data['performance'] = Performance[Steps(int(data['steps'])).name].value
+                data['performance'] = Performance.by_steps(data['steps']).value
            except ValueError | KeyError:
                pass

@@ -415,13 +445,11 @@ class A1111MetadataParser(MetadataParser):
            lora_data = data['lora_hashes']

        if lora_data != '':
-            lora_filenames = modules.config.lora_filenames.copy()
-            self.remove_special_loras(lora_filenames)
            for li, lora in enumerate(lora_data.split(', ')):
                lora_split = lora.split(': ')
                lora_name = lora_split[0]
                lora_weight = lora_split[2] if len(lora_split) == 3 else lora_split[1]
-                for filename in lora_filenames:
+                for filename in modules.config.lora_filenames:
                    path = Path(filename)
                    if lora_name == path.stem:
                        data[f'lora_combined_{li + 1}'] = f'{filename} : {lora_weight}'
@@ -429,7 +457,7 @@ class A1111MetadataParser(MetadataParser):

        return data

-    def parse_string(self, metadata: dict) -> str:
+    def to_string(self, metadata: dict) -> str:
        data = {k: v for _, k, v in metadata}

        width, height = eval(data['resolution'])
@@ -467,7 +495,7 @@ class A1111MetadataParser(MetadataParser):
                self.fooocus_to_a1111['refiner_model_hash']: self.refiner_model_hash
            }

-        for key in ['adaptive_cfg', 'overwrite_switch', 'refiner_swap_method', 'freeu']:
+        for key in ['adaptive_cfg', 'clip_skip', 'overwrite_switch', 'refiner_swap_method', 'freeu']:
            if key in data:
                generation_params[self.fooocus_to_a1111[key]] = data[key]

@@ -509,26 +537,22 @@ class FooocusMetadataParser(MetadataParser):
    def get_scheme(self) -> MetadataScheme:
        return MetadataScheme.FOOOCUS

-    def parse_json(self, metadata: dict) -> dict:
-        model_filenames = modules.config.model_filenames.copy()
-        lora_filenames = modules.config.lora_filenames.copy()
-        vae_filenames = modules.config.vae_filenames.copy()
-        self.remove_special_loras(lora_filenames)
+    def to_json(self, metadata: dict) -> dict:
        for key, value in metadata.items():
            if value in ['', 'None']:
                continue
            if key in ['base_model', 'refiner_model']:
-                metadata[key] = self.replace_value_with_filename(key, value, model_filenames)
+                metadata[key] = self.replace_value_with_filename(key, value, modules.config.model_filenames)
            elif key.startswith('lora_combined_'):
-                metadata[key] = self.replace_value_with_filename(key, value, lora_filenames)
+                metadata[key] = self.replace_value_with_filename(key, value, modules.config.lora_filenames)
            elif key == 'vae':
-                metadata[key] = self.replace_value_with_filename(key, value, vae_filenames)
+                metadata[key] = self.replace_value_with_filename(key, value, modules.config.vae_filenames)
            else:
                continue

        return metadata

-    def parse_string(self, metadata: list) -> str:
+    def to_string(self, metadata: list) -> str:
        for li, (label, key, value) in enumerate(metadata):
            # remove model folder paths from metadata
            if key.startswith('lora_combined_'):
@@ -568,6 +592,8 @@ class FooocusMetadataParser(MetadataParser):
            elif value == path.stem:
                return filename

+        return None
+

 def get_metadata_parser(metadata_scheme: MetadataScheme) -> MetadataParser:
    match metadata_scheme:
@@ -27,7 +27,7 @@ def log(img, metadata, metadata_parser: MetadataParser | None = None, output_for
    date_string, local_temp_filename, only_name = generate_temp_filename(folder=path_outputs, extension=output_format)
    os.makedirs(os.path.dirname(local_temp_filename), exist_ok=True)

-    parsed_parameters = metadata_parser.parse_string(metadata.copy()) if metadata_parser is not None else ''
+    parsed_parameters = metadata_parser.to_string(metadata.copy()) if metadata_parser is not None else ''
    image = Image.fromarray(img)

    if output_format == OutputFormat.PNG.value:
@@ -175,7 +175,7 @@ def calculate_sigmas_scheduler_hacked(model, scheduler_name, steps):
    elif scheduler_name == "sgm_uniform":
        sigmas = normal_scheduler(model, steps, sgm=True)
    elif scheduler_name == "turbo":
-        sigmas = SDTurboScheduler().get_sigmas(namedtuple('Patcher', ['model'])(model=model), steps=steps, denoise=1.0)[0]
+        sigmas = SDTurboScheduler().get_sigmas(model=model, steps=steps, denoise=1.0)[0]
    elif scheduler_name == "align_your_steps":
        model_type = 'SDXL' if isinstance(model.latent_format, ldm_patched.modules.latent_formats.SDXL) else 'SD1'
        sigmas = AlignYourStepsScheduler().get_sigmas(model_type=model_type, steps=steps, denoise=1.0)[0]
@@ -37,6 +37,7 @@ def sort_styles(selected):
    global all_styles
    unselected = [y for y in all_styles if y not in selected]
    sorted_styles = selected + unselected
+    """
    try:
        with open('sorted_styles.json', 'wt', encoding='utf-8') as fp:
            json.dump(sorted_styles, fp, indent=4)
@@ -44,6 +45,7 @@ def sort_styles(selected):
        print('Write style sorting failed.')
        print(e)
    all_styles = sorted_styles
+    """
    return gr.CheckboxGroup.update(choices=sorted_styles)


@@ -0,0 +1,15 @@
+import translators
+from functools import lru_cache
+
+@lru_cache(maxsize=32, typed=False)
+def translate2en(text, element):
+    if not text:
+        return text
+
+    try:
+        result = translators.translate_text(text,to_language='en')
+        print(f'[Parameters] Translated {element}: {result}')
+        return result
+    except Exception as e:
+        print(f'[Parameters] Error during translation of {element}: {e}')
+        return text
@@ -1,13 +1,11 @@
-import os
-import torch
-import modules.core as core
-
-from ldm_patched.pfn.architecture.RRDB import RRDBNet as ESRGAN
-from ldm_patched.contrib.external_upscale_model import ImageUpscaleWithModel
 from collections import OrderedDict
-from modules.config import path_upscale_models

-model_filename = os.path.join(path_upscale_models, 'fooocus_upscaler_s409985e5.bin')
+import modules.core as core
+import torch
+from ldm_patched.contrib.external_upscale_model import ImageUpscaleWithModel
+from ldm_patched.pfn.architecture.RRDB import RRDBNet as ESRGAN
+from modules.config import downloading_upscale_model
+
 opImageUpscaleWithModel = ImageUpscaleWithModel()
 model = None

@@ -18,6 +16,7 @@ def perform_upscale(img):
    print(f'Upscaling image with shape {str(img.shape)} ...')

    if model is None:
+        model_filename = downloading_upscale_model()
        sd = torch.load(model_filename)
        sdo = OrderedDict()
        for k, v in sd.items():
@@ -1,3 +1,5 @@
+from pathlib import Path
+
 import numpy as np
 import datetime
 import random
@@ -12,15 +14,16 @@ import hashlib

 from PIL import Image

+import modules.config
 import modules.sdxl_styles
+from modules.flags import Performance

 LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)

-
 # Regexp compiled once. Matches entries with the following pattern:
 # <lora:some_lora:1>
 # <lora:aNotherLora:-1.6>
-LORAS_PROMPT_PATTERN = re.compile(r".* <lora : ([^:]+) : ([+-]? (?: (?:\d+ (?:\.\d*)?) | (?:\.\d+)))> .*", re.X)
+LORAS_PROMPT_PATTERN = re.compile(r"(<lora:([^:]+):([+-]?(?:\d+(?:\.\d*)?|\.\d+))>)", re.X)

 HASH_SHA256_LENGTH = 10

@@ -173,13 +176,11 @@ def generate_temp_filename(folder='./outputs/', extension='png'):


 def sha256(filename, use_addnet_hash=False, length=HASH_SHA256_LENGTH):
-    print(f"Calculating sha256 for {filename}: ", end='')
    if use_addnet_hash:
        with open(filename, "rb") as file:
            sha256_value = addnet_hash_safetensors(file)
    else:
        sha256_value = calculate_sha256(filename)
-    print(f"{sha256_value}")

    return sha256_value[:length] if length is not None else sha256_value

@@ -360,6 +361,14 @@ def is_json(data: str) -> bool:
    return True


+def get_filname_by_stem(lora_name, filenames: List[str]) -> str | None:
+    for filename in filenames:
+        path = Path(filename)
+        if lora_name == path.stem:
+            return filename
+    return None
+
+
 def get_file_from_folder_list(name, folders):
    if not isinstance(folders, list):
        folders = [folders]
@@ -372,35 +381,88 @@ def get_file_from_folder_list(name, folders):
    return os.path.abspath(os.path.realpath(os.path.join(folders[0], name)))


-def ordinal_suffix(number: int) -> str:
-    return 'th' if 10 <= number % 100 <= 20 else {1: 'st', 2: 'nd', 3: 'rd'}.get(number % 10, 'th')
+def get_enabled_loras(loras: list, remove_none=True) -> list:
+    return [(lora[1], lora[2]) for lora in loras if lora[0] and (lora[1] != 'None' if remove_none else True)]


-def makedirs_with_log(path):
-    try:
-        os.makedirs(path, exist_ok=True)
-    except OSError as error:
-        print(f'Directory {path} could not be created, reason: {error}')
+def parse_lora_references_from_prompt(prompt: str, loras: List[Tuple[AnyStr, float]], loras_limit: int = 5,
+                                      skip_file_check=False, prompt_cleanup=True, deduplicate_loras=True,
+                                      lora_filenames=None) -> tuple[List[Tuple[AnyStr, float]], str]:
+    # prevent unintended side effects when returning without detection
+    loras = loras.copy()

+    if lora_filenames is None:
+        lora_filenames = []

-def get_enabled_loras(loras: list) -> list:
-    return [(lora[1], lora[2]) for lora in loras if lora[0]]
+    found_loras = []
+    prompt_without_loras = ''
+    cleaned_prompt = ''

+    for token in prompt.split(','):
+        matches = LORAS_PROMPT_PATTERN.findall(token)
+
+        if len(matches) == 0:
+            prompt_without_loras += token + ', '
+            continue
+        for match in matches:
+            lora_name = match[1] + '.safetensors'
+            if not skip_file_check:
+                lora_name = get_filname_by_stem(match[1], lora_filenames)
+            if lora_name is not None:
+                found_loras.append((lora_name, float(match[2])))
+            token = token.replace(match[0], '')
+        prompt_without_loras += token + ', '
+
+    if prompt_without_loras != '':
+        cleaned_prompt = prompt_without_loras[:-2]
+
+    if prompt_cleanup:
+        cleaned_prompt = cleanup_prompt(prompt_without_loras)

-def parse_lora_references_from_prompt(prompt: str, loras: List[Tuple[AnyStr, float]], loras_limit: int = 5) -> List[Tuple[AnyStr, float]]:
    new_loras = []
+    lora_names = [lora[0] for lora in loras]
+    for found_lora in found_loras:
+        if deduplicate_loras and (found_lora[0] in lora_names or found_lora in new_loras):
+            continue
+        new_loras.append(found_lora)
+
+    if len(new_loras) == 0:
+        return loras, cleaned_prompt
+
    updated_loras = []
-    for token in prompt.split(","):
-        m = LORAS_PROMPT_PATTERN.match(token)
-
-        if m:
-            new_loras.append((f"{m.group(1)}.safetensors", float(m.group(2))))
-
    for lora in loras + new_loras:
        if lora[0] != "None":
            updated_loras.append(lora)

