Update

.pre-commit-config.yaml

@@ -18,13 +18,15 @@ repos:
     hooks:
       - id: docformatter
         args: ["--in-place"]
-  - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.4
     hooks:
-      - id: isort
-        args: ["--profile", "black"]
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
+        args: ["--line-length", "119"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.12.0
+    rev: v1.14.0
     hooks:
       - id: mypy
         args: ["--ignore-missing-imports"]
@@ -35,18 +37,8 @@ repos:
             "types-PyYAML",
             "types-pytz",
           ]
-  - repo: https://github.com/psf/black
-    rev: 24.10.0
-    hooks:
-      - id: black
-        language_version: python3.10
-        args: ["--line-length", "119"]
-  - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: v0.7.0
-    hooks:
-      - id: ruff
   - repo: https://github.com/kynan/nbstripout
-    rev: 0.7.1
+    rev: 0.8.1
     hooks:
       - id: nbstripout
         args:
@@ -55,7 +47,7 @@ repos:
             "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
           ]
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.7
+    rev: 1.9.1
     hooks:
       - id: nbqa-black
       - id: nbqa-pyupgrade

.vscode/extensions.json

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

.vscode/settings.json

@@ -2,29 +2,20 @@
     "editor.formatOnSave": true,
     "files.insertFinalNewline": false,
     "[python]": {
-        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.defaultFormatter": "charliermarsh.ruff",
         "editor.formatOnType": true,
         "editor.codeActionsOnSave": {
+            "source.fixAll.ruff": "explicit",
             "source.organizeImports": "explicit"
         }
     },
     "[jupyter]": {
         "files.insertFinalNewline": false
     },
-    "black-formatter.args": [
-        "--line-length=119"
-    ],
-    "isort.args": ["--profile", "black"],
-    "flake8.args": [
-        "--max-line-length=119"
-    ],
-    "ruff.lint.args": [
-        "--line-length=119"
-    ],
     "notebook.output.scrolling": true,
     "notebook.formatOnCellExecution": true,
     "notebook.formatOnSave.enabled": true,
-        "notebook.codeActionsOnSave": {
-            "source.organizeImports": "explicit"
-        }
+    "notebook.codeActionsOnSave": {
+        "source.organizeImports": "explicit"
+    }
 }

README.md

@@ -4,7 +4,7 @@ emoji: 📉
 colorFrom: yellow
 colorTo: green
 sdk: gradio
-sdk_version: 5.6.0
+sdk_version: 5.9.1
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -1,7 +1,5 @@
 #!/usr/bin/env python
 
-from __future__ import annotations
-
 import gradio as gr
 import torch
 

model.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import gc
 
 import numpy as np
@@ -40,14 +38,16 @@ def download_all_controlnet_weights() -> None:
 
 
 class Model:
-    def __init__(self, base_model_id: str = "stable-diffusion-v1-5/stable-diffusion-v1-5", task_name: str = "Canny"):
+    def __init__(
+        self, base_model_id: str = "stable-diffusion-v1-5/stable-diffusion-v1-5", task_name: str = "Canny"
+    ) -> None:
         self.device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
         self.base_model_id = ""
         self.task_name = ""
         self.pipe = self.load_pipe(base_model_id, task_name)
         self.preprocessor = Preprocessor()
 
-    def load_pipe(self, base_model_id: str, task_name) -> DiffusionPipeline:
+    def load_pipe(self, base_model_id: str, task_name: str) -> DiffusionPipeline:
         if (
             base_model_id == self.base_model_id
             and task_name == self.task_name
@@ -78,7 +78,7 @@ class Model:
         gc.collect()
         try:
             self.pipe = self.load_pipe(base_model_id, self.task_name)
-        except Exception:
+        except Exception:  # noqa: BLE001
             self.pipe = self.load_pipe(self.base_model_id, self.task_name)
         return self.base_model_id
 
