gradio==5.24.0

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v5.0.0
     hooks:
       - id: check-executables-have-shebangs
       - id: check-json
@@ -13,43 +13,21 @@ repos:
         args: ["--fix=lf"]
       - id: requirements-txt-fixer
       - id: trailing-whitespace
-  - repo: https://github.com/myint/docformatter
-    rev: v1.7.5
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.2
     hooks:
-      - id: docformatter
-        args: ["--in-place"]
-  - repo: https://github.com/pycqa/isort
-    rev: 5.12.0
-    hooks:
-      - id: isort
-        args: ["--profile", "black"]
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.6.0
+    rev: v1.15.0
     hooks:
       - id: mypy
         args: ["--ignore-missing-imports"]
         additional_dependencies:
-          ["types-python-slugify", "types-requests", "types-PyYAML"]
-  - repo: https://github.com/psf/black
-    rev: 23.9.1
-    hooks:
-      - id: black
-        language_version: python3.10
-        args: ["--line-length", "119"]
-  - repo: https://github.com/kynan/nbstripout
-    rev: 0.6.1
-    hooks:
-      - id: nbstripout
-        args:
           [
-            "--extra-keys",
-            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
+            "types-python-slugify",
+            "types-pytz",
+            "types-PyYAML",
+            "types-requests",
           ]
-  - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.7.0
-    hooks:
-      - id: nbqa-black
-      - id: nbqa-pyupgrade
-        args: ["--py37-plus"]
-      - id: nbqa-isort
-        args: ["--float-to-top"]

.python-version

@@ -0,0 +1 @@
+3.10

.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+    "recommendations": [
+        "ms-python.python",
+        "charliermarsh.ruff",
+        "streetsidesoftware.code-spell-checker",
+        "tamasfe.even-better-toml"
+    ]
+}

.vscode/settings.json

@@ -1,21 +1,17 @@
 {
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
     "[python]": {
-        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.defaultFormatter": "charliermarsh.ruff",
         "editor.formatOnType": true,
         "editor.codeActionsOnSave": {
-            "source.organizeImports": true
+            "source.fixAll.ruff": "explicit",
+            "source.organizeImports": "explicit"
         }
     },
-    "black-formatter.args": [
-        "--line-length=119"
-    ],
-    "isort.args": ["--profile", "black"],
-    "flake8.args": [
-        "--max-line-length=119"
-    ],
-    "ruff.args": [
-        "--line-length=119"
-    ],
-    "editor.formatOnSave": true,
-    "files.insertFinalNewline": true
+    "[jupyter]": {
+        "files.insertFinalNewline": false
+    },
+    "notebook.output.scrolling": true,
+    "notebook.formatOnSave.enabled": true
 }

README.md

@@ -4,8 +4,7 @@ emoji: 📉
 colorFrom: indigo
 colorTo: blue
 sdk: gradio
-sdk_version: 3.49.0
-python_version: 3.10.13
+sdk_version: 5.24.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -12,12 +12,33 @@ from transformers import VitMatteForImageMatting, VitMatteImageProcessor
 DESCRIPTION = """\
 # [ViTMatte](https://github.com/hustvl/ViTMatte)
 
-This is the demo for [ViTMatte](https://github.com/hustvl/ViTMatte), an image matting application.
-You can matte any subject in a given image.
+This is a demo of [ViTMatte](https://github.com/hustvl/ViTMatte), an image matting method that uses Vision Transformers (ViT) to accurately extract the foreground from an image.
+It predicts a soft alpha matte to help separate the subject from the background — even tricky areas like hair and fur!
+
+You've got two ways to get started:
+
+### 🖼️ Option 1: Upload Image & Trimap
+- Upload your original image.
+- Upload a **trimap**: a helper image that labels regions as **foreground (white)**, **background (black)**, and **unknown (gray)**.
+- The trimap must be a **grayscale image** containing only three pixel values:
+  - `0` for **background**
+  - `128` for **unknown**
+  - `255` for **foreground**
+- The model will use this trimap to generate the alpha matte and extract the foreground.
+
+### ✏️ Option 2: Draw Your Own Trimap
+- Upload just your image.
+- Go to the **"Draw Trimap"** tab to start drawing masks.
+- Use the tools to mark:
+  - **Foreground** (e.g. the subject),
+  - **Unknown** (areas where the boundary is unclear).
+- Once you're done, click the **"Generate Trimap"** button to generate the trimap from your drawing.
+
+### ✨ Optional: Replace Background
+Want to swap the background? Just check the **"Replace Background"** option and choose a new background image.
+The app will blend your extracted subject with the new background seamlessly!
 
-If you wish to replace background of the image, simply select the checkbox and drag and drop your background image.
 