-    return updated_loras[:loras_limit]
+    return updated_loras[:loras_limit], cleaned_prompt
+
+
+def remove_performance_lora(filenames: list, performance: Performance | None):
+    loras_without_performance = filenames.copy()
+
+    if performance is None:
+        return loras_without_performance
+
+    performance_lora = performance.lora_filename()
+
+    for filename in filenames:
+        path = Path(filename)
+        if performance_lora == path.name:
+            loras_without_performance.remove(filename)
+
+    return loras_without_performance
+
+
+def cleanup_prompt(prompt):
+    prompt = re.sub(' +', ' ', prompt)
+    prompt = re.sub(',+', ',', prompt)
+    cleaned_prompt = ''
+    for token in prompt.split(','):
+        token = token.strip()
+        if token == '':
+            continue
+        cleaned_prompt += token + ', '
+    return cleaned_prompt[:-2]


 def apply_wildcards(wildcard_text, rng, i, read_wildcards_in_order) -> str:
@@ -428,3 +490,26 @@ def apply_wildcards(wildcard_text, rng, i, read_wildcards_in_order) -> str:

    print(f'[Wildcards] BFS stack overflow. Current text: {wildcard_text}')
    return wildcard_text
+
+
+def get_image_size_info(image: np.ndarray, aspect_ratios: list) -> str:
+    try:
+        image = Image.fromarray(np.uint8(image))
+        width, height = image.size
+        ratio = round(width / height, 2)
+        gcd = math.gcd(width, height)
+        lcm_ratio = f'{width // gcd}:{height // gcd}'
+        size_info = f'Image Size: {width} x {height}, Ratio: {ratio}, {lcm_ratio}'
+
+        closest_ratio = min(aspect_ratios, key=lambda x: abs(ratio - float(x.split('*')[0]) / float(x.split('*')[1])))
+        recommended_width, recommended_height = map(int, closest_ratio.split('*'))
+        recommended_ratio = round(recommended_width / recommended_height, 2)
+        recommended_gcd = math.gcd(recommended_width, recommended_height)
+        recommended_lcm_ratio = f'{recommended_width // recommended_gcd}:{recommended_height // recommended_gcd}'
+
+        size_info = f'{width} x {height}, {ratio}, {lcm_ratio}'
+        size_info += f'\n{recommended_width} x {recommended_height}, {recommended_ratio}, {recommended_lcm_ratio}'
+
+        return size_info
+    except Exception as e:
+        return f'Error reading image: {e}'
@@ -2,5 +2,7 @@
 !anime.json
 !default.json
 !lcm.json
+!playground_v2.5.json
+!pony_v6.json
 !realistic.json
 !sai.json
@@ -1,5 +1,5 @@
 {
-    "default_model": "animaPencilXL_v310.safetensors",
+    "default_model": "animaPencilXL_v500.safetensors",
    "default_refiner": "None",
    "default_refiner_switch": 0.5,
    "default_loras": [
@@ -42,16 +42,19 @@
        "Fooocus Masterpiece"
    ],
    "default_aspect_ratio": "896*1152",
+    "default_overwrite_step": -1,
    "checkpoint_downloads": {
-        "animaPencilXL_v310.safetensors": "https://huggingface.co/mashb1t/fav_models/resolve/main/fav/animaPencilXL_v310.safetensors"
+        "animaPencilXL_v500.safetensors": "https://huggingface.co/mashb1t/fav_models/resolve/main/fav/animaPencilXL_v500.safetensors"
    },
    "embeddings_downloads": {},
    "lora_downloads": {},
    "previous_default_models": [
+        "animaPencilXL_v400.safetensors",
+        "animaPencilXL_v310.safetensors",
        "animaPencilXL_v300.safetensors",
        "animaPencilXL_v260.safetensors",
        "animaPencilXL_v210.safetensors",
        "animaPencilXL_v200.safetensors",
        "animaPencilXL_v100.safetensors"
    ]
-}
+}
@@ -42,6 +42,7 @@
        "Fooocus Sharp"
    ],
    "default_aspect_ratio": "1152*896",
+    "default_overwrite_step": -1,
    "checkpoint_downloads": {
        "juggernautXL_v8Rundiffusion.safetensors": "https://huggingface.co/lllyasviel/fav_models/resolve/main/fav/juggernautXL_v8Rundiffusion.safetensors"
    },
@@ -42,6 +42,7 @@
        "Fooocus Sharp"
    ],
    "default_aspect_ratio": "1152*896",
+    "default_overwrite_step": -1,
    "checkpoint_downloads": {
        "juggernautXL_v8Rundiffusion.safetensors": "https://huggingface.co/lllyasviel/fav_models/resolve/main/fav/juggernautXL_v8Rundiffusion.safetensors"
    },
@@ -0,0 +1,51 @@
+{
+    "default_model": "playground-v2.5-1024px-aesthetic.fp16.safetensors",
+    "default_refiner": "None",
+    "default_refiner_switch": 0.5,
+    "default_loras": [
+        [
+            true,
+            "None",
+            1.0
+        ],
+        [
+            true,
+            "None",
+            1.0
+        ],
+        [
+            true,
+            "None",
+            1.0
+        ],
+        [
+            true,
+            "None",
+            1.0
+        ],
+        [
+            true,
+            "None",
+            1.0
+        ]
+    ],
+    "default_cfg_scale": 2.0,
+    "default_sample_sharpness": 2.0,
+    "default_sampler": "dpmpp_2m",
+    "default_scheduler": "edm_playground_v2.5",
+    "default_performance": "Speed",
+    "default_prompt": "",
+    "default_prompt_negative": "",
+    "default_styles": [
+        "Fooocus V2"
+    ],
+    "default_aspect_ratio": "1024*1024",
+    "default_overwrite_step": -1,
+    "default_inpaint_engine_version": "None",
+    "checkpoint_downloads": {
+        "playground-v2.5-1024px-aesthetic.fp16.safetensors": "https://huggingface.co/mashb1t/fav_models/resolve/main/fav/playground-v2.5-1024px-aesthetic.fp16.safetensors"
+    },
+    "embeddings_downloads": {},
+    "lora_downloads": {},
+    "previous_default_models": []
+}
@@ -0,0 +1,54 @@
+{
+    "default_model": "ponyDiffusionV6XL.safetensors",
+    "default_refiner": "None",
+    "default_refiner_switch": 0.5,
+    "default_vae": "ponyDiffusionV6XL_vae.safetensors",
+    "default_loras": [
+        [
+            true,
+            "None",
+            1.0
+        ],
+        [
+            true,
+            "None",
+            1.0
+        ],
+        [
+            true,
+            "None",
+            1.0
+        ],
+        [
+            true,
+            "None",
+            1.0
+        ],
+        [
+            true,
+            "None",
+            1.0
+        ]
+    ],
+    "default_cfg_scale": 7.0,
+    "default_sample_sharpness": 2.0,
+    "default_sampler": "dpmpp_2m_sde_gpu",
+    "default_scheduler": "karras",
+    "default_performance": "Speed",
+    "default_prompt": "",
+    "default_prompt_negative": "",
+    "default_styles": [
+        "Fooocus Pony"
+    ],
+    "default_aspect_ratio": "896*1152",
+    "default_overwrite_step": -1,
+    "default_inpaint_engine_version": "None",
+    "checkpoint_downloads": {
+        "ponyDiffusionV6XL.safetensors": "https://huggingface.co/mashb1t/fav_models/resolve/main/fav/ponyDiffusionV6XL.safetensors"
+    },
+    "embeddings_downloads": {},
+    "lora_downloads": {},
+    "vae_downloads": {
+        "ponyDiffusionV6XL_vae.safetensors": "https://huggingface.co/mashb1t/fav_models/resolve/main/fav/ponyDiffusionV6XL_vae.safetensors"
+    }
+}
@@ -5,7 +5,7 @@
    "default_loras": [
        [
            true,
-            "SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors",
+            "SDXL_FILM_PHOTOGRAPHY_STYLE_V1.safetensors",
            0.25
        ],
        [
@@ -42,12 +42,13 @@
        "Fooocus Negative"
    ],
    "default_aspect_ratio": "896*1152",
+    "default_overwrite_step": -1,
    "checkpoint_downloads": {
        "realisticStockPhoto_v20.safetensors": "https://huggingface.co/lllyasviel/fav_models/resolve/main/fav/realisticStockPhoto_v20.safetensors"
    },
    "embeddings_downloads": {},
    "lora_downloads": {
-        "SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors": "https://huggingface.co/lllyasviel/fav_models/resolve/main/fav/SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors"
+        "SDXL_FILM_PHOTOGRAPHY_STYLE_V1.safetensors": "https://huggingface.co/mashb1t/fav_models/resolve/main/fav/SDXL_FILM_PHOTOGRAPHY_STYLE_V1.safetensors"
    },
    "previous_default_models": ["realisticStockPhoto_v10.safetensors"]
 }
@@ -41,6 +41,7 @@
        "Fooocus Cinematic"
    ],
    "default_aspect_ratio": "1152*896",
+    "default_overwrite_step": -1,
    "checkpoint_downloads": {
        "sd_xl_base_1.0_0.9vae.safetensors": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0_0.9vae.safetensors",
        "sd_xl_refiner_1.0_0.9vae.safetensors": "https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/resolve/main/sd_xl_refiner_1.0_0.9vae.safetensors"
@@ -285,11 +285,11 @@ See the common problems [here](troubleshoot.md).

 Given different goals, the default models and configs of Fooocus are different:

-| Task | Windows | Linux args | Main Model | Refiner | Config                                                                         |
-| --- | --- | --- | --- | --- |--------------------------------------------------------------------------------|
-| General | run.bat |  | juggernautXL_v8Rundiffusion | not used | [here](https://github.com/lllyasviel/Fooocus/blob/main/presets/default.json)   |
-| Realistic | run_realistic.bat | --preset realistic | realisticStockPhoto_v20 | not used | [here](https://github.com/lllyasviel/Fooocus/blob/main/presets/realistic.json) |
-| Anime | run_anime.bat | --preset anime | animaPencilXL_v100 | not used | [here](https://github.com/lllyasviel/Fooocus/blob/main/presets/anime.json)     |
+| Task      | Windows | Linux args | Main Model                  | Refiner | Config                                                                         |
+|-----------| --- | --- |-----------------------------| --- |--------------------------------------------------------------------------------|
+| General   | run.bat |  | juggernautXL_v8Rundiffusion | not used | [here](https://github.com/lllyasviel/Fooocus/blob/main/presets/default.json)   |
+| Realistic | run_realistic.bat | --preset realistic | realisticStockPhoto_v20     | not used | [here](https://github.com/lllyasviel/Fooocus/blob/main/presets/realistic.json) |
+| Anime     | run_anime.bat | --preset anime | animaPencilXL_v500          | not used | [here](https://github.com/lllyasviel/Fooocus/blob/main/presets/anime.json)     |

 Note that the download is **automatic** - you do not need to do anything if the internet connection is okay. However, you can download them manually if you (or move them from somewhere else) have your own preparation.

