Update

.pre-commit-config.yaml

@@ -1,37 +1,61 @@
 exclude: ^patch
 repos:
-- repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.2.0
-  hooks:
-  - id: check-executables-have-shebangs
-  - id: check-json
-  - id: check-merge-conflict
-  - id: check-shebang-scripts-are-executable
-  - id: check-toml
-  - id: check-yaml
-  - id: double-quote-string-fixer
-  - id: end-of-file-fixer
-  - id: mixed-line-ending
-    args: ['--fix=lf']
-  - id: requirements-txt-fixer
-  - id: trailing-whitespace
-- repo: https://github.com/myint/docformatter
-  rev: v1.4
-  hooks:
-  - id: docformatter
-    args: ['--in-place']
-- repo: https://github.com/pycqa/isort
-  rev: 5.12.0
-  hooks:
-    - id: isort
-- repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.991
-  hooks:
-    - id: mypy
-      args: ['--ignore-missing-imports']
-      additional_dependencies: ['types-python-slugify']
-- repo: https://github.com/google/yapf
-  rev: v0.32.0
-  hooks:
-  - id: yapf
-    args: ['--parallel', '--in-place']
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-executables-have-shebangs
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/myint/docformatter
+    rev: v1.7.5
+    hooks:
+      - id: docformatter
+        args: ["--in-place"]
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        args: ["--profile", "black"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.10.0
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-requests",
+            "types-PyYAML",
+            "types-pytz",
+          ]
+  - repo: https://github.com/psf/black
+    rev: 24.4.2
+    hooks:
+      - id: black
+        language_version: python3.10
+        args: ["--line-length", "119"]
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.7.1
+    hooks:
+      - id: nbstripout
+        args:
+          [
+            "--extra-keys",
+            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
+          ]
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.8.5
+    hooks:
+      - id: nbqa-black
+      - id: nbqa-pyupgrade
+        args: ["--py37-plus"]
+      - id: nbqa-isort
+        args: ["--float-to-top"]

.style.yapf

@@ -1,5 +0,0 @@
-[style]
-based_on_style = pep8
-blank_line_before_nested_class_or_def = false
-spaces_before_comment = 2
-split_before_logical_operator = true

.vscode/settings.json

@@ -0,0 +1,30 @@
+{
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "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"
+        }
+}

app.py

@@ -9,24 +9,24 @@ import gradio as gr
 
 from dualstylegan import Model
 
-DESCRIPTION = '''# Portrait Style Transfer with <a href="https://github.com/williamyang1991/DualStyleGAN">DualStyleGAN</a>
+DESCRIPTION = """# Portrait Style Transfer with <a href="https://github.com/williamyang1991/DualStyleGAN">DualStyleGAN</a>
 
 <img id="overview" alt="overview" src="https://raw.githubusercontent.com/williamyang1991/DualStyleGAN/main/doc_images/overview.jpg" />
-'''
+"""
 
 
 def get_style_image_url(style_name: str) -> str:
-    base_url = 'https://raw.githubusercontent.com/williamyang1991/DualStyleGAN/main/doc_images'
+    base_url = "https://raw.githubusercontent.com/williamyang1991/DualStyleGAN/main/doc_images"
     filenames = {
-        'cartoon': 'cartoon_overview.jpg',
-        'caricature': 'caricature_overview.jpg',
-        'anime': 'anime_overview.jpg',
-        'arcane': 'Reconstruction_arcane_overview.jpg',
-        'comic': 'Reconstruction_comic_overview.jpg',
-        'pixar': 'Reconstruction_pixar_overview.jpg',
-        'slamdunk': 'Reconstruction_slamdunk_overview.jpg',
+        "cartoon": "cartoon_overview.jpg",
+        "caricature": "caricature_overview.jpg",
+        "anime": "anime_overview.jpg",
+        "arcane": "Reconstruction_arcane_overview.jpg",
+        "comic": "Reconstruction_comic_overview.jpg",
+        "pixar": "Reconstruction_pixar_overview.jpg",
+        "slamdunk": "Reconstruction_slamdunk_overview.jpg",
     }
-    return f'{base_url}/{filenames[style_name]}'
+    return f"{base_url}/{filenames[style_name]}"
 