-You can draw your own foreground mask and unknown (border) mask using the canvas.
 """
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
@@ -29,22 +50,31 @@ processor = VitMatteImageProcessor.from_pretrained(MODEL_ID)
 model = VitMatteForImageMatting.from_pretrained(MODEL_ID).to(device)
 
 
-def check_image_size(image: PIL.Image.Image) -> None:
+def resize_input_image(image: PIL.Image.Image | None) -> PIL.Image.Image:
+    if image is None:
+        return None
     if max(image.size) > MAX_IMAGE_SIZE:
-        raise gr.Error(f"Image size is too large. Max image size is {MAX_IMAGE_SIZE} pixels.")
+        w, h = image.size
+        scale = MAX_IMAGE_SIZE / max(w, h)
+        new_w = int(w * scale)
+        new_h = int(h * scale)
+        gr.Info(
+            f"The uploaded image exceeded the maximum resolution limit of {MAX_IMAGE_SIZE}px. It has been resized to {new_w}x{new_h}."
+        )
+        return image.resize((new_w, new_h))
+    return image
 
 
 def binarize_mask(mask: np.ndarray) -> np.ndarray:
-    mask[mask < 128] = 0
     mask[mask > 0] = 1
     return mask
 
 
-def update_trimap(foreground_mask: dict[str, np.ndarray], unknown_mask: dict[str, np.ndarray]) -> np.ndarray:
-    foreground = foreground_mask["mask"][:, :, 0]
+def update_trimap(foreground_mask_editor: gr.ImageEditor, unknown_mask_editor: gr.ImageEditor) -> np.ndarray:
+    foreground = foreground_mask_editor["layers"][0]
     foreground = binarize_mask(foreground)
 
-    unknown = unknown_mask["mask"][:, :, 0]
+    unknown = unknown_mask_editor["layers"][0]
     unknown = binarize_mask(unknown)
 
     trimap = np.zeros_like(foreground)
@@ -65,8 +95,7 @@ def adjust_background_image(background_image: PIL.Image.Image, target_size: tupl
     top = (new_bg_h - target_h) // 2
     right = left + target_w
     bottom = top + target_h
-    background_image = background_image.crop((left, top, right, bottom))
-    return background_image
+    return background_image.crop((left, top, right, bottom))
 
 
 def replace_background(
@@ -84,8 +113,7 @@ def replace_background(
     image = np.array(image).astype(float) / 255
     background_image = np.array(background_image).astype(float) / 255
     result = image * alpha[:, :, None] + background_image * (1 - alpha[:, :, None])
-    result = (result * 255).astype(np.uint8)
-    return result
+    return (result * 255).astype(np.uint8)
 
 
 @spaces.GPU
@@ -99,7 +127,8 @@ def run(
     if image.size != trimap.size:
         raise gr.Error("Image and trimap must have the same size.")
     if max(image.size) > MAX_IMAGE_SIZE:
-        raise gr.Error(f"Image size is too large. Max image size is {MAX_IMAGE_SIZE} pixels.")
+        error_message = f"Image size is too large. Max image size is {MAX_IMAGE_SIZE} pixels."
+        raise gr.Error(error_message)
     if image.mode != "RGB":
         raise gr.Error("Image must be RGB.")
     if trimap.mode != "L":
@@ -116,56 +145,51 @@ def run(
     foreground = (foreground * 255).astype(np.uint8)
     foreground = PIL.Image.fromarray(foreground)
 
-    if apply_background_replacement:
-        res_bg_replacement = replace_background(image, alpha, background_image)
-    else:
-        res_bg_replacement = None
+    res_bg_replacement = replace_background(image, alpha, background_image) if apply_background_replacement else None
 
     return alpha, foreground, res_bg_replacement
 
 
-with gr.Blocks(css="style.css") as demo:
+with gr.Blocks(css_paths="style.css") as demo:
     gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(
-        value="Duplicate Space for private use",
-        elem_id="duplicate-button",
-        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
-    )
 