@@ -370,25 +370,36 @@ entry_with_update.py  [-h] [--listen [IP]] [--port PORT]
                      [--web-upload-size WEB_UPLOAD_SIZE]
                      [--hf-mirror HF_MIRROR]
                      [--external-working-path PATH [PATH ...]]
-                      [--output-path OUTPUT_PATH] [--temp-path TEMP_PATH]
+                      [--output-path OUTPUT_PATH]
+                      [--temp-path TEMP_PATH]
                      [--cache-path CACHE_PATH] [--in-browser]
-                      [--disable-in-browser] [--gpu-device-id DEVICE_ID]
+                      [--disable-in-browser]
+                      [--gpu-device-id DEVICE_ID]
                      [--async-cuda-allocation | --disable-async-cuda-allocation]
-                      [--disable-attention-upcast] [--all-in-fp32 | --all-in-fp16]
+                      [--disable-attention-upcast]
+                      [--all-in-fp32 | --all-in-fp16]
                      [--unet-in-bf16 | --unet-in-fp16 | --unet-in-fp8-e4m3fn | --unet-in-fp8-e5m2]
-                      [--vae-in-fp16 | --vae-in-fp32 | --vae-in-bf16]
+                      [--vae-in-fp16 | --vae-in-fp32 | --vae-in-bf16]   
+                      [--vae-in-cpu]
                      [--clip-in-fp8-e4m3fn | --clip-in-fp8-e5m2 | --clip-in-fp16 | --clip-in-fp32]
-                      [--directml [DIRECTML_DEVICE]] [--disable-ipex-hijack]
+                      [--directml [DIRECTML_DEVICE]]
+                      [--disable-ipex-hijack]
                      [--preview-option [none,auto,fast,taesd]]
                      [--attention-split | --attention-quad | --attention-pytorch]
                      [--disable-xformers]
-                      [--always-gpu | --always-high-vram | --always-normal-vram | 
-                       --always-low-vram | --always-no-vram | --always-cpu [CPU_NUM_THREADS]]
-                      [--always-offload-from-vram] [--disable-server-log]
-                      [--debug-mode] [--is-windows-embedded-python]
-                      [--disable-server-info] [--share] [--preset PRESET]
-                      [--language LANGUAGE] [--disable-offload-from-vram]
-                      [--theme THEME] [--disable-image-log]
+                      [--always-gpu | --always-high-vram | --always-normal-vram |
+                      --always-low-vram | --always-no-vram | --always-cpu [CPU_NUM_THREADS]]
+                      [--always-offload-from-vram]
+                      [--pytorch-deterministic] [--disable-server-log]  
+                      [--debug-mode] [--is-windows-embedded-python]     
+                      [--disable-server-info] [--multi-user] [--share]  
+                      [--preset PRESET] [--disable-preset-selection]    
+                      [--language LANGUAGE]
+                      [--disable-offload-from-vram] [--theme THEME]     
+                      [--disable-image-log] [--disable-analytics]       
+                      [--disable-metadata] [--disable-preset-download]  
+                      [--enable-describe-uov-image]
+                      [--always-download-new-model]
 ```

 ## Advanced Features
@@ -1,5 +1,2 @@
-torch==2.0.1
-torchvision==0.15.2
-torchaudio==2.0.2
-torchtext==0.15.2
-torchdata==0.6.1
+torch==2.1.0
+torchvision==0.16.0
@@ -6,7 +6,7 @@ accelerate==0.21.0
 pyyaml==6.0
 Pillow==9.2.0
 scipy==1.9.3
-tqdm==4.64.1
+tqdm==4.65.0
 psutil==5.9.5
 pytorch_lightning==1.9.4
 omegaconf==2.2.3
@@ -16,3 +16,7 @@ opencv-contrib-python==4.8.0.74
 httpx==0.24.1
 onnxruntime==1.16.3
 timm==0.9.2
+translators==5.9.2
+rembg==2.0.57
+groundingdino-py==0.4.0
+segment_anything==1.0
@@ -14,7 +14,7 @@
    },
    {
        "name": "Fooocus Masterpiece",
-        "prompt": "(masterpiece), (best quality), (ultra-detailed), {prompt}, illustration, disheveled hair, detailed eyes, perfect composition, moist skin, intricate details, earrings, by wlop",
+        "prompt": "(masterpiece), (best quality), (ultra-detailed), {prompt}, illustration, disheveled hair, detailed eyes, perfect composition, moist skin, intricate details, earrings",
        "negative_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, fewer digits, cropped, worst quality, low quality"
    },
    {
@@ -30,5 +30,10 @@
        "name": "Fooocus Cinematic",
        "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured"
+    },
+    {
+        "name": "Fooocus Pony",
+        "prompt": "score_9, score_8_up, score_7_up, {prompt}",
+        "negative_prompt": "score_6, score_5, score_4"
    }
 ]
@@ -0,0 +1,74 @@
+import numbers
+import os
+import unittest
+
+import modules.flags
+from modules import extra_utils
+
+
+class TestUtils(unittest.TestCase):
+    def test_try_eval_env_var(self):
+        test_cases = [
+            {
+                "input": ("foo", str),
+                "output": "foo"
+            },
+            {
+                "input": ("1", int),
+                "output": 1
+            },
+            {
+                "input": ("1.0", float),
+                "output": 1.0
+            },
+            {
+                "input": ("1", numbers.Number),
+                "output": 1
+            },
+            {
+                "input": ("1.0", numbers.Number),
+                "output": 1.0
+            },
+            {
+                "input": ("true", bool),
+                "output": True
+            },
+            {
+                "input": ("True", bool),
+                "output": True
+            },
+            {
+                "input": ("false", bool),
+                "output": False
+            },
+            {
+                "input": ("False", bool),
+                "output": False
+            },
+            {
+                "input": ("True", str),
+                "output": "True"
+            },
+            {
+                "input": ("False", str),
+                "output": "False"
+            },
+            {
+                "input": ("['a', 'b', 'c']", list),
+                "output": ['a', 'b', 'c']
+            },
+            {
+                "input": ("{'a':1}", dict),
+                "output": {'a': 1}
+            },
+            {
+                "input": ("('foo', 1)", tuple),
+                "output": ('foo', 1)
+            }
+        ]
+
+        for test in test_cases:
+            value, expected_type = test["input"]
+            expected = test["output"]
+            actual = extra_utils.try_eval_env_var(value, expected_type)
+            self.assertEqual(expected, actual)
@@ -1,5 +1,7 @@
+import os
 import unittest

+import modules.flags
 from modules import util


@@ -7,13 +9,17 @@ class TestUtils(unittest.TestCase):
    def test_can_parse_tokens_with_lora(self):
        test_cases = [
            {
-                "input": ("some prompt, very cool, <lora:hey-lora:0.4>,  cool   <lora:you-lora:0.2>", [], 5),
-                "output": [("hey-lora.safetensors", 0.4), ("you-lora.safetensors", 0.2)],
+                "input": ("some prompt, very cool, <lora:hey-lora:0.4>,  cool   <lora:you-lora:0.2>", [], 5, True),
+                "output": (
+                    [('hey-lora.safetensors', 0.4), ('you-lora.safetensors', 0.2)], 'some prompt, very cool, cool'),
            },
            # Test can not exceed limit
            {
-                "input": ("some prompt, very cool, <lora:hey-lora:0.4>,  cool   <lora:you-lora:0.2>", [], 1),
-                "output": [("hey-lora.safetensors", 0.4)],
+                "input": ("some prompt, very cool, <lora:hey-lora:0.4>,  cool   <lora:you-lora:0.2>", [], 1, True),
+                "output": (
+                    [('hey-lora.safetensors', 0.4)],
+                    'some prompt, very cool, cool'
+                ),
            },
            # test Loras from UI take precedence over prompt
            {
@@ -21,28 +27,111 @@ class TestUtils(unittest.TestCase):
                    "some prompt, very cool, <lora:l1:0.4>, <lora:l2:-0.2>, <lora:l3:0.3>, <lora:l4:0.5>, <lora:l6:0.24>, <lora:l7:0.1>",
                    [("hey-lora.safetensors", 0.4)],
                    5,
+                    True
                ),
-                "output": [
-                    ("hey-lora.safetensors", 0.4),
-                    ("l1.safetensors", 0.4),
-                    ("l2.safetensors", -0.2),
-                    ("l3.safetensors", 0.3),
-                    ("l4.safetensors", 0.5),
-                ],
+                "output": (
+                    [
+                        ('hey-lora.safetensors', 0.4),
+                        ('l1.safetensors', 0.4),
+                        ('l2.safetensors', -0.2),
+                        ('l3.safetensors', 0.3),
+                        ('l4.safetensors', 0.5)
+                    ],
+                    'some prompt, very cool'
+                )
            },
-            # Test lora specification not separated by comma are ignored, only latest specified is used
+            # test correct matching even if there is no space separating loras in the same token
            {
-                "input": ("some prompt, very cool, <lora:hey-lora:0.4><lora:you-lora:0.2>", [], 3),
-                "output": [("you-lora.safetensors", 0.2)],
+                "input": ("some prompt, very cool, <lora:hey-lora:0.4><lora:you-lora:0.2>", [], 3, True),
+                "output": (
+                    [
+                        ('hey-lora.safetensors', 0.4),
+                        ('you-lora.safetensors', 0.2)
+                    ],
+                    'some prompt, very cool'
+                ),
+            },
+            # test deduplication, also selected loras are never overridden with loras in prompt
+            {
+                "input": (
+                    "some prompt, very cool, <lora:hey-lora:0.4><lora:hey-lora:0.4><lora:you-lora:0.2>",
+                    [('you-lora.safetensors', 0.3)],
+                    3,
+                    True
+                ),
+                "output": (
+                    [
+                        ('you-lora.safetensors', 0.3),
+                        ('hey-lora.safetensors', 0.4)
+                    ],
+                    'some prompt, very cool'
+                ),
            },
            {
-                "input": ("<lora:foo:1..2>, <lora:bar:.>, <lora:baz:+> and <lora:quux:>", [], 6),
-                "output": []
+                "input": ("<lora:foo:1..2>, <lora:bar:.>, <test:1.0>, <lora:baz:+> and <lora:quux:>", [], 6, True),
+                "output": (
+                    [],
+                    '<lora:foo:1..2>, <lora:bar:.>, <test:1.0>, <lora:baz:+> and <lora:quux:>'
+                )
            }
        ]

        for test in test_cases:
-            prompt, loras, loras_limit = test["input"]
+            prompt, loras, loras_limit, skip_file_check = test["input"]
            expected = test["output"]
-            actual = util.parse_lora_references_from_prompt(prompt, loras, loras_limit)
+            actual = util.parse_lora_references_from_prompt(prompt, loras, loras_limit=loras_limit,
+                                                            skip_file_check=skip_file_check)
+            self.assertEqual(expected, actual)
+
+    def test_can_parse_tokens_and_strip_performance_lora(self):
+        lora_filenames = [
+            'hey-lora.safetensors',
+            modules.flags.PerformanceLoRA.EXTREME_SPEED.value,
+            modules.flags.PerformanceLoRA.LIGHTNING.value,
+            os.path.join('subfolder', modules.flags.PerformanceLoRA.HYPER_SD.value)
+        ]
+
+        test_cases = [
+            {
+                "input": ("some prompt, <lora:hey-lora:0.4>", [], 5, True, modules.flags.Performance.QUALITY),
+                "output": (
+                    [('hey-lora.safetensors', 0.4)],
+                    'some prompt'
+                ),
+            },
+            {
+                "input": ("some prompt, <lora:hey-lora:0.4>", [], 5, True, modules.flags.Performance.SPEED),
+                "output": (
+                    [('hey-lora.safetensors', 0.4)],
+                    'some prompt'
+                ),
+            },
+            {
+                "input": ("some prompt, <lora:sdxl_lcm_lora:1>, <lora:hey-lora:0.4>", [], 5, True, modules.flags.Performance.EXTREME_SPEED),
+                "output": (
+                    [('hey-lora.safetensors', 0.4)],
+                    'some prompt'
+                ),
+            },
+            {
+                "input": ("some prompt, <lora:sdxl_lightning_4step_lora:1>, <lora:hey-lora:0.4>", [], 5, True, modules.flags.Performance.LIGHTNING),
+                "output": (
+                    [('hey-lora.safetensors', 0.4)],
+                    'some prompt'
+                ),
+            },
+            {
+                "input": ("some prompt, <lora:sdxl_hyper_sd_4step_lora:1>, <lora:hey-lora:0.4>", [], 5, True, modules.flags.Performance.HYPER_SD),
+                "output": (
+                    [('hey-lora.safetensors', 0.4)],
+                    'some prompt'
+                ),
+            }
+        ]
+
+        for test in test_cases:
+            prompt, loras, loras_limit, skip_file_check, performance = test["input"]
+            lora_filenames = modules.util.remove_performance_lora(lora_filenames, performance)
+            expected = test["output"]
+            actual = util.parse_lora_references_from_prompt(prompt, loras, loras_limit=loras_limit, lora_filenames=lora_filenames)
            self.assertEqual(expected, actual)
@@ -1,3 +1,65 @@
+# [2.5.0-rc1](https://github.com/lllyasviel/Fooocus/releases/tag/v2.5.0-rc1)
+
+* Add enhance feature, which offers easy image refinement steps (similar to adetailer, but based on dynamic image detection instead of specific mask detection models). See [documentation](https://github.com/lllyasviel/Fooocus/discussions/3281).
+* Rewrite async worker code, make code much more reusable to allow iterations and improve reusability
+* Improve GroundingDINO and SAM image masking
+* Fix inference tensor version counter tracking issue for GroundingDINO after using Enhance (see [discussion](https://github.com/lllyasviel/Fooocus/discussions/3213))
+* Update python dependencies, add segment_anything
+* Move checkboxes Enable Mask Upload and Invert Mask When Generating from Developer Debug Mode to Inpaint Or Outpaint
+* Add persistent model cache for metadata. Use `--rebuild-hash-cache X` (X = int, number of CPU cores, default all) to manually rebuild the cache for all non-cached hashes
+* Rename `--enable-describe-uov-image` to `--enable-auto-describe-image`, now also works for enhance image upload
+* Rename checkbox `Enable Mask Upload` to `Enable Advanced Masking Features` to better hint to mask auto-generation feature
+* Get upscale model filepath by calling downloading_upscale_model() to ensure the model exists
+* Rename tab titles and translations from singular to plural
+* Rename document to documentation
+* Update default models to latest versions
+  * animaPencilXL_v400 => animaPencilXL_v500
+  * DreamShaperXL_Turbo_dpmppSdeKarras => DreamShaperXL_Turbo_v2_1
+  * SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4 => SDXL_FILM_PHOTOGRAPHY_STYLE_V1
+* Add preset for pony_v6 (using ponyDiffusionV6XL)
+* Add style `Fooocus Pony`
+* Add restart sampler ([paper](https://arxiv.org/abs/2306.14878))
+* Add config option for default_inpaint_engine_version, sets inpaint engine for pony_v6 and playground_v2.5 to None for improved results (incompatible with inpaint engine)
+* Add image editor functionality to mask upload (same as for inpaint, now correctly resizes and allows more detailed mask creation)
+