 
 def get_style_image_markdown_text(style_name: str) -> str:
@@ -36,13 +36,13 @@ def get_style_image_markdown_text(style_name: str) -> str:
 
 def update_slider(choice: str) -> dict:
     max_vals = {
-        'cartoon': 316,
-        'caricature': 198,
-        'anime': 173,
-        'arcane': 99,
-        'comic': 100,
-        'pixar': 121,
-        'slamdunk': 119,
+        "cartoon": 316,
+        "caricature": 198,
+        "anime": 173,
+        "arcane": 99,
+        "comic": 100,
+        "pixar": 121,
+        "slamdunk": 119,
     }
     return gr.Slider.update(maximum=max_vals[choice])
 
@@ -72,125 +72,113 @@ def set_example_weights(example: list) -> list[dict]:
 
 model = Model()
 
-with gr.Blocks(css='style.css') as demo:
+with gr.Blocks(css="style.css") as demo:
     gr.Markdown(DESCRIPTION)
 
     with gr.Box():
-        gr.Markdown('''## Step 1 (Preprocess Input Image)
+        gr.Markdown(
+            """## Step 1 (Preprocess Input Image)
 
 - Drop an image containing a near-frontal face to the **Input Image**.
 - If there are multiple faces in the image, hit the Edit button in the upper right corner and crop the input image beforehand.
 - Hit the **Detect & Align Face** button.
 - Hit the **Reconstruct Face** button.
 - The final result will be based on this **Reconstructed Face**. So, if the reconstructed image is not satisfactory, you may want to change the input image.
-''')
+"""
+        )
         with gr.Row():
             with gr.Column():
                 with gr.Row():
-                    input_image = gr.Image(label='Input Image',
-                                           type='filepath')
+                    input_image = gr.Image(label="Input Image", type="filepath")
                 with gr.Row():
-                    detect_button = gr.Button('Detect & Align Face')
+                    detect_button = gr.Button("Detect & Align Face")
             with gr.Column():
                 with gr.Row():
-                    aligned_face = gr.Image(label='Aligned Face',
-                                            type='numpy',
-                                            interactive=False)
+                    aligned_face = gr.Image(label="Aligned Face", type="numpy", interactive=False)
                 with gr.Row():
-                    reconstruct_button = gr.Button('Reconstruct Face')
+                    reconstruct_button = gr.Button("Reconstruct Face")
             with gr.Column():
-                reconstructed_face = gr.Image(label='Reconstructed Face',
-                                              type='numpy')
+                reconstructed_face = gr.Image(label="Reconstructed Face", type="numpy")
                 instyle = gr.Variable()
 
         with gr.Row():
-            paths = sorted(pathlib.Path('images').glob('*.jpg'))
-            gr.Examples(examples=[[path.as_posix()] for path in paths],
-                        inputs=input_image)
+            paths = sorted(pathlib.Path("images").glob("*.jpg"))
+            gr.Examples(examples=[[path.as_posix()] for path in paths], inputs=input_image)
 
     with gr.Box():
-        gr.Markdown('''## Step 2 (Select Style Image)
+        gr.Markdown(
+            """## Step 2 (Select Style Image)
 
 - Select **Style Type**.
 - Select **Style Image Index** from the image table below.
-''')
+"""
+        )
         with gr.Row():
             with gr.Column():
-                style_type = gr.Radio(label='Style Type',
-                                      choices=model.style_types)
-                text = get_style_image_markdown_text('cartoon')
+                style_type = gr.Radio(label="Style Type", choices=model.style_types)
+                text = get_style_image_markdown_text("cartoon")
                 style_image = gr.Markdown(value=text)
-                style_index = gr.Slider(label='Style Image Index',
-                                        minimum=0,
-                                        maximum=316,
-                                        step=1,
-                                        value=26)
+                style_index = gr.Slider(label="Style Image Index", minimum=0, maximum=316, step=1, value=26)
 
         with gr.Row():
-            gr.Examples(examples=[
-                ['cartoon', 26],
-                ['caricature', 65],
-                ['arcane', 63],
-                ['pixar', 80],
-            ],
-                        inputs=[style_type, style_index])
+            gr.Examples(
+                examples=[
+                    ["cartoon", 26],
+                    ["caricature", 65],
+                    ["arcane", 63],
+                    ["pixar", 80],
+                ],
+                inputs=[style_type, style_index],
+            )
 
     with gr.Box():
-        gr.Markdown('''## Step 3 (Generate Style Transferred Image)
+        gr.Markdown(
+            """## Step 3 (Generate Style Transferred Image)
 
