File size: 6,496 Bytes
b85284b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f77ad3f
 
 
 
 
 
 
b85284b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5c0e5ea
f77ad3f
b85284b
 
 
 
 
 
 
e89b524
b85284b
 
 
 
 
 
 
 
 
 
80d903f
 
b85284b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f77ad3f
b85284b
 
e89b524
 
b85284b
e89b524
 
 
 
 
b85284b
 
e89b524
b85284b
 
 
 
e89b524
b85284b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#!/usr/bin/env python

from __future__ import annotations

import argparse
import os
import pathlib
import subprocess

import gradio as gr

if os.getenv('SYSTEM') == 'spaces':
    subprocess.call('pip uninstall -y mmcv-full'.split())
    subprocess.call('pip install mmcv-full==1.5.2'.split())
    subprocess.call('git apply ../patch'.split(), cwd='Text2Human')

from model import Model

DESCRIPTION = '''# Text2Human

This is an unofficial demo for <a href="https://github.com/yumingj/Text2Human">https://github.com/yumingj/Text2Human</a>.
You can modify sample steps and seeds. By varying seeds, you can sample different human images under the same pose, shape description, and texture description. The larger the sample steps, the better quality of the generated images. (The default value of sample steps is 256 in the original repo.)
'''
FOOTER = '<img id="visitor-badge" alt="visitor badge" src="https://visitor-badge.glitch.me/badge?page_id=hysts.text2human" />'


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser()
    parser.add_argument('--device', type=str, default='cpu')
    parser.add_argument('--theme', type=str)
    parser.add_argument('--share', action='store_true')
    parser.add_argument('--port', type=int)
    parser.add_argument('--disable-queue',
                        dest='enable_queue',
                        action='store_false')
    return parser.parse_args()


def set_example_image(example: list) -> dict:
    return gr.Image.update(value=example[0])


def set_example_text(example: list) -> dict:
    return gr.Textbox.update(value=example[0])


def main():
    args = parse_args()
    model = Model(args.device)

    with gr.Blocks(theme=args.theme, css='style.css') as demo:
        gr.Markdown(DESCRIPTION)

        with gr.Row():
            with gr.Column():
                with gr.Row():
                    input_image = gr.Image(label='Input Pose Image',
                                           type='pil',
                                           elem_id='input-image')
                    pose_data = gr.Variable()
                with gr.Row():
                    paths = sorted(pathlib.Path('pose_images').glob('*.png'))
                    example_images = gr.Dataset(components=[input_image],
                                                samples=[[path.as_posix()]
                                                         for path in paths])

            with gr.Column():
                with gr.Row():
                    label_image = gr.Image(label='Label Image',
                                           type='numpy',
                                           elem_id='label-image',
                                           interactive=False)
                with gr.Row():
                    shape_text = gr.Textbox(
                        label='Shape Description',
                        placeholder=
                        '''<gender>, <sleeve length>, <length of lower clothing>, <outer clothing type>, <other accessories1>, ...
Note: The outer clothing type and accessories can be omitted.''')
                with gr.Row():
                    shape_example_texts = gr.Dataset(
                        components=[shape_text],
                        samples=[['man, sleeveless T-shirt, long pants'],
                                 ['woman, short-sleeve T-shirt, short jeans']])
                with gr.Row():
                    generate_label_button = gr.Button('Generate Label Image')

            with gr.Column():
                with gr.Row():
                    result = gr.Image(label='Result',
                                      type='numpy',
                                      elem_id='result-image')
                with gr.Row():
                    texture_text = gr.Textbox(
                        label='Texture Description',
                        placeholder=
                        '''<upper clothing texture>, <lower clothing texture>, <outer clothing texture>
Note: Currently, only 5 types of textures are supported, i.e., pure color, stripe/spline, plaid/lattice, floral, denim.'''
                    )
                with gr.Row():
                    texture_example_texts = gr.Dataset(
                        components=[texture_text],
                        samples=[['pure color, denim'], ['floral, stripe']])
                with gr.Row():
                    sample_steps = gr.Slider(10,
                                             300,
                                             value=10,
                                             step=10,
                                             label='Sample Steps')
                with gr.Row():
                    seed = gr.Slider(0, 1000000, value=0, step=1, label='Seed')
                with gr.Row():
                    generate_human_button = gr.Button('Generate Human')

        gr.Markdown(FOOTER)

        input_image.change(fn=model.process_pose_image,
                           inputs=input_image,
                           outputs=pose_data)
        generate_label_button.click(fn=model.generate_label_image,
                                    inputs=[
                                        pose_data,
                                        shape_text,
                                    ],
                                    outputs=label_image)
        generate_human_button.click(fn=model.generate_human,
                                    inputs=[
                                        label_image,
                                        texture_text,
                                        sample_steps,
                                        seed,
                                    ],
                                    outputs=result)
        example_images.click(fn=set_example_image,
                             inputs=example_images,
                             outputs=example_images.components)
        shape_example_texts.click(fn=set_example_text,
                                  inputs=shape_example_texts,
                                  outputs=shape_example_texts.components)
        texture_example_texts.click(fn=set_example_text,
                                    inputs=texture_example_texts,
                                    outputs=texture_example_texts.components)

    demo.launch(
        enable_queue=args.enable_queue,
        server_port=args.port,
        share=args.share,
    )


if __name__ == '__main__':
    main()