+# [2.4.3](https://github.com/lllyasviel/Fooocus/releases/tag/v2.4.3)
+
+* Fix alphas_cumprod setter for TCD sampler
+* Add parser for env var strings to expected config value types to allow override of all non-path config keys 
+
+# [2.4.2](https://github.com/lllyasviel/Fooocus/releases/tag/v2.4.2)
+
+* Fix some small bugs (tcd scheduler when gamma is 0, chown in Dockerfile, update cmd args in readme, translation for aspect ratios, vae default after file reload)
+* Fix performance LoRA replacement when data is loaded from history log and inline prompt
+* Add support and preset for playground v2.5 (only works with performance Quality or Speed, use with scheduler edm_playground_v2)
+* Make textboxes (incl. positive prompt) resizable
+* Hide intermediate images when performance of Gradio would bottleneck the generation process (Extreme Speed, Lightning, Hyper-SD)
+
+# [2.4.1](https://github.com/lllyasviel/Fooocus/releases/tag/v2.4.1)
+
+* Fix some small bugs (e.g. adjust clip skip default value from 1 to 2, add type check to aspect ratios js update function)
+* Add automated docker build on push to main, tagged with `edge`. See [available docker images](https://github.com/lllyasviel/Fooocus/pkgs/container/fooocus).
+
+# [2.4.0](https://github.com/lllyasviel/Fooocus/releases/tag/v2.4.0)
+
+* Change settings tab elements to be more compact
+* Add clip skip slider
+* Add select for custom VAE
+* Add new style "Random Style"
+* Update default anime model to animaPencilXL_v310
+* Add button to reconnect the UI after Fooocus crashed without having to configure everything again (no page reload required)
+* Add performance "hyper-sd" (based on [Hyper-SDXL 4 step LoRA](https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-SDXL-4steps-lora.safetensors))
+* Add [AlignYourSteps](https://research.nvidia.com/labs/toronto-ai/AlignYourSteps/) scheduler by Nvidia, see 
+* Add [TCD](https://github.com/jabir-zheng/TCD) sampler and scheduler (based on sgm_uniform)
+* Add NSFW image censoring (disables intermediate image preview while generating). Set config value `default_black_out_nsfw` to True to always enable.
+* Add argument `--enable-describe-uov-image` to automatically describe uploaded images for upscaling
+* Add inline lora prompt references with subfolder support, example prompt: `colorful bird <lora:toucan:1.2>`
+* Add size and aspect ratio recommendation on image describe
+* Add inpaint brush color picker, helpful when image and mask brush have the same color
+* Add automated Docker image build using Github Actions on each release.
+* Add full raw prompts to history logs
+* Change code ownership from @lllyasviel to @mashb1t for automated issue / MR notification
+
 # [2.3.1](https://github.com/lllyasviel/Fooocus/releases/tag/2.3.1)

 * Remove positive prompt from anime prefix to not reset prompt after switching presets
@@ -16,6 +16,7 @@ import modules.meta_parser
 import args_manager
 import copy
 import launch
+from extras.inpaint_mask import SAMOptions

 from modules.sdxl_styles import legal_style_names
 from modules.private_logger import get_current_html_path
@@ -89,6 +90,37 @@ def generate_clicked(task: worker.AsyncTask):
    return


+def inpaint_mode_change(mode, inpaint_engine_version):
+    assert mode in modules.flags.inpaint_options
+
+    # inpaint_additional_prompt, outpaint_selections, example_inpaint_prompts,
+    # inpaint_disable_initial_latent, inpaint_engine,
+    # inpaint_strength, inpaint_respective_field
+
+    if mode == modules.flags.inpaint_option_detail:
+        return [
+            gr.update(visible=True), gr.update(visible=False, value=[]),
+            gr.Dataset.update(visible=True, samples=modules.config.example_inpaint_prompts),
+            False, 'None', 0.5, 0.0
+        ]
+
+    if inpaint_engine_version == 'empty':
+        inpaint_engine_version = modules.config.default_inpaint_engine_version
+
+    if mode == modules.flags.inpaint_option_modify:
+        return [
+            gr.update(visible=True), gr.update(visible=False, value=[]),
+            gr.Dataset.update(visible=False, samples=modules.config.example_inpaint_prompts),
+            True, inpaint_engine_version, 1.0, 0.0
+        ]
+
+    return [
+        gr.update(visible=False, value=''), gr.update(visible=True),
+        gr.Dataset.update(visible=False, samples=modules.config.example_inpaint_prompts),
+        False, inpaint_engine_version, 1.0, 0.618
+    ]
+
+
 reload_javascript()

 title = f'Fooocus {fooocus_version.version}'
@@ -100,6 +132,7 @@ shared.gradio_root = gr.Blocks(title=title).queue()

 with shared.gradio_root:
    currentTask = gr.State(worker.AsyncTask(args=[]))
+    inpaint_engine_state = gr.State('empty')
    with gr.Row():
        with gr.Column(scale=2):
            with gr.Row():
@@ -112,10 +145,10 @@ with shared.gradio_root:
            gallery = gr.Gallery(label='Gallery', show_label=False, object_fit='contain', visible=True, height=768,
                                 elem_classes=['resizable_area', 'main_view', 'final_gallery', 'image_gallery'],
                                 elem_id='final_gallery')
-            with gr.Row(elem_classes='type_row'):
+            with gr.Row():
                with gr.Column(scale=17):
                    prompt = gr.Textbox(show_label=False, placeholder="Type prompt here or paste parameters.", elem_id='positive_prompt',
-                                        container=False, autofocus=True, elem_classes='type_row', lines=1024)
+                                        autofocus=True, lines=3)

                    default_prompt = modules.config.default_prompt
                    if isinstance(default_prompt, str) and default_prompt != '':
@@ -146,16 +179,17 @@ with shared.gradio_root:
                    skip_button.click(skip_clicked, inputs=currentTask, outputs=currentTask, queue=False, show_progress=False)
            with gr.Row(elem_classes='advanced_check_row'):
                input_image_checkbox = gr.Checkbox(label='Input Image', value=False, container=False, elem_classes='min_check')
+                enhance_checkbox = gr.Checkbox(label='Enhance', value=modules.config.default_enhance_checkbox, container=False, elem_classes='min_check')
                advanced_checkbox = gr.Checkbox(label='Advanced', value=modules.config.default_advanced_checkbox, container=False, elem_classes='min_check')
            with gr.Row(visible=False) as image_input_panel:
                with gr.Tabs():
                    with gr.TabItem(label='Upscale or Variation') as uov_tab:
                        with gr.Row():
                            with gr.Column():
-                                uov_input_image = grh.Image(label='Drag above image to here', source='upload', type='numpy')
+                                uov_input_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False)
                            with gr.Column():
                                uov_method = gr.Radio(label='Upscale or Variation:', choices=flags.uov_list, value=flags.disabled)
-                                gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/390" target="_blank">\U0001F4D4 Document</a>')
+                                gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/390" target="_blank">\U0001F4D4 Documentation</a>')
                    with gr.TabItem(label='Image Prompt') as ip_tab:
                        with gr.Row():
                            ip_images = []
@@ -188,7 +222,7 @@ with shared.gradio_root:
                                        ip_type.change(lambda x: flags.default_parameters[x], inputs=[ip_type], outputs=[ip_stop, ip_weight], queue=False, show_progress=False)
                                    ip_ad_cols.append(ad_col)
                        ip_advanced = gr.Checkbox(label='Advanced', value=False, container=False)
-                        gr.HTML('* \"Image Prompt\" is powered by Fooocus Image Mixture Engine (v1.0.1). <a href="https://github.com/lllyasviel/Fooocus/discussions/557" target="_blank">\U0001F4D4 Document</a>')
+                        gr.HTML('* \"Image Prompt\" is powered by Fooocus Image Mixture Engine (v1.0.1). <a href="https://github.com/lllyasviel/Fooocus/discussions/557" target="_blank">\U0001F4D4 Documentation</a>')

                        def ip_advance_checked(x):
                            return [gr.update(visible=x)] * len(ip_ad_cols) + \
@@ -199,32 +233,113 @@ with shared.gradio_root:
                        ip_advanced.change(ip_advance_checked, inputs=ip_advanced,
                                           outputs=ip_ad_cols + ip_types + ip_stops + ip_weights,
                                           queue=False, show_progress=False)
+
                    with gr.TabItem(label='Inpaint or Outpaint') as inpaint_tab:
                        with gr.Row():
-                            inpaint_input_image = grh.Image(label='Drag inpaint or outpaint image to here', source='upload', type='numpy', tool='sketch', height=500, brush_color="#FFFFFF", elem_id='inpaint_canvas')
-                            inpaint_mask_image = grh.Image(label='Mask Upload', source='upload', type='numpy', height=500, visible=False)
+                            with gr.Column():
+                                inpaint_input_image = grh.Image(label='Image', source='upload', type='numpy', tool='sketch', height=500, brush_color="#FFFFFF", elem_id='inpaint_canvas', show_label=False)
+                                inpaint_advanced_masking_checkbox = gr.Checkbox(label='Enable Advanced Masking Features', value=False)
+                                inpaint_mode = gr.Dropdown(choices=modules.flags.inpaint_options, value=modules.config.default_inpaint_method, label='Method')
+                                inpaint_additional_prompt = gr.Textbox(placeholder="Describe what you want to inpaint.", elem_id='inpaint_additional_prompt', label='Inpaint Additional Prompt', visible=False)
+                                outpaint_selections = gr.CheckboxGroup(choices=['Left', 'Right', 'Top', 'Bottom'], value=[], label='Outpaint Direction')
+                                example_inpaint_prompts = gr.Dataset(samples=modules.config.example_inpaint_prompts,
+                                                                     label='Additional Prompt Quick List',
+                                                                     components=[inpaint_additional_prompt],
+                                                                     visible=False)
+                                gr.HTML('* Powered by Fooocus Inpaint Engine <a href="https://github.com/lllyasviel/Fooocus/discussions/414" target="_blank">\U0001F4D4 Documentation</a>')
+                                example_inpaint_prompts.click(lambda x: x[0], inputs=example_inpaint_prompts, outputs=inpaint_additional_prompt, show_progress=False, queue=False)
+
+                            with gr.Column(visible=False) as inpaint_mask_generation_col:
+                                inpaint_mask_image = grh.Image(label='Mask Upload', source='upload', type='numpy', tool='sketch', height=500, brush_color="#FFFFFF", mask_opacity=1, elem_id='inpaint_mask_canvas')
+                                invert_mask_checkbox = gr.Checkbox(label='Invert Mask When Generating', value=False)
+                                inpaint_mask_model = gr.Dropdown(label='Mask generation model',
+                                                                 choices=flags.inpaint_mask_models,
+                                                                 value=modules.config.default_inpaint_mask_model)
+                                inpaint_mask_cloth_category = gr.Dropdown(label='Cloth category',
+                                                             choices=flags.inpaint_mask_cloth_category,
+                                                             value=modules.config.default_inpaint_mask_cloth_category,
+                                                             visible=False)
+                                inpaint_mask_dino_prompt_text = gr.Textbox(label='Detection prompt', value='', visible=False, info='Use singular whenever possible', placeholder='Describe what you want to detect.')
+                                example_inpaint_mask_dino_prompt_text = gr.Dataset(
+                                    samples=modules.config.example_enhance_detection_prompts,
+                                    label='Detection Prompt Quick List',
+                                    components=[inpaint_mask_dino_prompt_text],
+                                    visible=modules.config.default_inpaint_mask_model == 'sam')
+                                example_inpaint_mask_dino_prompt_text.click(lambda x: x[0],
+                                                                            inputs=example_inpaint_mask_dino_prompt_text,
+                                                                            outputs=inpaint_mask_dino_prompt_text,
+                                                                            show_progress=False, queue=False)
+
+                                with gr.Accordion("Advanced options", visible=False, open=False) as inpaint_mask_advanced_options:
+                                    inpaint_mask_sam_model = gr.Dropdown(label='SAM model', choices=flags.inpaint_mask_sam_model, value=modules.config.default_inpaint_mask_sam_model)
+                                    inpaint_mask_box_threshold = gr.Slider(label="Box Threshold", minimum=0.0, maximum=1.0, value=0.3, step=0.05)
+                                    inpaint_mask_text_threshold = gr.Slider(label="Text Threshold", minimum=0.0, maximum=1.0, value=0.25, step=0.05)
+                                    inpaint_mask_sam_max_detections = gr.Slider(label="Maximum number of detections", info="Set to 0 to detect all", minimum=0, maximum=10, value=modules.config.default_sam_max_detections, step=1, interactive=True)
+                                generate_mask_button = gr.Button(value='Generate mask from image')
+
+                                def generate_mask(image, mask_model, cloth_category, dino_prompt_text, sam_model, box_threshold, text_threshold, sam_max_detections, dino_erode_or_dilate, dino_debug):
+                                    from extras.inpaint_mask import generate_mask_from_image
+
+                                    extras = {}
+                                    sam_options = None
+                                    if mask_model == 'u2net_cloth_seg':
+                                        extras['cloth_category'] = cloth_category
+                                    elif mask_model == 'sam':
+                                        sam_options = SAMOptions(
+                                            dino_prompt=dino_prompt_text,
+                                            dino_box_threshold=box_threshold,
+                                            dino_text_threshold=text_threshold,
+                                            dino_erode_or_dilate=dino_erode_or_dilate,
+                                            dino_debug=dino_debug,
+                                            max_detections=sam_max_detections,
+                                            model_type=sam_model
+                                        )
+
+                                    mask, _, _, _ = generate_mask_from_image(image, mask_model, extras, sam_options)
+
+                                    return mask
+
+
+                                inpaint_mask_model.change(lambda x: [gr.update(visible=x == 'u2net_cloth_seg')] +
+                                                                    [gr.update(visible=x == 'sam')] * 2 +