 - Adjust **Structure Weight** and **Color Weight**.
 - These are weights for the style image, so the larger the value, the closer the resulting image will be to the style image.
 - Hit the **Generate** button.
-''')
+"""
+        )
         with gr.Row():
             with gr.Column():
                 with gr.Row():
-                    structure_weight = gr.Slider(label='Structure Weight',
-                                                 minimum=0,
-                                                 maximum=1,
-                                                 step=0.1,
-                                                 value=0.6)
+                    structure_weight = gr.Slider(label="Structure Weight", minimum=0, maximum=1, step=0.1, value=0.6)
                 with gr.Row():
-                    color_weight = gr.Slider(label='Color Weight',
-                                             minimum=0,
-                                             maximum=1,
-                                             step=0.1,
-                                             value=1)
+                    color_weight = gr.Slider(label="Color Weight", minimum=0, maximum=1, step=0.1, value=1)
                 with gr.Row():
-                    structure_only = gr.Checkbox(label='Structure Only')
+                    structure_only = gr.Checkbox(label="Structure Only")
                 with gr.Row():
-                    generate_button = gr.Button('Generate')
+                    generate_button = gr.Button("Generate")
 
             with gr.Column():
-                result = gr.Image(label='Result')
+                result = gr.Image(label="Result")
 
         with gr.Row():
-            gr.Examples(examples=[
-                [0.6, 1.0],
-                [0.3, 1.0],
-                [0.0, 1.0],
-                [1.0, 0.0],
-            ],
-                        inputs=[structure_weight, color_weight])
-
-    detect_button.click(fn=model.detect_and_align_face,
-                        inputs=input_image,
-                        outputs=aligned_face)
-    reconstruct_button.click(fn=model.reconstruct_face,
-                             inputs=aligned_face,
-                             outputs=[reconstructed_face, instyle])
+            gr.Examples(
+                examples=[
+                    [0.6, 1.0],
+                    [0.3, 1.0],
+                    [0.0, 1.0],
+                    [1.0, 0.0],
+                ],
+                inputs=[structure_weight, color_weight],
+            )
+
+    detect_button.click(fn=model.detect_and_align_face, inputs=input_image, outputs=aligned_face)
+    reconstruct_button.click(fn=model.reconstruct_face, inputs=aligned_face, outputs=[reconstructed_face, instyle])
     style_type.change(fn=update_slider, inputs=style_type, outputs=style_index)
-    style_type.change(fn=update_style_image,
-                      inputs=style_type,
-                      outputs=style_image)
-    generate_button.click(fn=model.generate,
-                          inputs=[
-                              style_type,
-                              style_index,
-                              structure_weight,
-                              color_weight,
-                              structure_only,
-                              instyle,
-                          ],
-                          outputs=result)
+    style_type.change(fn=update_style_image, inputs=style_type, outputs=style_image)
+    generate_button.click(
+        fn=model.generate,
+        inputs=[
+            style_type,
+            style_index,
+            structure_weight,
+            color_weight,
+            structure_only,
+            instyle,
+        ],
+        outputs=result,
+    )
 demo.queue(max_size=10).launch()

dualstylegan.py

@@ -16,12 +16,12 @@ import torch
 import torch.nn as nn
 import torchvision.transforms as T
 
