File size: 6,475 Bytes
99243b4
 
 
 
 
 
 
c06a3d7
73099b9
c06a3d7
ae149aa
c06a3d7
73099b9
ae149aa
2dfdfa9
 
73099b9
ae149aa
73099b9
ae149aa
 
 
 
 
 
 
73099b9
ae149aa
2dfdfa9
 
73099b9
 
1421d7a
2dfdfa9
 
73099b9
 
ae149aa
 
 
 
 
 
 
73099b9
ae149aa
2dfdfa9
 
73099b9
 
ae149aa
99243b4
 
9735cfa
99243b4
ae149aa
9735cfa
73099b9
ae149aa
 
 
73099b9
 
9735cfa
f4b5294
9735cfa
 
ae149aa
 
9735cfa
ae149aa
 
 
 
 
9735cfa
 
 
ae149aa
9735cfa
ae149aa
9735cfa
 
ae149aa
9735cfa
ae149aa
9735cfa
 
 
ae149aa
 
9735cfa
ae149aa
 
 
73099b9
 
 
ae149aa
 
9735cfa
 
ae149aa
 
8d3fe6c
ae149aa
9735cfa
 
 
 
ae149aa
 
 
 
9735cfa
 
 
 
ae149aa
 
 
73099b9
 
9735cfa
 
73099b9
ae149aa
 
9735cfa
 
 
ae149aa
9735cfa
ae149aa
9735cfa
ae149aa
9735cfa
ae149aa
9735cfa
 
ae149aa
9735cfa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99243b4
9735cfa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae149aa
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
#!/usr/bin/env python

from __future__ import annotations

import pathlib

import gradio as gr

from dualstylegan import Model

DESCRIPTION = """# Portrait Style Transfer with [DualStyleGAN](https://github.com/williamyang1991/DualStyleGAN)

<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"
    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",
    }
    return f"{base_url}/{filenames[style_name]}"


def get_style_image_markdown_text(style_name: str) -> str:
    url = get_style_image_url(style_name)
    return f'<img id="style-image" src="{url}" alt="style image">'


def update_slider(choice: str) -> dict:
    max_vals = {
        "cartoon": 316,
        "caricature": 198,
        "anime": 173,
        "arcane": 99,
        "comic": 100,
        "pixar": 121,
        "slamdunk": 119,
    }
    return gr.Slider(maximum=max_vals[choice])


def update_style_image(style_name: str) -> dict:
    text = get_style_image_markdown_text(style_name)
    return gr.Markdown(value=text)


model = Model()

with gr.Blocks(css="style.css") as demo:
    gr.Markdown(DESCRIPTION)

    with gr.Group():
        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 **Preprocess** button.
- Choose the encoder version. Default is Z+ encoder which has better stylization performance. W+ encoder better reconstructs the input image to preserve more details.
- 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():
            encoder_type = gr.Radio(
                label="Encoder Type",
                choices=["Z+ encoder (better stylization)", "W+ encoder (better reconstruction)"],
                value="Z+ encoder (better stylization)",
            )
        with gr.Row():
            with gr.Column():
                with gr.Row():
                    input_image = gr.Image(label="Input Image", type="filepath")
                with gr.Row():
                    preprocess_button = gr.Button("Preprocess")
            with gr.Column():
                with gr.Row():
                    aligned_face = gr.Image(label="Aligned Face", type="numpy", interactive=False)
            with gr.Column():
                reconstructed_face = gr.Image(label="Reconstructed Face", type="numpy")
                instyle = gr.State()

        with gr.Row():
            paths = sorted(pathlib.Path("images").glob("*.jpg"))
            gr.Examples(examples=[[path.as_posix()] for path in paths], inputs=input_image)

    with gr.Group():
        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, value=model.style_types[0])
                text = get_style_image_markdown_text("cartoon")
                style_image = gr.Markdown(value=text, latex_delimiters=[])
                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],
            )

    with gr.Group():
        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.
- Tips: For W+ encoder, better way of (Structure Only) is to uncheck (Structure Only) and set Color weight to 0.
- 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)
                with gr.Row():
                    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", value=False)
                with gr.Row():
                    generate_button = gr.Button("Generate")

            with gr.Column():
                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],
            )

    preprocess_button.click(
        fn=model.detect_and_align_face,
        inputs=[input_image],
        outputs=aligned_face,
    )
    aligned_face.change(
        fn=model.reconstruct_face,
        inputs=[aligned_face, encoder_type],
        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,
    )

if __name__ == "__main__":
    demo.queue(max_size=20).launch()