+                                                                    [gr.Dataset.update(visible=x == 'sam',
+                                                                                       samples=modules.config.example_enhance_detection_prompts)],
+                                                          inputs=inpaint_mask_model,
+                                                          outputs=[inpaint_mask_cloth_category,
+                                                                   inpaint_mask_dino_prompt_text,
+                                                                   inpaint_mask_advanced_options,
+                                                                   example_inpaint_mask_dino_prompt_text],
+                                                          queue=False, show_progress=False)

-                        with gr.Row():
-                            inpaint_additional_prompt = gr.Textbox(placeholder="Describe what you want to inpaint.", elem_id='inpaint_additional_prompt', label='Inpaint Additional Prompt', visible=False)
-                            outpaint_selections = gr.CheckboxGroup(choices=['Left', 'Right', 'Top', 'Bottom'], value=[], label='Outpaint Direction')
-                            inpaint_mode = gr.Dropdown(choices=modules.flags.inpaint_options, value=modules.flags.inpaint_option_default, label='Method')
-                        example_inpaint_prompts = gr.Dataset(samples=modules.config.example_inpaint_prompts, label='Additional Prompt Quick List', components=[inpaint_additional_prompt], visible=False)
-                        gr.HTML('* Powered by Fooocus Inpaint Engine <a href="https://github.com/lllyasviel/Fooocus/discussions/414" target="_blank">\U0001F4D4 Document</a>')
-                        example_inpaint_prompts.click(lambda x: x[0], inputs=example_inpaint_prompts, outputs=inpaint_additional_prompt, show_progress=False, queue=False)
                    with gr.TabItem(label='Describe') as desc_tab:
                        with gr.Row():
                            with gr.Column():
-                                desc_input_image = grh.Image(label='Drag any image to here', source='upload', type='numpy')
+                                desc_input_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False)
                            with gr.Column():
                                desc_method = gr.Radio(
                                    label='Content Type',
                                    choices=[flags.desc_type_photo, flags.desc_type_anime],
                                    value=flags.desc_type_photo)
                                desc_btn = gr.Button(value='Describe this Image into Prompt')
-                                gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/1363" target="_blank">\U0001F4D4 Document</a>')
-                    with gr.TabItem(label='Metadata') as load_tab:
+                                desc_image_size = gr.Textbox(label='Image Size and Recommended Size', elem_id='desc_image_size', visible=False)
+                                gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/1363" target="_blank">\U0001F4D4 Documentation</a>')
+
+                                def trigger_show_image_properties(image):
+                                    value = modules.util.get_image_size_info(image, modules.flags.sdxl_aspect_ratios)
+                                    return gr.update(value=value, visible=True)
+
+                                desc_input_image.upload(trigger_show_image_properties, inputs=desc_input_image,
+                                                        outputs=desc_image_size, show_progress=False, queue=False)
+
+                    with gr.TabItem(label='Enhance') as enhance_tab:
+                        with gr.Row():
+                            with gr.Column():
+                                enhance_input_image = grh.Image(label='Use with Enhance, skips image generation', source='upload', type='numpy')
+                                gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/3281" target="_blank">\U0001F4D4 Documentation</a>')
+
+                    with gr.TabItem(label='Metadata') as metadata_tab:
                        with gr.Column():
-                            metadata_input_image = grh.Image(label='Drag any image generated by Fooocus here', source='upload', type='filepath')
+                            metadata_input_image = grh.Image(label='For images created by Fooocus', source='upload', type='filepath')
                            metadata_json = gr.JSON(label='Metadata')
                            metadata_import_button = gr.Button(value='Apply Metadata')

@@ -243,6 +358,164 @@ with shared.gradio_root:
                        metadata_input_image.upload(trigger_metadata_preview, inputs=metadata_input_image,
                                                    outputs=metadata_json, queue=False, show_progress=True)

+            with gr.Row(visible=modules.config.default_enhance_checkbox) as enhance_input_panel:
+                with gr.Tabs():
+                    with gr.TabItem(label='Upscale or Variation'):
+                        with gr.Row():
+                            with gr.Column():
+                                enhance_uov_method = gr.Radio(label='Upscale or Variation:', choices=flags.uov_list,
+                                                              value=modules.config.default_enhance_uov_method)
+                                enhance_uov_processing_order = gr.Radio(label='Order of Processing',
+                                                                        info='Use before to enhance small details and after to enhance large areas.',
+                                                                        choices=flags.enhancement_uov_processing_order,
+                                                                        value=modules.config.default_enhance_uov_processing_order)
+                                enhance_uov_prompt_type = gr.Radio(label='Prompt',
+                                                                   info='Choose which prompt to use for Upscale or Variation.',
+                                                                   choices=flags.enhancement_uov_prompt_types,
+                                                                   value=modules.config.default_enhance_uov_prompt_type,
+                                                                   visible=modules.config.default_enhance_uov_processing_order == flags.enhancement_uov_after)
+
+                                enhance_uov_processing_order.change(lambda x: gr.update(visible=x == flags.enhancement_uov_after),
+                                                                    inputs=enhance_uov_processing_order,
+                                                                    outputs=enhance_uov_prompt_type,
+                                                                    queue=False, show_progress=False)
+                                gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/3281" target="_blank">\U0001F4D4 Documentation</a>')
+                    enhance_ctrls = []
+                    enhance_inpaint_mode_ctrls = []
+                    enhance_inpaint_engine_ctrls = []
+                    enhance_inpaint_update_ctrls = []
+                    for index in range(modules.config.default_enhance_tabs):
+                        with gr.TabItem(label=f'#{index + 1}') as enhance_tab_item:
+                            enhance_enabled = gr.Checkbox(label='Enable', value=False, elem_classes='min_check',
+                                                          container=False)
+
+                            enhance_mask_dino_prompt_text = gr.Textbox(label='Detection prompt',
+                                                                       info='Use singular whenever possible',
+                                                                       placeholder='Describe what you want to detect.',
+                                                                       interactive=True,
+                                                                       visible=modules.config.default_enhance_inpaint_mask_model == 'sam')
+                            example_enhance_mask_dino_prompt_text = gr.Dataset(
+                                samples=modules.config.example_enhance_detection_prompts,
+                                label='Detection Prompt Quick List',
+                                components=[enhance_mask_dino_prompt_text],
+                                visible=modules.config.default_enhance_inpaint_mask_model == 'sam')
+                            example_enhance_mask_dino_prompt_text.click(lambda x: x[0],
+                                                                        inputs=example_enhance_mask_dino_prompt_text,
+                                                                        outputs=enhance_mask_dino_prompt_text,
+                                                                        show_progress=False, queue=False)
+
+                            enhance_prompt = gr.Textbox(label="Enhancement positive prompt",
+                                                        placeholder="Uses original prompt instead if empty.",
+                                                        elem_id='enhance_prompt')
+                            enhance_negative_prompt = gr.Textbox(label="Enhancement negative prompt",
+                                                                 placeholder="Uses original negative prompt instead if empty.",
+                                                                 elem_id='enhance_negative_prompt')
+
+                            with gr.Accordion("Detection", open=False):
+                                enhance_mask_model = gr.Dropdown(label='Mask generation model',
+                                                                 choices=flags.inpaint_mask_models,
+                                                                 value=modules.config.default_enhance_inpaint_mask_model)
+                                enhance_mask_cloth_category = gr.Dropdown(label='Cloth category',
+                                                                          choices=flags.inpaint_mask_cloth_category,
+                                                                          value=modules.config.default_inpaint_mask_cloth_category,
+                                                                          visible=modules.config.default_enhance_inpaint_mask_model == 'u2net_cloth_seg',
+                                                                          interactive=True)
+
+                                with gr.Accordion("SAM Options",
+                                                  visible=modules.config.default_enhance_inpaint_mask_model == 'sam',
+                                                  open=False) as sam_options:
+                                    enhance_mask_sam_model = gr.Dropdown(label='SAM model',
+                                                                         choices=flags.inpaint_mask_sam_model,
+                                                                         value=modules.config.default_inpaint_mask_sam_model,
+                                                                         interactive=True)
+                                    enhance_mask_box_threshold = gr.Slider(label="Box Threshold", minimum=0.0,
+                                                                           maximum=1.0, value=0.3, step=0.05,
+                                                                           interactive=True)
+                                    enhance_mask_text_threshold = gr.Slider(label="Text Threshold", minimum=0.0,
+                                                                            maximum=1.0, value=0.25, step=0.05,
+                                                                            interactive=True)
+                                    enhance_mask_sam_max_detections = gr.Slider(label="Maximum number of detections",
+                                                                                info="Set to 0 to detect all",
+                                                                                minimum=0, maximum=10,
+                                                                                value=modules.config.default_sam_max_detections,
+                                                                                step=1, interactive=True)
+
+                            with gr.Accordion("Inpaint", visible=True, open=False):
+                                enhance_inpaint_mode = gr.Dropdown(choices=modules.flags.inpaint_options,
+                                                                   value=modules.config.default_inpaint_method,
+                                                                   label='Method', interactive=True)
+                                enhance_inpaint_disable_initial_latent = gr.Checkbox(
+                                    label='Disable initial latent in inpaint', value=False)
+                                enhance_inpaint_engine = gr.Dropdown(label='Inpaint Engine',
+                                                                     value=modules.config.default_inpaint_engine_version,
+                                                                     choices=flags.inpaint_engine_versions,
+                                                                     info='Version of Fooocus inpaint model. If set, use performance Quality or Speed (no performance LoRAs) for best results.')
+                                enhance_inpaint_strength = gr.Slider(label='Inpaint Denoising Strength',
+                                                                     minimum=0.0, maximum=1.0, step=0.001,
+                                                                     value=1.0,
+                                                                     info='Same as the denoising strength in A1111 inpaint. '
+                                                                          'Only used in inpaint, not used in outpaint. '
+                                                                          '(Outpaint always use 1.0)')
+                                enhance_inpaint_respective_field = gr.Slider(label='Inpaint Respective Field',
+                                                                             minimum=0.0, maximum=1.0, step=0.001,
+                                                                             value=0.618,
+                                                                             info='The area to inpaint. '
+                                                                                  'Value 0 is same as "Only Masked" in A1111. '
+                                                                                  'Value 1 is same as "Whole Image" in A1111. '
+                                                                                  'Only used in inpaint, not used in outpaint. '
+                                                                                  '(Outpaint always use 1.0)')
+                                enhance_inpaint_erode_or_dilate = gr.Slider(label='Mask Erode or Dilate',
+                                                                            minimum=-64, maximum=64, step=1, value=0,
+                                                                            info='Positive value will make white area in the mask larger, '