-if os.getenv('SYSTEM') == 'spaces' and not torch.cuda.is_available():
-    with open('patch') as f:
-        subprocess.run(shlex.split('patch -p1'), cwd='DualStyleGAN', stdin=f)
+if os.getenv("SYSTEM") == "spaces" and not torch.cuda.is_available():
+    with open("patch") as f:
+        subprocess.run(shlex.split("patch -p1"), cwd="DualStyleGAN", stdin=f)
 
 app_dir = pathlib.Path(__file__).parent
-submodule_dir = app_dir / 'DualStyleGAN'
+submodule_dir = app_dir / "DualStyleGAN"
 sys.path.insert(0, submodule_dir.as_posix())
 
 from model.dualstylegan import DualStyleGAN
@@ -31,44 +31,36 @@ from model.encoder.psp import pSp
 
 class Model:
     def __init__(self):
-        self.device = torch.device(
-            'cuda:0' if torch.cuda.is_available() else 'cpu')
+        self.device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
         self.landmark_model = self._create_dlib_landmark_model()
         self.encoder = self._load_encoder()
         self.transform = self._create_transform()
 
         self.style_types = [
-            'cartoon',
-            'caricature',
-            'anime',
-            'arcane',
-            'comic',
-            'pixar',
-            'slamdunk',
+            "cartoon",
+            "caricature",
+            "anime",
+            "arcane",
+            "comic",
+            "pixar",
+            "slamdunk",
         ]
-        self.generator_dict = {
-            style_type: self._load_generator(style_type)
-            for style_type in self.style_types
-        }
-        self.exstyle_dict = {
-            style_type: self._load_exstylecode(style_type)
-            for style_type in self.style_types
-        }
+        self.generator_dict = {style_type: self._load_generator(style_type) for style_type in self.style_types}
+        self.exstyle_dict = {style_type: self._load_exstylecode(style_type) for style_type in self.style_types}
 
     @staticmethod
     def _create_dlib_landmark_model():
         path = huggingface_hub.hf_hub_download(
-            'public-data/dlib_face_landmark_model',
-            'shape_predictor_68_face_landmarks.dat')
+            "public-data/dlib_face_landmark_model", "shape_predictor_68_face_landmarks.dat"
+        )
         return dlib.shape_predictor(path)
 
     def _load_encoder(self) -> nn.Module:
-        ckpt_path = huggingface_hub.hf_hub_download('public-data/DualStyleGAN',
-                                                    'models/encoder.pt')
-        ckpt = torch.load(ckpt_path, map_location='cpu')
-        opts = ckpt['opts']
-        opts['device'] = self.device.type
-        opts['checkpoint_path'] = ckpt_path
+        ckpt_path = huggingface_hub.hf_hub_download("public-data/DualStyleGAN", "models/encoder.pt")
+        ckpt = torch.load(ckpt_path, map_location="cpu")
+        opts = ckpt["opts"]
+        opts["device"] = self.device.type
+        opts["checkpoint_path"] = ckpt_path
         opts = argparse.Namespace(**opts)
         model = pSp(opts)
         model.to(self.device)
@@ -77,32 +69,32 @@ class Model:
 
     @staticmethod
     def _create_transform() -> Callable:
-        transform = T.Compose([
-            T.Resize(256),
-            T.CenterCrop(256),
-            T.ToTensor(),
-            T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]),
-        ])
+        transform = T.Compose(
+            [
+                T.Resize(256),
+                T.CenterCrop(256),
+                T.ToTensor(),
+                T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]),
+            ]
+        )
         return transform
 
     def _load_generator(self, style_type: str) -> nn.Module:
         model = DualStyleGAN(1024, 512, 8, 2, res_index=6)
-        ckpt_path = huggingface_hub.hf_hub_download(
-            'public-data/DualStyleGAN', f'models/{style_type}/generator.pt')
-        ckpt = torch.load(ckpt_path, map_location='cpu')
-        model.load_state_dict(ckpt['g_ema'])
+        ckpt_path = huggingface_hub.hf_hub_download("public-data/DualStyleGAN", f"models/{style_type}/generator.pt")
+        ckpt = torch.load(ckpt_path, map_location="cpu")
+        model.load_state_dict(ckpt["g_ema"])
         model.to(self.device)
         model.eval()
         return model
 
