Upload path to pretrained model on SHHQ

.pre-commit-config.yaml

@@ -21,11 +21,11 @@ repos:
   - id: docformatter
     args: ['--in-place']
 - repo: https://github.com/pycqa/isort
-  rev: 5.12.0
+  rev: 5.10.1
   hooks:
     - id: isort
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.991
+  rev: v0.812
   hooks:
     - id: mypy
       args: ['--ignore-missing-imports']
@@ -34,3 +34,13 @@ repos:
   hooks:
   - id: yapf
     args: ['--parallel', '--in-place']
+- repo: https://github.com/kynan/nbstripout
+  rev: 0.5.0
+  hooks:
+    - id: nbstripout
+      args: ['--extra-keys', 'metadata.interpreter metadata.kernelspec cell.metadata.pycharm']
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.3.1
+  hooks:
+    - id: nbqa-isort
+    - id: nbqa-yapf

README.md

@@ -4,10 +4,9 @@ emoji: 🏃
 colorFrom: purple
 colorTo: gray
 sdk: gradio
-sdk_version: 3.36.1
+sdk_version: 3.0.17
 app_file: app.py
 pinned: false
-suggested_hardware: t4-small
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -2,14 +2,12 @@
 
 from __future__ import annotations
 
+import argparse
 import os
 import pathlib
-import random
-import shlex
 import subprocess
 
 import gradio as gr
-import numpy as np
 
 if os.getenv('SYSTEM') == 'spaces':
     import mim
@@ -18,123 +16,143 @@ if os.getenv('SYSTEM') == 'spaces':
     mim.install('mmcv-full==1.5.2', is_yes=True)
 
     with open('patch') as f:
-        subprocess.run(shlex.split('patch -p1'), cwd='Text2Human', stdin=f)
+        subprocess.run('patch -p1'.split(), cwd='Text2Human', stdin=f)
 
 from model import Model
 
-DESCRIPTION = '''# [Text2Human](https://github.com/yumingj/Text2Human)
+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.)
 
 Label image generation step can be skipped. However, in that case, the input label image must be 512x256 in size and must contain only the specified colors.
 '''
-
-MAX_SEED = np.iinfo(np.int32).max
-
-
-def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-    return seed
-
-
-model = Model()
-
-with gr.Blocks(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.State()
-            with gr.Row():
-                paths = sorted(pathlib.Path('pose_images').glob('*.png'))
-                gr.Examples(examples=[[path.as_posix()] for path in paths],
-                            inputs=input_image)
-
-            with gr.Row():
-                shape_text = gr.Textbox(
-                    label='Shape Description',
-                    placeholder=
-                    '''<gender>, <sleeve length>, <length of lower clothing>, <outer clothing type>, <other accessories1>, ...
+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.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():
-                gr.Examples(
-                    examples=[['man, sleeveless T-shirt, long pants'],
-                              ['woman, short-sleeve T-shirt, short jeans']],
-                    inputs=shape_text)
-            with gr.Row():
-                generate_label_button = gr.Button('Generate Label Image')
-
-        with gr.Column():
-            with gr.Row():
-                label_image = gr.Image(label='Label Image',
-                                       type='numpy',
-                                       elem_id='label-image')
-
-            with gr.Row():
-                texture_text = gr.Textbox(
-                    label='Texture Description',
-                    placeholder=
-                    '''<upper clothing texture>, <lower clothing texture>, <outer clothing texture>
+                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():
+                    label_image = gr.Image(label='Label Image',
+                                           type='numpy',
+                                           elem_id='label-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():
-                gr.Examples(examples=[
-                    ['pure color, denim'],
-                    ['floral, stripe'],
-                ],
-                            inputs=texture_text)
-            with gr.Row():
-                sample_steps = gr.Slider(label='Sample Steps',
-                                         minimum=10,
-                                         maximum=300,
-                                         step=1,
-                                         value=256)
-            with gr.Row():
-                seed = gr.Slider(label='Seed',
-                                 minimum=0,
-                                 maximum=MAX_SEED,
-                                 step=1,
-                                 value=0)
-                randomize_seed = gr.Checkbox(label='Randomize seed',
-                                             value=True)
-            with gr.Row():
-                generate_human_button = gr.Button('Generate Human')
-
-        with gr.Column():
-            with gr.Row():
-                result = gr.Image(label='Result',
-                                  type='numpy',
-                                  elem_id='result-image')
-
-    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=randomize_seed_fn,
-                                inputs=[seed, randomize_seed],
-                                outputs=seed,
-                                queue=False).then(
-                                    fn=model.generate_human,
+                    )
+                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')
+
+            with gr.Column():
+                with gr.Row():
+                    result = gr.Image(label='Result',
+                                      type='numpy',
+                                      elem_id='result-image')
+
+        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,
-                                )
-demo.queue(max_size=10).launch()
+                                    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()

model.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import os
 import pathlib
 import sys
 import zipfile
@@ -46,10 +47,9 @@ COLOR_LIST = [
 
 
 class Model:
-    def __init__(self):
-        device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+    def __init__(self, device: str):
         self.config = self._load_config()
-        self.config['device'] = device.type
+        self.config['device'] = device
         self._download_models()
         self.model = SampleFromPoseModel(self.config)
         self.model.batch_size = 1
@@ -64,8 +64,10 @@ class Model:
         model_dir = pathlib.Path('pretrained_models')
         if model_dir.exists():
             return
+        token = os.getenv('HF_TOKEN')
         path = huggingface_hub.hf_hub_download('yumingj/Text2Human_SSHQ',
-                                               'pretrained_models.zip')
+                                               'pretrained_models.zip',
+                                               use_auth_token=token)
         model_dir.mkdir()
         with zipfile.ZipFile(path) as f:
             f.extractall(model_dir)

requirements.txt

@@ -1,12 +1,12 @@
-einops==0.6.1
+einops==0.4.1
 lpips==0.1.4
 mmcv-full==1.5.2
 mmsegmentation==0.24.1
-numpy==1.23.5
+numpy==1.22.3
 openmim==0.1.5
-Pillow==9.5.0
-sentence-transformers==2.2.2
-tokenizers==0.13.3
+Pillow==9.1.1
+sentence-transformers==2.2.0
+tokenizers==0.12.1
 torch==1.11.0
 torchvision==0.12.0
-transformers==4.30.2
+transformers==4.19.2