+                                                                                 'negative value will make white area smaller. '
+                                                                                 '(default is 0, always processed before any mask invert)')
+                                enhance_mask_invert = gr.Checkbox(label='Invert Mask', value=False)
+
+                            gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/3281" target="_blank">\U0001F4D4 Documentation</a>')
+
+                        enhance_ctrls += [
+                            enhance_enabled,
+                            enhance_mask_dino_prompt_text,
+                            enhance_prompt,
+                            enhance_negative_prompt,
+                            enhance_mask_model,
+                            enhance_mask_cloth_category,
+                            enhance_mask_sam_model,
+                            enhance_mask_text_threshold,
+                            enhance_mask_box_threshold,
+                            enhance_mask_sam_max_detections,
+                            enhance_inpaint_disable_initial_latent,
+                            enhance_inpaint_engine,
+                            enhance_inpaint_strength,
+                            enhance_inpaint_respective_field,
+                            enhance_inpaint_erode_or_dilate,
+                            enhance_mask_invert
+                        ]
+
+                        enhance_inpaint_mode_ctrls += [enhance_inpaint_mode]
+                        enhance_inpaint_engine_ctrls += [enhance_inpaint_engine]
+
+                        enhance_inpaint_update_ctrls += [[
+                            enhance_inpaint_mode, enhance_inpaint_disable_initial_latent, enhance_inpaint_engine,
+                            enhance_inpaint_strength, enhance_inpaint_respective_field
+                        ]]
+
+                        enhance_inpaint_mode.change(inpaint_mode_change, inputs=[enhance_inpaint_mode, inpaint_engine_state], outputs=[
+                            inpaint_additional_prompt, outpaint_selections, example_inpaint_prompts,
+                            enhance_inpaint_disable_initial_latent, enhance_inpaint_engine,
+                            enhance_inpaint_strength, enhance_inpaint_respective_field
+                        ], show_progress=False, queue=False)
+
+                        enhance_mask_model.change(
+                            lambda x: [gr.update(visible=x == 'u2net_cloth_seg')] +
+                                      [gr.update(visible=x == 'sam')] * 2 +
+                                      [gr.Dataset.update(visible=x == 'sam',
+                                                         samples=modules.config.example_enhance_detection_prompts)],
+                            inputs=enhance_mask_model,
+                            outputs=[enhance_mask_cloth_category, enhance_mask_dino_prompt_text, sam_options,
+                                     example_enhance_mask_dino_prompt_text],
+                            queue=False, show_progress=False)
+
            switch_js = "(x) => {if(x){viewer_to_bottom(100);viewer_to_bottom(500);}else{viewer_to_top();} return x;}"
            down_js = "() => {viewer_to_bottom();}"

@@ -255,25 +528,39 @@ with shared.gradio_root:
            inpaint_tab.select(lambda: 'inpaint', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
            ip_tab.select(lambda: 'ip', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
            desc_tab.select(lambda: 'desc', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
+            enhance_tab.select(lambda: 'enhance', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
+            metadata_tab.select(lambda: 'metadata', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
+            enhance_checkbox.change(lambda x: gr.update(visible=x), inputs=enhance_checkbox,
+                                        outputs=enhance_input_panel, queue=False, show_progress=False, _js=switch_js)

        with gr.Column(scale=1, visible=modules.config.default_advanced_checkbox) as advanced_column:
-            with gr.Tab(label='Setting'):
+            with gr.Tab(label='Settings'):
                if not args_manager.args.disable_preset_selection:
-                    preset_selection = gr.Radio(label='Preset',
-                                                choices=modules.config.available_presets,
-                                                value=args_manager.args.preset if args_manager.args.preset else "initial",
-                                                interactive=True)
+                    preset_selection = gr.Dropdown(label='Preset',
+                                                   choices=modules.config.available_presets,
+                                                   value=args_manager.args.preset if args_manager.args.preset else "initial",
+                                                   interactive=True)
+
                performance_selection = gr.Radio(label='Performance',
-                                                 choices=flags.Performance.list(),
-                                                 value=modules.config.default_performance)
-                aspect_ratios_selection = gr.Radio(label='Aspect Ratios', choices=modules.config.available_aspect_ratios,
-                                                   value=modules.config.default_aspect_ratio, info='width × height',
-                                                   elem_classes='aspect_ratios')
+                                                 choices=flags.Performance.values(),
+                                                 value=modules.config.default_performance,
+                                                 elem_classes=['performance_selection'])
+
+                with gr.Accordion(label='Aspect Ratios', open=False, elem_id='aspect_ratios_accordion') as aspect_ratios_accordion:
+                    aspect_ratios_selection = gr.Radio(label='Aspect Ratios', show_label=False,
+                                                       choices=modules.config.available_aspect_ratios_labels,
+                                                       value=modules.config.default_aspect_ratio,
+                                                       info='width × height',
+                                                       elem_classes='aspect_ratios')
+
+                    aspect_ratios_selection.change(lambda x: None, inputs=aspect_ratios_selection, queue=False, show_progress=False, _js='(x)=>{refresh_aspect_ratios_label(x);}')
+                    shared.gradio_root.load(lambda x: None, inputs=aspect_ratios_selection, queue=False, show_progress=False, _js='(x)=>{refresh_aspect_ratios_label(x);}')
+
                image_number = gr.Slider(label='Image Number', minimum=1, maximum=modules.config.default_max_image_number, step=1, value=modules.config.default_image_number)

                output_format = gr.Radio(label='Output Format',
-                                            choices=flags.OutputFormat.list(),
-                                            value=modules.config.default_output_format)
+                                         choices=flags.OutputFormat.list(),
+                                         value=modules.config.default_output_format)

                negative_prompt = gr.Textbox(label='Negative Prompt', show_label=True, placeholder="Type prompt here.",
                                             info='Describing what you do not want to see.', lines=2,
@@ -303,13 +590,13 @@ with shared.gradio_root:
                def update_history_link():
                    if args_manager.args.disable_image_log:
                        return gr.update(value='')
-                    
+
                    return gr.update(value=f'<a href="file={get_current_html_path(output_format)}" target="_blank">\U0001F4DA History Log</a>')

                history_link = gr.HTML()
                shared.gradio_root.load(update_history_link, outputs=history_link, queue=False, show_progress=False)

-            with gr.Tab(label='Style', elem_classes=['style_selections_tab']):
+            with gr.Tab(label='Styles', elem_classes=['style_selections_tab']):
                style_sorter.try_load_sorted_styles(
                    style_names=legal_style_names,
                    default_selected=modules.config.default_styles)
@@ -342,7 +629,7 @@ with shared.gradio_root:
                                                       show_progress=False).then(
                    lambda: None, _js='()=>{refresh_style_localization();}')

-            with gr.Tab(label='Model'):
+            with gr.Tab(label='Models'):
                with gr.Group():
                    with gr.Row():
                        base_model = gr.Dropdown(label='Base Model (SDXL only)', choices=modules.config.model_filenames, value=modules.config.default_base_model_name, show_label=True)
@@ -383,7 +670,7 @@ with shared.gradio_root:
                sharpness = gr.Slider(label='Image Sharpness', minimum=0.0, maximum=30.0, step=0.001,
                                      value=modules.config.default_sample_sharpness,
                                      info='Higher value means image and texture are sharper.')
-                gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/117" target="_blank">\U0001F4D4 Document</a>')
+                gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/117" target="_blank">\U0001F4D4 Documentation</a>')
                dev_mode = gr.Checkbox(label='Developer Debug Mode', value=False, container=False)

                with gr.Column(visible=False) as dev_tools:
@@ -403,6 +690,9 @@ with shared.gradio_root:
                                                 value=modules.config.default_cfg_tsnr,
                                                 info='Enabling Fooocus\'s implementation of CFG mimicking for TSNR '
                                                      '(effective when real CFG > mimicked CFG).')
+                        clip_skip = gr.Slider(label='CLIP Skip', minimum=1, maximum=flags.clip_skip_max, step=1,
+                                                 value=modules.config.default_clip_skip,
+                                                 info='Bypass CLIP layers to avoid overfitting (use 1 to not skip any layers, 2 is recommended).')
                        sampler_name = gr.Dropdown(label='Sampler', choices=flags.sampler_list,
                                                   value=modules.config.default_sampler)
                        scheduler_name = gr.Dropdown(label='Scheduler', choices=flags.scheduler_list,
@@ -434,22 +724,23 @@ with shared.gradio_root:
                                                            minimum=-1, maximum=1.0, step=0.001, value=-1,
                                                            info='Set as negative number to disable. For developer debugging.')
                        overwrite_upscale_strength = gr.Slider(label='Forced Overwrite of Denoising Strength of "Upscale"',
-                                                               minimum=-1, maximum=1.0, step=0.001, value=-1,
+                                                               minimum=-1, maximum=1.0, step=0.001,
+                                                               value=modules.config.default_overwrite_upscale,
                                                               info='Set as negative number to disable. For developer debugging.')
+
                        disable_preview = gr.Checkbox(label='Disable Preview', value=modules.config.default_black_out_nsfw,
                                                      interactive=not modules.config.default_black_out_nsfw,
                                                      info='Disable preview during generation.')
-                        disable_intermediate_results = gr.Checkbox(label='Disable Intermediate Results', 
-                                                      value=modules.config.default_performance == flags.Performance.EXTREME_SPEED.value,
-                                                      interactive=modules.config.default_performance != flags.Performance.EXTREME_SPEED.value,
+                        disable_intermediate_results = gr.Checkbox(label='Disable Intermediate Results',
+                                                      value=flags.Performance.has_restricted_features(modules.config.default_performance),
                                                      info='Disable intermediate results during generation, only show final gallery.')
+
                        disable_seed_increment = gr.Checkbox(label='Disable seed increment',
                                                             info='Disable automatic seed increment when image number is > 1.',
                                                             value=False)
                        read_wildcards_in_order = gr.Checkbox(label="Read wildcards in order", value=False)

-                        black_out_nsfw = gr.Checkbox(label='Black Out NSFW',
-                                                     value=modules.config.default_black_out_nsfw,
+                        black_out_nsfw = gr.Checkbox(label='Black Out NSFW', value=modules.config.default_black_out_nsfw,
                                                     interactive=not modules.config.default_black_out_nsfw,
                                                     info='Use black image if NSFW is detected.')

@@ -464,7 +755,7 @@ with shared.gradio_root:
                                                       info='Image Prompt parameters are not included. Use png and a1111 for compatibility with Civitai.',
                                                       visible=modules.config.default_save_metadata_to_images)

-                            save_metadata_to_images.change(lambda x: gr.update(visible=x), inputs=[save_metadata_to_images], outputs=[metadata_scheme], 
+                            save_metadata_to_images.change(lambda x: gr.update(visible=x), inputs=[save_metadata_to_images], outputs=[metadata_scheme],
                                                           queue=False, show_progress=False)

                    with gr.Tab(label='Control'):
@@ -490,11 +781,15 @@ with shared.gradio_root:

                    with gr.Tab(label='Inpaint'):
                        debugging_inpaint_preprocessor = gr.Checkbox(label='Debug Inpaint Preprocessing', value=False)
+                        debugging_enhance_masks_checkbox = gr.Checkbox(label='Debug Enhance Masks', value=False,
+                                                                       info='Show enhance masks in preview and final results')
+                        debugging_dino = gr.Checkbox(label='Debug GroundingDINO', value=False,
+                                                     info='Use GroundingDINO boxes instead of more detailed SAM masks')
                        inpaint_disable_initial_latent = gr.Checkbox(label='Disable initial latent in inpaint', value=False)
                        inpaint_engine = gr.Dropdown(label='Inpaint Engine',
                                                     value=modules.config.default_inpaint_engine_version,
                                                     choices=flags.inpaint_engine_versions,
-                                                     info='Version of Fooocus inpaint model')
+                                                     info='Version of Fooocus inpaint model. If set, use performance Quality or Speed (no performance LoRAs) for best results.')