@@ -98,11 +98,7 @@ class Model:
         self.task_name = task_name
 
     def get_prompt(self, prompt: str, additional_prompt: str) -> str:
-        if not prompt:
-            prompt = additional_prompt
-        else:
-            prompt = f"{prompt}, {additional_prompt}"
-        return prompt
+        return additional_prompt if not prompt else f"{prompt}, {additional_prompt}"
 
     @torch.autocast("cuda")
     def run_pipe(
@@ -163,7 +159,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_mlsd(
@@ -206,7 +202,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_scribble(
@@ -260,7 +256,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_scribble_interactive(
@@ -297,7 +293,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_softedge(
@@ -355,7 +351,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_openpose(
@@ -401,7 +397,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_segmentation(
@@ -446,7 +442,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_depth(
@@ -491,7 +487,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_normal(
@@ -536,7 +532,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_lineart(
@@ -593,7 +589,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_shuffle(
@@ -636,7 +632,7 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]
 
     @torch.inference_mode()
     def process_ip2p(
@@ -671,4 +667,4 @@ class Model:
             guidance_scale=guidance_scale,
             seed=seed,
         )
-        return [control_image] + results
+        return [control_image, *results]

preprocessor.py

@@ -1,4 +1,8 @@
 import gc
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
 
 import numpy as np
 import PIL.Image
@@ -25,11 +29,11 @@ from image_segmentor import ImageSegmentor
 class Preprocessor:
     MODEL_ID = "lllyasviel/Annotators"
 
-    def __init__(self):
-        self.model = None
+    def __init__(self) -> None:
+        self.model: Callable = None  # type: ignore
         self.name = ""
 
-    def load(self, name: str) -> None:
+    def load(self, name: str) -> None:  # noqa: C901, PLR0912
         if name == self.name:
             return
         if name == "HED":
@@ -62,7 +66,7 @@ class Preprocessor:
         gc.collect()
         self.name = name
 
-    def __call__(self, image: PIL.Image.Image, **kwargs) -> PIL.Image.Image:
+    def __call__(self, image: PIL.Image.Image, **kwargs) -> PIL.Image.Image:  # noqa: ANN003
         if self.name == "Canny":
             if "detect_resolution" in kwargs:
                 detect_resolution = kwargs.pop("detect_resolution")
@@ -71,7 +75,7 @@ class Preprocessor:
                 image = resize_image(image, resolution=detect_resolution)
             image = self.model(image, **kwargs)
             return PIL.Image.fromarray(image)
-        elif self.name == "Midas":
+        if self.name == "Midas":
             detect_resolution = kwargs.pop("detect_resolution", 512)
             image_resolution = kwargs.pop("image_resolution", 512)
             image = np.array(image)
@@ -81,5 +85,4 @@ class Preprocessor:
             image = HWC3(image)
             image = resize_image(image, resolution=image_resolution)
             return PIL.Image.fromarray(image)
-        else:
-            return self.model(image, **kwargs)
+        return self.model(image, **kwargs)

pyproject.toml

@@ -5,18 +5,54 @@ description = ""
 readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
-    "accelerate>=1.1.1",
+    "accelerate>=1.2.1",
     "controlnet-aux>=0.0.9",
-    "diffusers>=0.31.0",
+    "diffusers>=0.32.1",
     "einops>=0.8.0",
-    "gradio>=5.6.0",
+    "gradio>=5.9.1",
     "hf-transfer>=0.1.8",
     "mediapipe>=0.10.18",
     "opencv-python-headless>=4.10.0.84",
     "safetensors>=0.4.5",
-    "spaces>=0.30.4",
+    "spaces>=0.31.1",
     "torch==2.4.0",
     "torchvision>=0.19.0",
-    "transformers>=4.46.3",
+    "transformers>=4.47.1",
     "xformers>=0.0.27.post2",
 ]
+
+[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
+]
+extend-ignore = [
+    "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.format]
+docstring-code-format = true