     with gr.Row():
         with gr.Column():
-            with gr.Box():
-                image = gr.Image(label="Input image", type="pil", height=500)
+            with gr.Group():
+                image = gr.Image(label="Input image", type="pil")
                 with gr.Tabs():
                     with gr.Tab(label="Trimap"):
-                        trimap = gr.Image(label="Trimap", type="pil", image_mode="L", height=500)
+                        trimap = gr.Image(label="Trimap", type="pil", image_mode="L")
                     with gr.Tab(label="Draw trimap"):
-                        load_image_button = gr.Button("Load image")
-                        foreground_mask = gr.Image(
+                        foreground_mask = gr.ImageEditor(
                             label="Foreground",
-                            tool="sketch",
                             type="numpy",
-                            brush_color="green",
-                            mask_opacity=0.7,
+                            sources=("upload",),
+                            transforms=(),
+                            image_mode="L",
                             height=500,
+                            brush=gr.Brush(default_color=("#00ff00", 0.6)),
+                            layers=gr.LayerOptions(allow_additional_layers=False, layers=["Foreground mask"]),
                         )
-                        unknown_mask = gr.Image(
+                        unknown_mask = gr.ImageEditor(
                             label="Unknown",
-                            tool="sketch",
                             type="numpy",
-                            brush_color="green",
-                            mask_opacity=0.7,
+                            sources=("upload",),
+                            transforms=(),
+                            image_mode="L",
                             height=500,
+                            brush=gr.Brush(default_color=("#00ff00", 0.6)),
+                            layers=gr.LayerOptions(allow_additional_layers=False, layers=["Unknown mask"]),
                         )
-                        set_trimap_button = gr.Button("Set trimap")
-                apply_background_replacement = gr.Checkbox(label="Apply background replacement", checked=False)
-                background_image = gr.Image(label="Background image", type="pil", height=500, visible=False)
+                        generate_trimap_button = gr.Button("Generate trimap")
+                apply_background_replacement = gr.Checkbox(label="Replace background", value=False)
+                background_image = gr.Image(label="Background image", type="pil", visible=False)
                 run_button = gr.Button("Run")
         with gr.Column():
-            with gr.Box():
-                out_alpha = gr.Image(label="Alpha", height=500)
-                out_foreground = gr.Image(label="Foreground", height=500)
-                out_background_replacement = gr.Image(label="Background replacement", height=500, visible=False)
+            with gr.Group():
+                out_alpha = gr.Image(label="Alpha")
+                out_foreground = gr.Image(label="Foreground")
+                out_background_replacement = gr.Image(label="Background replacement", visible=False)
 
     inputs = [
         image,
@@ -186,34 +210,30 @@ with gr.Blocks(css="style.css") as demo:
         inputs=inputs,
         outputs=outputs,
         fn=run,
-        cache_examples=os.getenv("CACHE_EXAMPLES") == "1",
+        cache_examples=False,
     )
 
-    image.change(
-        fn=check_image_size,
+    image.input(
+        fn=resize_input_image,
         inputs=image,
-        queue=False,
+        outputs=image,
         api_name=False,
-    )
-    load_image_button.click(
+    ).then(
         fn=lambda image: (image, image),
         inputs=image,
         outputs=[foreground_mask, unknown_mask],
-        queue=False,
         api_name=False,
     )
-    set_trimap_button.click(
+    generate_trimap_button.click(
         fn=update_trimap,
         inputs=[foreground_mask, unknown_mask],
         outputs=trimap,
-        queue=False,
         api_name=False,
     )
     apply_background_replacement.change(
         fn=lambda checked: (gr.Image(visible=checked), gr.Image(visible=checked)),
         inputs=apply_background_replacement,
         outputs=[background_image, out_background_replacement],
-        queue=False,
         api_name=False,
     )
 
@@ -221,8 +241,7 @@ with gr.Blocks(css="style.css") as demo:
         fn=run,
         inputs=inputs,
         outputs=outputs,
-        api_name="run",
     )
 
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+    demo.launch()

pyproject.toml

@@ -0,0 +1,54 @@
+[project]
+name = "vitmatte"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "gradio>=5.24.0",
+    "hf-transfer>=0.1.9",
+    "spaces>=0.34.2",
+    "torch==2.4.0",
+    "transformers>=4.51.1",
+]
+
+[tool.ruff]
+line-length = 119
+
+[tool.ruff.lint]
+select = ["ALL"]
+ignore = [
+    "COM812", # missing-trailing-comma
+    "D203",   # one-blank-line-before-class
+    "D213",   # multi-line-summary-second-line
+    "E501",   # line-too-long
+    "SIM117", # multiple-with-statements
+    #
+    "D100",    # undocumented-public-module
+    "D101",    # undocumented-public-class
+    "D102",    # undocumented-public-method
+    "D103",    # undocumented-public-function
+    "D104",    # undocumented-public-package
+    "D105",    # undocumented-magic-method
+    "D107",    # undocumented-public-init
+    "EM101",   # raw-string-in-exception
+    "FBT001",  # boolean-type-hint-positional-argument
+    "FBT002",  # boolean-default-value-positional-argument
+    "PD901",   # pandas-df-variable-name
+    "PGH003",  # blanket-type-ignore
+    "PLR0913", # too-many-arguments
+    "PLR0915", # too-many-statements
+    "TRY003",  # raise-vanilla-args
+]
+unfixable = [
+    "F401", # unused-import
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.per-file-ignores]
+"*.ipynb" = ["T201", "T203"]
+
+[tool.ruff.format]
+docstring-code-format = true