                        inpaint_strength = gr.Slider(label='Inpaint Denoising Strength',
                                                     minimum=0.0, maximum=1.0, step=0.001, value=1.0,
                                                     info='Same as the denoising strength in A1111 inpaint. '
@@ -510,18 +805,28 @@ with shared.gradio_root:
                        inpaint_erode_or_dilate = gr.Slider(label='Mask Erode or Dilate',
                                                            minimum=-64, maximum=64, step=1, value=0,
                                                            info='Positive value will make white area in the mask larger, '
-                                                                 'negative value will make white area smaller.'
-                                                                 '(default is 0, always process before any mask invert)')
-                        inpaint_mask_upload_checkbox = gr.Checkbox(label='Enable Mask Upload', value=False)
-                        invert_mask_checkbox = gr.Checkbox(label='Invert Mask', value=False)
+                                                                 'negative value will make white area smaller. '
+                                                                 '(default is 0, always processed before any mask invert)')
+                        dino_erode_or_dilate = gr.Slider(label='GroundingDINO Box Erode or Dilate',
+                                                         minimum=-64, maximum=64, step=1, value=0,
+                                                         info='Positive value will make white area in the mask larger, '
+                                                              'negative value will make white area smaller. '
+                                                              '(default is 0, processed before SAM)')
+
+                        inpaint_mask_color = gr.ColorPicker(label='Inpaint brush color', value='#FFFFFF', elem_id='inpaint_brush_color')

                        inpaint_ctrls = [debugging_inpaint_preprocessor, inpaint_disable_initial_latent, inpaint_engine,
                                         inpaint_strength, inpaint_respective_field,
-                                         inpaint_mask_upload_checkbox, invert_mask_checkbox, inpaint_erode_or_dilate]
+                                         inpaint_advanced_masking_checkbox, invert_mask_checkbox, inpaint_erode_or_dilate]

-                        inpaint_mask_upload_checkbox.change(lambda x: gr.update(visible=x),
-                                                           inputs=inpaint_mask_upload_checkbox,
-                                                           outputs=inpaint_mask_image, queue=False, show_progress=False)
+                        inpaint_advanced_masking_checkbox.change(lambda x: [gr.update(visible=x)] * 2,
+                                                                 inputs=inpaint_advanced_masking_checkbox,
+                                                                 outputs=[inpaint_mask_image, inpaint_mask_generation_col],
+                                                                 queue=False, show_progress=False)
+
+                        inpaint_mask_color.change(lambda x: gr.update(brush_color=x), inputs=inpaint_mask_color,
+                                                  outputs=inpaint_input_image,
+                                                  queue=False, show_progress=False)

                    with gr.Tab(label='FreeU'):
                        freeu_enabled = gr.Checkbox(label='Enabled', value=False)
@@ -541,7 +846,7 @@ with shared.gradio_root:
                    modules.config.update_files()
                    results = [gr.update(choices=modules.config.model_filenames)]
                    results += [gr.update(choices=['None'] + modules.config.model_filenames)]
-                    results += [gr.update(choices=['None'] + modules.config.vae_filenames)]
+                    results += [gr.update(choices=[flags.default_vae] + modules.config.vae_filenames)]
                    if not args_manager.args.disable_preset_selection:
                        results += [gr.update(choices=modules.config.available_presets)]
                    for i in range(modules.config.default_max_lora_number):
@@ -555,17 +860,37 @@ with shared.gradio_root:
                refresh_files.click(refresh_files_clicked, [], refresh_files_output + lora_ctrls,
                                    queue=False, show_progress=False)

+            with gr.Tab(label='Audio'):
+                play_notification = gr.Checkbox(label='Play notification after rendering', value=False)
+                notification_file = 'notification.mp3'
+                if os.path.exists(notification_file):
+                    notification = gr.State(value=notification_file)
+                    notification_input = gr.Audio(label='Notification', interactive=True, elem_id='audio_notification', visible=False, show_edit_button=False)
+
+                    def play_notification_checked(r, notification):
+                        return gr.update(visible=r, value=notification if r else None)
+
+                    def notification_input_changed(notification_input, notification):
+                        if notification_input:
+                            notification = notification_input
+                        return notification
+
+                    play_notification.change(fn=play_notification_checked, inputs=[play_notification, notification], outputs=[notification_input], queue=False)
+                    notification_input.change(fn=notification_input_changed, inputs=[notification_input, notification], outputs=[notification], queue=False)
+
        state_is_generating = gr.State(False)

        load_data_outputs = [advanced_checkbox, image_number, prompt, negative_prompt, style_selections,
                             performance_selection, overwrite_step, overwrite_switch, aspect_ratios_selection,
                             overwrite_width, overwrite_height, guidance_scale, sharpness, adm_scaler_positive,
-                             adm_scaler_negative, adm_scaler_end, refiner_swap_method, adaptive_cfg, base_model,
-                             refiner_model, refiner_switch, sampler_name, scheduler_name, vae_name, seed_random,
-                             image_seed, generate_button, load_parameter_button] + freeu_ctrls + lora_ctrls
+                             adm_scaler_negative, adm_scaler_end, refiner_swap_method, adaptive_cfg, clip_skip,
+                             base_model, refiner_model, refiner_switch, sampler_name, scheduler_name, vae_name,
+                             seed_random, image_seed, inpaint_engine, inpaint_engine_state,
+                             inpaint_mode] + enhance_inpaint_mode_ctrls + [generate_button,
+                             load_parameter_button] + freeu_ctrls + lora_ctrls

        if not args_manager.args.disable_preset_selection:
-            def preset_selection_change(preset, is_generating):
+            def preset_selection_change(preset, is_generating, inpaint_mode):
                preset_content = modules.config.try_get_preset_content(preset) if preset != 'initial' else {}
                preset_prepared = modules.meta_parser.parse_meta_from_preset(preset_content)

@@ -574,67 +899,73 @@ with shared.gradio_root:
                checkpoint_downloads = preset_prepared.get('checkpoint_downloads', {})
                embeddings_downloads = preset_prepared.get('embeddings_downloads', {})
                lora_downloads = preset_prepared.get('lora_downloads', {})
+                vae_downloads = preset_prepared.get('vae_downloads', {})

-                preset_prepared['base_model'], preset_prepared['lora_downloads'] = launch.download_models(
-                    default_model, previous_default_models, checkpoint_downloads, embeddings_downloads, lora_downloads)
+                preset_prepared['base_model'], preset_prepared['checkpoint_downloads'] = launch.download_models(
+                    default_model, previous_default_models, checkpoint_downloads, embeddings_downloads, lora_downloads,
+                    vae_downloads)

                if 'prompt' in preset_prepared and preset_prepared.get('prompt') == '':
                    del preset_prepared['prompt']

-                return modules.meta_parser.load_parameter_button_click(json.dumps(preset_prepared), is_generating)
+                return modules.meta_parser.load_parameter_button_click(json.dumps(preset_prepared), is_generating, inpaint_mode)

-            preset_selection.change(preset_selection_change, inputs=[preset_selection, state_is_generating], outputs=load_data_outputs, queue=False, show_progress=True) \
+
+            def inpaint_engine_state_change(inpaint_engine_version, *args):
+                if inpaint_engine_version == 'empty':
+                    inpaint_engine_version = modules.config.default_inpaint_engine_version
+
+                result = []
+                for inpaint_mode in args:
+                    if inpaint_mode != modules.flags.inpaint_option_detail:
+                        result.append(gr.update(value=inpaint_engine_version))
+                    else:
+                        result.append(gr.update())
+
+                return result
+
+            preset_selection.change(preset_selection_change, inputs=[preset_selection, state_is_generating, inpaint_mode], outputs=load_data_outputs, queue=False, show_progress=True) \
                .then(fn=style_sorter.sort_styles, inputs=style_selections, outputs=style_selections, queue=False, show_progress=False) \
+                .then(lambda: None, _js='()=>{refresh_style_localization();}') \
+                .then(inpaint_engine_state_change, inputs=[inpaint_engine_state] + enhance_inpaint_mode_ctrls, outputs=enhance_inpaint_engine_ctrls, queue=False, show_progress=False)

        performance_selection.change(lambda x: [gr.update(interactive=not flags.Performance.has_restricted_features(x))] * 11 +
                                               [gr.update(visible=not flags.Performance.has_restricted_features(x))] * 1 +
-                                               [gr.update(interactive=not flags.Performance.has_restricted_features(x), value=flags.Performance.has_restricted_features(x))] * 1,
+                                               [gr.update(value=flags.Performance.has_restricted_features(x))] * 1,
                                     inputs=performance_selection,
                                     outputs=[
                                         guidance_scale, sharpness, adm_scaler_end, adm_scaler_positive,
                                         adm_scaler_negative, refiner_switch, refiner_model, sampler_name,
                                         scheduler_name, adaptive_cfg, refiner_swap_method, negative_prompt, disable_intermediate_results
                                     ], queue=False, show_progress=False)
-        
+
        output_format.input(lambda x: gr.update(output_format=x), inputs=output_format)
-        
+
        advanced_checkbox.change(lambda x: gr.update(visible=x), advanced_checkbox, advanced_column,
                                 queue=False, show_progress=False) \
            .then(fn=lambda: None, _js='refresh_grid_delayed', queue=False, show_progress=False)

-        def inpaint_mode_change(mode):
-            assert mode in modules.flags.inpaint_options
-
-            # inpaint_additional_prompt, outpaint_selections, example_inpaint_prompts,
-            # inpaint_disable_initial_latent, inpaint_engine,
-            # inpaint_strength, inpaint_respective_field
-
-            if mode == modules.flags.inpaint_option_detail:
-                return [
-                    gr.update(visible=True), gr.update(visible=False, value=[]),
-                    gr.Dataset.update(visible=True, samples=modules.config.example_inpaint_prompts),
-                    False, 'None', 0.5, 0.0
-                ]
-
-            if mode == modules.flags.inpaint_option_modify:
-                return [
-                    gr.update(visible=True), gr.update(visible=False, value=[]),
-                    gr.Dataset.update(visible=False, samples=modules.config.example_inpaint_prompts),
-                    True, modules.config.default_inpaint_engine_version, 1.0, 0.0
-                ]
-
-            return [
-                gr.update(visible=False, value=''), gr.update(visible=True),
-                gr.Dataset.update(visible=False, samples=modules.config.example_inpaint_prompts),
-                False, modules.config.default_inpaint_engine_version, 1.0, 0.618
-            ]
-
-        inpaint_mode.input(inpaint_mode_change, inputs=inpaint_mode, outputs=[
+        inpaint_mode.change(inpaint_mode_change, inputs=[inpaint_mode, inpaint_engine_state], outputs=[
            inpaint_additional_prompt, outpaint_selections, example_inpaint_prompts,
            inpaint_disable_initial_latent, inpaint_engine,
            inpaint_strength, inpaint_respective_field
        ], show_progress=False, queue=False)

+        # load configured default_inpaint_method
+        default_inpaint_ctrls = [inpaint_mode, inpaint_disable_initial_latent, inpaint_engine, inpaint_strength, inpaint_respective_field]
+        for mode, disable_initial_latent, engine, strength, respective_field in [default_inpaint_ctrls] + enhance_inpaint_update_ctrls:
+            shared.gradio_root.load(inpaint_mode_change, inputs=[mode, inpaint_engine_state], outputs=[
+                inpaint_additional_prompt, outpaint_selections, example_inpaint_prompts, disable_initial_latent,
+                engine, strength, respective_field
+            ], show_progress=False, queue=False)
+
+        generate_mask_button.click(fn=generate_mask,
+                                   inputs=[inpaint_input_image, inpaint_mask_model, inpaint_mask_cloth_category,
+                                           inpaint_mask_dino_prompt_text, inpaint_mask_sam_model,
+                                           inpaint_mask_box_threshold, inpaint_mask_text_threshold,
+                                           inpaint_mask_sam_max_detections, dino_erode_or_dilate, debugging_dino],
+                                   outputs=inpaint_mask_image, show_progress=True, queue=True)
+
        ctrls = [currentTask, generate_image_grid]
        ctrls += [
            prompt, negative_prompt, style_selections,
@@ -647,7 +978,7 @@ with shared.gradio_root:
        ctrls += [uov_method, uov_input_image]
        ctrls += [outpaint_selections, inpaint_input_image, inpaint_additional_prompt, inpaint_mask_image]
        ctrls += [disable_preview, disable_intermediate_results, disable_seed_increment, black_out_nsfw]
-        ctrls += [adm_scaler_positive, adm_scaler_negative, adm_scaler_end, adaptive_cfg]
+        ctrls += [adm_scaler_positive, adm_scaler_negative, adm_scaler_end, adaptive_cfg, clip_skip]
        ctrls += [sampler_name, scheduler_name, vae_name]
        ctrls += [overwrite_step, overwrite_switch, overwrite_width, overwrite_height, overwrite_vary_strength]
        ctrls += [overwrite_upscale_strength, mixing_image_prompt_and_vary_upscale, mixing_image_prompt_and_inpaint]
@@ -660,6 +991,10 @@ with shared.gradio_root:
            ctrls += [save_metadata_to_images, metadata_scheme]

        ctrls += ip_ctrls
+        ctrls += [debugging_dino, dino_erode_or_dilate, debugging_enhance_masks_checkbox,
+                  enhance_input_image, enhance_checkbox, enhance_uov_method, enhance_uov_processing_order,