requirements.txt

@@ -2,29 +2,29 @@
 #    uv pip compile pyproject.toml -o requirements.txt
 absl-py==2.1.0
     # via mediapipe
-accelerate==1.1.1
+accelerate==1.2.1
     # via controlnet-v1-1 (pyproject.toml)
 aiofiles==23.2.1
     # via gradio
 annotated-types==0.7.0
     # via pydantic
-anyio==4.6.2.post1
+anyio==4.7.0
     # via
     #   gradio
     #   httpx
     #   starlette
-attrs==24.2.0
+attrs==24.3.0
     # via mediapipe
-certifi==2024.8.30
+certifi==2024.12.14
     # via
     #   httpcore
     #   httpx
     #   requests
 cffi==1.17.1
     # via sounddevice
-charset-normalizer==3.4.0
+charset-normalizer==3.4.1
     # via requests
-click==8.1.7
+click==8.1.8
     # via
     #   typer
     #   uvicorn
@@ -34,7 +34,7 @@ controlnet-aux==0.0.9
     # via controlnet-v1-1 (pyproject.toml)
 cycler==0.12.1
     # via matplotlib
-diffusers==0.31.0
+diffusers==0.32.1
     # via controlnet-v1-1 (pyproject.toml)
 einops==0.8.0
     # via
@@ -42,9 +42,9 @@ einops==0.8.0
     #   controlnet-aux
 exceptiongroup==1.2.2
     # via anyio
-fastapi==0.115.5
+fastapi==0.115.6
     # via gradio
-ffmpy==0.4.0
+ffmpy==0.5.0
     # via gradio
 filelock==3.16.1
     # via
@@ -54,20 +54,20 @@ filelock==3.16.1
     #   torch
     #   transformers
     #   triton
-flatbuffers==24.3.25
+flatbuffers==24.12.23
     # via mediapipe
-fonttools==4.55.0
+fonttools==4.55.3
     # via matplotlib
-fsspec==2024.10.0
+fsspec==2024.12.0
     # via
     #   gradio-client
     #   huggingface-hub
     #   torch
-gradio==5.6.0
+gradio==5.9.1
     # via
     #   controlnet-v1-1 (pyproject.toml)
     #   spaces
-gradio-client==1.4.3
+gradio-client==1.5.2
     # via gradio
 h11==0.14.0
     # via
@@ -77,13 +77,13 @@ hf-transfer==0.1.8
     # via controlnet-v1-1 (pyproject.toml)
 httpcore==1.0.7
     # via httpx
-httpx==0.27.2
+httpx==0.28.1
     # via
     #   gradio
     #   gradio-client
     #   safehttpx
     #   spaces
-huggingface-hub==0.26.2
+huggingface-hub==0.27.0
     # via
     #   accelerate
     #   controlnet-aux
@@ -97,23 +97,23 @@ idna==3.10
     #   anyio
     #   httpx
     #   requests
-imageio==2.36.0
+imageio==2.36.1
     # via scikit-image
 importlib-metadata==8.5.0
     # via
     #   controlnet-aux
     #   diffusers
-jax==0.4.35
+jax==0.4.38
     # via mediapipe
-jaxlib==0.4.35
+jaxlib==0.4.38
     # via
     #   jax
     #   mediapipe
-jinja2==3.1.4
+jinja2==3.1.5
     # via
     #   gradio
     #   torch
-kiwisolver==1.4.7
+kiwisolver==1.4.8
     # via matplotlib
 lazy-loader==0.4
     # via scikit-image
@@ -123,11 +123,11 @@ markupsafe==2.1.5
     # via
     #   gradio
     #   jinja2
-matplotlib==3.9.2
+matplotlib==3.10.0
     # via mediapipe
 mdurl==0.1.2
     # via markdown-it-py
-mediapipe==0.10.18
+mediapipe==0.10.20
     # via controlnet-v1-1 (pyproject.toml)
 ml-dtypes==0.5.0
     # via
@@ -186,7 +186,7 @@ nvidia-cusparse-cu12==12.1.0.106
     #   torch
 nvidia-nccl-cu12==2.20.5
     # via torch
-nvidia-nvjitlink-cu12==12.6.77