requirements.txt

@@ -1,6 +1,233 @@
-gradio==3.49.0
-Pillow==10.2.0
-spaces==0.20.0
-torch==2.0.0
-torchvision==0.15.1
-transformers==4.36.2
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+aiofiles==24.1.0
+    # via gradio
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.9.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+certifi==2025.1.31
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.1
+    # via requests
+click==8.1.8
+    # via
+    #   typer
+    #   uvicorn
+exceptiongroup==1.2.2
+    # via anyio
+fastapi==0.115.12
+    # via gradio
+ffmpy==0.5.0
+    # via gradio
+filelock==3.18.0
+    # via
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   triton
+fsspec==2025.3.2
+    # via
+    #   gradio-client
+    #   huggingface-hub
+    #   torch
+gradio==5.24.0
+    # via
+    #   vitmatte (pyproject.toml)
+    #   spaces
+gradio-client==1.8.0
+    # via gradio
+groovy==0.1.2
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-transfer==0.1.9
+    # via vitmatte (pyproject.toml)
+httpcore==1.0.7
+    # via httpx
+httpx==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   safehttpx
+    #   spaces
+huggingface-hub==0.30.2
+    # via
+    #   gradio
+    #   gradio-client
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+jinja2==3.1.6
+    # via
+    #   gradio
+    #   torch
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==3.0.2
+    # via
+    #   gradio
+    #   jinja2
+mdurl==0.1.2
+    # via markdown-it-py
+mpmath==1.3.0
+    # via sympy
+networkx==3.4.2
+    # via torch
+numpy==2.2.4
+    # via
+    #   gradio
+    #   pandas
+    #   transformers
+nvidia-cublas-cu12==12.1.3.1
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.1.105
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.1.105
+    # via torch
+nvidia-cuda-runtime-cu12==12.1.105
+    # via torch
+nvidia-cudnn-cu12==9.1.0.70
+    # via torch
+nvidia-cufft-cu12==11.0.2.54
+    # via torch
+nvidia-curand-cu12==10.3.2.106
+    # via torch
+nvidia-cusolver-cu12==11.4.5.107
+    # via torch
+nvidia-cusparse-cu12==12.1.0.106
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-nccl-cu12==2.20.5
+    # via torch
+nvidia-nvjitlink-cu12==12.8.93
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+nvidia-nvtx-cu12==12.1.105
+    # via torch
+orjson==3.10.16
+    # via gradio
+packaging==24.2
+    # via
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+pandas==2.2.3
+    # via gradio
+pillow==11.1.0
+    # via gradio
+psutil==5.9.8
+    # via spaces
+pydantic==2.11.3
+    # via
+    #   fastapi
+    #   gradio
+    #   spaces
+pydantic-core==2.33.1
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.19.1
+    # via rich
+python-dateutil==2.9.0.post0
+    # via pandas
+python-multipart==0.0.20
+    # via gradio
+pytz==2025.2
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   gradio
+    #   huggingface-hub
+    #   transformers
+regex==2024.11.6
+    # via transformers
+requests==2.32.3
+    # via
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+rich==14.0.0
+    # via typer
+ruff==0.11.4
+    # via gradio
+safehttpx==0.1.6
+    # via gradio
+safetensors==0.5.3
+    # via transformers
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via anyio
+spaces==0.34.2
+    # via vitmatte (pyproject.toml)
+starlette==0.46.1
+    # via
+    #   fastapi
+    #   gradio
+sympy==1.13.3
+    # via torch
+tokenizers==0.21.1
+    # via transformers
+tomlkit==0.13.2
+    # via gradio
+torch==2.4.0
+    # via vitmatte (pyproject.toml)
+tqdm==4.67.1
+    # via
+    #   huggingface-hub
+    #   transformers
+transformers==4.51.1
+    # via vitmatte (pyproject.toml)
+triton==3.0.0
+    # via torch
+typer==0.15.2
+    # via gradio
+typing-extensions==4.13.1
+    # via
+    #   anyio
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+    #   rich
+    #   spaces
+    #   torch
+    #   typer
+    #   typing-inspection
+    #   uvicorn
+typing-inspection==0.4.0
+    # via pydantic
+tzdata==2025.2
+    # via pandas
+urllib3==2.3.0
+    # via requests
+uvicorn==0.34.0
+    # via gradio
+websockets==15.0.1
+    # via gradio-client

style.css

@@ -1,10 +1,4 @@
 h1 {
   text-align: center;
-}
-
-#duplicate-button {
-  margin: auto;
-  color: #fff;
-  background: #1565c0;
-  border-radius: 100vh;
+  display: block;
 }