+                  enhance_uov_prompt_type]
+        ctrls += enhance_ctrls

        def parse_meta(raw_prompt_txt, is_generating):
            loaded_json = None
@@ -676,7 +1011,7 @@ with shared.gradio_root:

        prompt.input(parse_meta, inputs=[prompt, state_is_generating], outputs=[prompt, generate_button, load_parameter_button], queue=False, show_progress=False)

-        load_parameter_button.click(modules.meta_parser.load_parameter_button_click, inputs=[prompt, state_is_generating], outputs=load_data_outputs, queue=False, show_progress=False)
+        load_parameter_button.click(modules.meta_parser.load_parameter_button_click, inputs=[prompt, state_is_generating, inpaint_mode], outputs=load_data_outputs, queue=False, show_progress=False)

        def trigger_metadata_import(filepath, state_is_generating):
            parameters, metadata_scheme = modules.meta_parser.read_info_from_image(filepath)
@@ -685,9 +1020,9 @@ with shared.gradio_root:
                parsed_parameters = {}
            else:
                metadata_parser = modules.meta_parser.get_metadata_parser(metadata_scheme)
-                parsed_parameters = metadata_parser.parse_json(parameters)
+                parsed_parameters = metadata_parser.to_json(parameters)

-            return modules.meta_parser.load_parameter_button_click(parsed_parameters, state_is_generating)
+            return modules.meta_parser.load_parameter_button_click(parsed_parameters, state_is_generating, inpaint_mode)

        metadata_import_button.click(trigger_metadata_import, inputs=[metadata_input_image, state_is_generating], outputs=load_data_outputs, queue=False, show_progress=True) \
            .then(style_sorter.sort_styles, inputs=style_selections, outputs=style_selections, queue=False, show_progress=False)
@@ -710,11 +1045,6 @@ with shared.gradio_root:
                                    progress_html, progress_window, progress_gallery, gallery],
                           queue=False)

-        for notification_file in ['notification.ogg', 'notification.mp3']:
-            if os.path.exists(notification_file):
-                gr.Audio(interactive=False, value=notification_file, elem_id='audio_notification', visible=False)
-                break
-
        def trigger_describe(mode, img):
            if mode == flags.desc_type_photo:
                from extras.interrogate import default_interrogator as default_interrogator_photo
@@ -727,15 +1057,18 @@ with shared.gradio_root:
        desc_btn.click(trigger_describe, inputs=[desc_method, desc_input_image],
                       outputs=[prompt, style_selections], show_progress=True, queue=True)

-        if args_manager.args.enable_describe_uov_image:
-            def trigger_uov_describe(mode, img, prompt):
+        if args_manager.args.enable_auto_describe_image:
+            def trigger_auto_describe(mode, img, prompt):
                # keep prompt if not empty
                if prompt == '':
                    return trigger_describe(mode, img)
                return gr.update(), gr.update()

-            uov_input_image.upload(trigger_uov_describe, inputs=[desc_method, uov_input_image, prompt],
-                           outputs=[prompt, style_selections], show_progress=True, queue=True)
+            uov_input_image.upload(trigger_auto_describe, inputs=[desc_method, uov_input_image, prompt],
+                                   outputs=[prompt, style_selections], show_progress=True, queue=True)
+
+            enhance_input_image.upload(lambda: gr.update(value=True), outputs=enhance_checkbox, queue=False, show_progress=False) \
+                .then(trigger_auto_describe, inputs=[desc_method, enhance_input_image, prompt], outputs=[prompt, style_selections], show_progress=True, queue=True)

 def dump_default_english_config():
    from modules.localization import dump_english_config
@@ -0,0 +1,8 @@
+*.txt
+!animal.txt
+!artist.txt
+!color.txt
+!color_flower.txt
+!extended-color.txt
+!flower.txt
+!nationality.txt
Author	SHA1	Message	Date
Manuel Schmid	e0d3325894	i18n: rename document to documentation	2024-07-14 21:40:10 +02:00
Manuel Schmid	5a1003a726	docs: update link for enhance documentation	2024-07-14 21:31:59 +02:00
Manuel Schmid	5e8110e430	i18n: adjust translations to use proper english for plural tab titles	2024-07-14 21:07:12 +02:00
Manuel Schmid	ee02643020	feat: revert adding detailed steps for each performance	2024-07-14 21:06:59 +02:00
Manuel Schmid	e1f4b65fc9	feat: revert adding translate feature	2024-07-14 20:35:39 +02:00
Manuel Schmid	f2a21900c6	Sync branch 'mashb1t_main' with develop_upstream	2024-07-14 20:28:38 +02:00
dependabot[bot]anddependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	5a71495822	build(deps): bump docker/build-push-action from 5 to 6 (#3223 ) Bumps [docker/build-push-action](https://github.com/docker/build-push-action) from 5 to 6. - [Release notes](https://github.com/docker/build-push-action/releases) - [Commits](https://github.com/docker/build-push-action/compare/v5...v6) --- updated-dependencies: - dependency-name: docker/build-push-action dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2024-07-01 20:03:25 +02:00
licyk	34f67c01a8	feat: add restart sampler (#3219 )	2024-07-01 14:24:21 +02:00
Manuel Schmid	9178aa8ebb	feat: add vae to possible preset keys (#3177 ) set default_vae in any preset to use it	2024-06-21 20:24:11 +02:00
Manuel Schmid	7c1a101c0f	hotfix: add missing method in performance enum (#3154 )	2024-06-16 18:53:20 +02:00
Manuel Schmid	9d41c9521b	fix: add workaround for same value in Steps IntEnum (#3153 )	2024-06-16 18:44:16 +02:00
Manuel Schmid	3e453501f7	fix: correctly identify and remove performance LoRA (#3150 )	2024-06-16 16:52:58 +02:00
Manuel Schmid	55ef7608ea	feat: adjust playground_v2.5 preset (#3136 ) * feat: reduce cfg of playground_v2.5 preset from 3 to 2 to prevent oversaturation * feat: adjust default styles for playground_v2.5	2024-06-11 22:50:09 +02:00
Manuel Schmid	ba77e7f706	release: bump version to 2.4.3, update changelog (#3109 )	2024-06-06 19:34:44 +02:00
Manuel Schmid	5abae220c5	feat: parse env var strings to expected config value types (#3107 ) * fix: add try_parse_bool for env var strings to enable config overrides of boolean values * fix: fallback to given value if not parseable * feat: extend eval to all valid types * fix: remove return type * fix: prevent strange type conversions by providing expected type * feat: add tests	2024-06-06 19:29:08 +02:00
Manuel Schmid	04d764820e	fix: correctly set alphas_cumprod (#3106 )	2024-06-06 13:42:26 +02:00
Manuel Schmid	350fdd9021	Merge pull request #3095 from lllyasviel/develop release v2.4.2	2024-06-05 21:50:42 +02:00
Manuel Schmid	85a8deecee	release: bump version to 2.4.2, update changelog	2024-06-05 21:30:43 +02:00
Manuel Schmid	b58bc7774e	fix: correct sampling when gamma is 0 (#3093 )	2024-06-04 21:03:37 +02:00
Manuel Schmid	2d55a5f257	feat: add support for playground v2.5 (#3073 ) * feat: add support for playground v2.5 * feat: add preset for playground v2.5 * feat: change URL to mashb1t * feat: optimize playground v2.5 preset	2024-06-04 20:15:49 +02:00
Manuel Schmid	cb24c686b0	Merge branch 'main_upstream' into develop_upstream	2024-06-04 20:11:42 +02:00
Manuel Schmid	ab01104d42	feat: make textboxes (incl. positive prompt) resizable (#3074 ) * feat: make textboxes (incl. positive prompt) resizable again * wip: auto-resize positive prompt on new line dirty approach as container is hidden and 1px padding is applied for border shadow to actually work * feat: set row height to 84, exactly matching 3 lines for positive prompt eliminate need for JS to resize positive prompt onUiLoaded	2024-06-02 13:40:42 +02:00
Manuel Schmid	3d43976e8e	feat: update cmd args (#3075 )	2024-06-02 02:13:16 +02:00
Manuel Schmid	07c6c89edf	fix: chown files directly at copy (#3066 )	2024-05-31 22:41:36 +02:00
Manuel Schmid	7899261755	fix: turbo scheduler loading issue (#3065 ) * fix: correctly load ModelPatcher * feat: do not load model at all, not needed	2024-05-31 22:24:19 +02:00
Manuel Schmid	64c29a8c43	feat: rework intermediate image display for restricted performances (#3050 ) disable intermediate results for all performacnes with restricted features make disable_intermediate_results interactive again even if performance has restricted features users who want to disable this option should be able to do so, even if performance will be impacted	2024-05-30 16:17:36 +02:00
Manuel Schmid	4e658bb63a	feat: optimize performance lora filtering in metadata (#3048 ) * feat: add remove_performance_lora method * feat: use class PerformanceLoRA instead of strings in config * refactor: cleanup flags, use __member__ to check if enums contains key * feat: only filter lora of selected performance instead of all performance LoRAs * fix: disable intermediate results for all restricted performances too fast for Gradio, which becomes a bottleneck * refactor: rename parse_json to to_json, rename parse_string to to_string * feat: use speed steps as default instead of hardcoded 30 * feat: add method to_steps to Performance * refactor: remove method ordinal_suffix, not needed anymore * feat: only filter lora of selected performance instead of all performance LoRAs both metadata and history log * feat: do not filter LoRAs in metadata parser but rather in metadata load action	2024-05-30 16:14:28 +02:00
Manuel Schmid	3ef663c5b7	fix: do not set textContent on undefined when no translation was given #2 (#3046 ) * fix: do not set textContent on undefined when no translation was given	2024-05-29 20:33:15 +02:00
Manuel Schmid	bf70815a66	fix: use default vae name instead of None on file refresh (#3045 )	2024-05-29 19:49:07 +02:00
Manuel Schmid	725bf05c31	release: bump version to 2.4.1, update changelog (#3027 )	2024-05-28 01:10:45 +02:00
Manuel Schmid	4a070a9d61	feat: build docker image tagged "edge" on push to main branch (#3026 ) * feat: build docker image on push to main branch * feat: add tag "edge" for main when building the docker image * feat: update name of build container workflow	2024-05-28 00:49:47 +02:00
Manuel Schmid	0e621ae34e	fix: add type check for undefined, use fallback when no translation for aspect ratios was given (#3025 )	2024-05-28 00:09:39 +02:00
Manuel Schmid	dfff9b7dcf	fix: adjust clip skip default value from 1 to 2 (#3011 ) * Revert "Revert "feat: add clip skip handling (#2999)" (#3008)" This reverts commit `989a1ad52b`. * feat: use clip skip 2 as default	2024-05-27 00:28:22 +02:00
Manuel Schmid	989a1ad52b	Revert "feat: add clip skip handling (#2999 )" (#3008 ) This reverts commit `cc58fe5270`.	2024-05-26 22:07:44 +02:00
Manuel Schmid	de34023c79	fix: use translation for aspect ratios label (#3001 ) use javascript code instead of python handling for updates for https://github.com/lllyasviel/Fooocus/pull/2590	2024-05-26 19:23:21 +02:00
Manuel Schmid	12dc2396f6	Merge pull request #3000 from lllyasviel/develop Release 2.4.0	2024-05-26 18:18:53 +02:00
Manuel Schmid	c227cf1f56	docs: update changelog	2024-05-26 18:16:18 +02:00
Alexdnk Manuel Schmid Manuel Schmid	57d2f2a0dd	feat: make ui settings more compact (#2590 ) * Slightly more compact ui settings Changed Radio to Dropdown. * feat: change preset from option to select, add accordion for resolution * feat: change title of aspect ratios accordion on load and update * refactor: reorder image number slider, code cleanup * fix: add missing scroll down for metadata tab * fix: adjust indent --------- Co-authored-by: Manuel Schmid <dev@mash1t.de> Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>	2024-05-26 18:10:29 +02:00
Manuel Schmid	67289dd0fe	release: bump version to 2.4.0, update changelog	2024-05-26 15:13:54 +02:00
Manuel Schmid	cc58fe5270	feat: add clip skip handling (#2999 )	2024-05-26 14:18:19 +02:00
Manuel Schmid	4e5509351f	feat: remove labels from most of the image input fields (#2998 )	2024-05-26 11:47:33 +02:00
Manuel Schmid	1d1a4a3ebd	feat: add inpaint color picker (#2997 ) Workaround as tool color-sketch applies changes directly to the image canvas and not the mask canvas. Color picker is not correctly implemented in Gradio 3.41.2 => does always get displayed as separate containers and not merged with other elements	2024-05-26 11:40:15 +02:00
Alexdnk	d850bca09f	feat: read value 'CFG Mimicking from TSNR' (adaptive_cfg) from presets (#2990 )	2024-05-24 22:05:28 +02:00
Manuel Schmid	04f64ab0bc	feat: add translation for image size describe (#2992 )	2024-05-24 21:58:17 +02:00
Manuel Schmid	7b70d27032	feat: configure line ending format LF for *.sh files (#2991 )	2024-05-24 21:36:07 +02:00
xyny Manuel Schmid Manuel Schmid	4da5a68c10	feat: build and push container image for ghcr.io, update docker.md, and other related fixes (#2805 ) * chore: update cuda version in container * fix: use symlink to fix error libcuda.so: cannot open shared object file: * fix: update docker entrypoint to use entry_with_update.py * feat: add container build & push workflow * fix: container action run conditions * fix: container action versions * fix: container action versions v2 * fix: docker action registry login and metadata * docs: adjust docker documentation based on latest changes, add docs for podman and docker * chore: replace image name env var with github.event.repository.name Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com> * chore: replace image name env var with github.event.repository.name (pt2) Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com> * fix: switch to semver versioning Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com> * fix: build only on versioned tags Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com> * fix: don't update in entrypoint Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com> * fix: remove dash in "docker-compose" Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com> * feat: sync pytorch for docker with version used in prepare_environment * feat: update cuda to 12.4.1 * fix: correctly clone checked out version in builds, not always main * refactor: remove irrelevant version in docker-compose.yml --------- Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com> Co-authored-by: Manuel Schmid <dev@mash1t.de>	2024-05-23 00:19:54 +02:00
xhoxye Manuel Schmid Manuel Schmid	302bfdf855	feat: read size and ratio of an image and provide the recommended size (#2971 ) * Add the information about the size and ratio of the read image * feat: use available aspect ratios from config, move function to util, change default visibility of label * refactor: extract sdxl aspect ratios to flags, use in describe as discussed in https://github.com/lllyasviel/Fooocus/pull/2971#discussion_r1608493765 https://github.com/lllyasviel/Fooocus/pull/2971#issuecomment-2123620595 --------- Co-authored-by: Manuel Schmid <dev@mash1t.de> Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>	2024-05-22 20:47:44 +02:00
Manuel Schmid	7537612bcc	feat: only use valid inline loras, add subfolder support (#2968 )	2024-05-20 19:21:41 +02:00
Manuel Schmid	ac14d9d03c	feat: change code owner from @lllyasviel to @mashb1t (#2948 )	2024-05-20 17:33:12 +02:00
Manuel Schmid	65a8b25129	feat: inline lora optimisations (#2967 ) * feat: add performance loras to the end of the loras array * fix: resolve circular dependency for unit tests * feat: allow multiple matches for each token, optimize and extract method cleanup_prompt * fix: update unit tests * feat: ignore custom wildcards	2024-05-20 17:31:51 +02:00
Manuel Schmid	c995511705	feat: progress bar improvements (#2962 ) * feat: align progress bar vertically * feat: use fixed width for status text, remove ordinals * refactor: align progress to actions	2024-05-19 20:43:11 +02:00