+nvidia-nvjitlink-cu12==12.6.85
     # via
     #   nvidia-cusolver-cu12
     #   nvidia-cusparse-cu12
@@ -200,7 +200,7 @@ opencv-python-headless==4.10.0.84
     #   controlnet-aux
 opt-einsum==3.4.0
     # via jax
-orjson==3.10.11
+orjson==3.10.13
     # via gradio
 packaging==24.2
     # via
@@ -232,24 +232,24 @@ psutil==5.9.8
     #   spaces
 pycparser==2.22
     # via cffi
-pydantic==2.9.2
+pydantic==2.10.4
     # via
     #   fastapi
     #   gradio
     #   spaces
-pydantic-core==2.23.4
+pydantic-core==2.27.2
     # via pydantic
 pydub==0.25.1
     # via gradio
 pygments==2.18.0
     # via rich
-pyparsing==3.2.0
+pyparsing==3.2.1
     # via matplotlib
 python-dateutil==2.9.0.post0
     # via
     #   matplotlib
     #   pandas
-python-multipart==0.0.12
+python-multipart==0.0.20
     # via gradio
 pytz==2024.2
     # via pandas
@@ -271,9 +271,9 @@ requests==2.32.3
     #   transformers
 rich==13.9.4
     # via typer
-ruff==0.7.4
+ruff==0.8.4
     # via gradio
-safehttpx==0.1.1
+safehttpx==0.1.6
     # via gradio
 safetensors==0.4.5
     # via
@@ -281,7 +281,7 @@ safetensors==0.4.5
     #   accelerate
     #   diffusers
     #   transformers
-scikit-image==0.24.0
+scikit-image==0.25.0
     # via controlnet-aux
 scipy==1.14.1
     # via
@@ -295,15 +295,13 @@ sentencepiece==0.2.0
     # via mediapipe
 shellingham==1.5.4
     # via typer
-six==1.16.0
+six==1.17.0
     # via python-dateutil
 sniffio==1.3.1
-    # via
-    #   anyio
-    #   httpx
+    # via anyio
 sounddevice==0.5.1
     # via mediapipe
-spaces==0.30.4
+spaces==0.31.1
     # via controlnet-v1-1 (pyproject.toml)
 starlette==0.41.3
     # via
@@ -311,13 +309,13 @@ starlette==0.41.3
     #   gradio
 sympy==1.13.3
     # via torch
-tifffile==2024.9.20
+tifffile==2024.12.12
     # via scikit-image
 timm==0.6.7
     # via controlnet-aux
-tokenizers==0.20.3
+tokenizers==0.21.0
     # via transformers
-tomlkit==0.12.0
+tomlkit==0.13.2
     # via gradio
 torch==2.4.0
     # via
@@ -332,15 +330,15 @@ torchvision==0.19.0
     #   controlnet-v1-1 (pyproject.toml)
     #   controlnet-aux
     #   timm
-tqdm==4.67.0
+tqdm==4.67.1
     # via
     #   huggingface-hub
     #   transformers
-transformers==4.46.3
+transformers==4.47.1
     # via controlnet-v1-1 (pyproject.toml)
 triton==3.0.0
     # via torch
-typer==0.13.1
+typer==0.15.1
     # via gradio
 typing-extensions==4.12.2
     # via
@@ -358,11 +356,11 @@ typing-extensions==4.12.2
     #   uvicorn
 tzdata==2024.2
     # via pandas
-urllib3==2.2.3
+urllib3==2.3.0
     # via requests
-uvicorn==0.32.0
+uvicorn==0.34.0
     # via gradio
-websockets==12.0
+websockets==14.1
     # via gradio-client
 xformers==0.0.27.post2
     # via controlnet-v1-1 (pyproject.toml)

utils.py

@@ -5,5 +5,5 @@ from settings import MAX_SEED
 
 def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
     if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
+        seed = random.randint(0, MAX_SEED)  # noqa: S311
     return seed