     @staticmethod
     def _load_exstylecode(style_type: str) -> dict[str, np.ndarray]:
-        if style_type in ['cartoon', 'caricature', 'anime']:
-            filename = 'refined_exstyle_code.npy'
+        if style_type in ["cartoon", "caricature", "anime"]:
+            filename = "refined_exstyle_code.npy"
         else:
-            filename = 'exstyle_code.npy'
-        path = huggingface_hub.hf_hub_download(
-            'public-data/DualStyleGAN', f'models/{style_type}/{filename}')
+            filename = "exstyle_code.npy"
+        path = huggingface_hub.hf_hub_download("public-data/DualStyleGAN", f"models/{style_type}/{filename}")
         exstyles = np.load(path, allow_pickle=True).item()
         return exstyles
 
@@ -119,24 +111,31 @@ class Model:
         return tensor.cpu().numpy().transpose(1, 2, 0)
 
     @torch.inference_mode()
-    def reconstruct_face(self,
-                         image: np.ndarray) -> tuple[np.ndarray, torch.Tensor]:
+    def reconstruct_face(self, image: np.ndarray) -> tuple[np.ndarray, torch.Tensor]:
         image = PIL.Image.fromarray(image)
         input_data = self.transform(image).unsqueeze(0).to(self.device)
-        img_rec, instyle = self.encoder(input_data,
-                                        randomize_noise=False,
-                                        return_latents=True,
-                                        z_plus_latent=True,
-                                        return_z_plus_latent=True,
-                                        resize=False)
+        img_rec, instyle = self.encoder(
+            input_data,
+            randomize_noise=False,
+            return_latents=True,
+            z_plus_latent=True,
+            return_z_plus_latent=True,
+            resize=False,
+        )
         img_rec = torch.clamp(img_rec.detach(), -1, 1)
         img_rec = self.postprocess(img_rec[0])
         return img_rec, instyle
 
     @torch.inference_mode()
-    def generate(self, style_type: str, style_id: int, structure_weight: float,
-                 color_weight: float, structure_only: bool,
-                 instyle: torch.Tensor) -> np.ndarray:
+    def generate(
+        self,
+        style_type: str,
+        style_id: int,
+        structure_weight: float,
+        color_weight: float,
+        structure_only: bool,
+        instyle: torch.Tensor,
+    ) -> np.ndarray:
         generator = self.generator_dict[style_type]
         exstyles = self.exstyle_dict[style_type]
 
@@ -147,17 +146,18 @@ class Model:
         if structure_only:
             latent[0, 7:18] = instyle[0, 7:18]
         exstyle = generator.generator.style(
-            latent.reshape(latent.shape[0] * latent.shape[1],
-                           latent.shape[2])).reshape(latent.shape)
-
-        img_gen, _ = generator([instyle],
-                               exstyle,
-                               z_plus_latent=True,
-                               truncation=0.7,
-                               truncation_latent=0,
-                               use_res=True,
-                               interp_weights=[structure_weight] * 7 +
-                               [color_weight] * 11)
+            latent.reshape(latent.shape[0] * latent.shape[1], latent.shape[2])
+        ).reshape(latent.shape)
+
+        img_gen, _ = generator(
+            [instyle],
+            exstyle,
+            z_plus_latent=True,
+            truncation=0.7,
+            truncation_latent=0,
+            use_res=True,
+            interp_weights=[structure_weight] * 7 + [color_weight] * 11,
+        )
         img_gen = torch.clamp(img_gen.detach(), -1, 1)
         img_gen = self.postprocess(img_gen[0])
         return img_gen

images/README.md

@@ -4,4 +4,3 @@ These images are freely-usable ones from [Unsplash](https://unsplash.com/).
 - https://unsplash.com/photos/et_78QkMMQs
 - https://unsplash.com/photos/ILip77SbmOE
 - https://unsplash.com/photos/95UF6LXe-Lo
-

style.css

@@ -1,5 +1,6 @@
 h1 {
   text-align: center;
+  display: block;
 }
 img#overview {
   max-width: 800px;
@@ -11,7 +12,3 @@ img#style-image {
   max-width: 1000px;
   max-height: 600px;
 }
-img#visitor-badge {
-  display: block;
-  margin: auto;
-}