File size: 13,186 Bytes
df6cc56
 
 
 
 
 
 
 
 
e0ba903
 
 
 
 
 
 
4a4217c
 
df6cc56
 
 
 
 
e0ba903
cd9b314
df6cc56
e0ba903
df6cc56
e0ba903
df6cc56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a36c88f
 
e0ba903
df6cc56
 
 
e0ba903
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
df6cc56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4a4217c
df6cc56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4a4217c
 
df6cc56
 
cd9b314
df6cc56
 
 
e0ba903
df6cc56
e0ba903
 
 
 
cd9b314
 
df6cc56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e0ba903
df6cc56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e0ba903
 
 
 
 
df6cc56
 
e0ba903
 
 
 
df6cc56
 
 
 
 
 
 
 
 
 
 
 
 
 
cd9b314
e0ba903
cd9b314
df6cc56
 
 
 
 
 
 
 
 
 
 
cd9b314
df6cc56
cd9b314
df6cc56
cd9b314
df6cc56
e0ba903
df6cc56
a36c88f
 
 
 
 
 
 
 
 
 
 
e0ba903
a36c88f
 
 
 
e0ba903
df6cc56
 
 
 
a36c88f
df6cc56
 
 
 
 
e0ba903
df6cc56
 
 
 
 
 
 
 
 
 
 
 
e0ba903
df6cc56
e0ba903
df6cc56
4a4217c
e0ba903
 
4a4217c
df6cc56
a36c88f
df6cc56
e0ba903
df6cc56
4a4217c
e0ba903
 
4a4217c
df6cc56
a36c88f
df6cc56
 
e0ba903
a36c88f
 
 
 
e0ba903
a36c88f
df6cc56
 
e0ba903
df6cc56
e0ba903
 
 
a36c88f
 
df6cc56
 
 
 
 
 
 
 
e0ba903
 
 
df6cc56
 
 
b2db940
e0ba903
 
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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
# install

import gradio as gr
import os

import subprocess

if os.getenv('SYSTEM') == 'spaces':
    # subprocess.run('pip install pyembree'.split())
    try:
        import pytorch3d
    except ImportError:
        subprocess.run(
            'pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py38_cu116_pyt1130/download.html'
            .split()
        )
    subprocess.run("python setup.py build_ext --inplace".split(), cwd="./lib/common/libmesh/")
    subprocess.run("python setup.py build_ext --inplace".split(), cwd="./lib/common/libvoxelize/")

from apps.infer import generate_model, generate_video

# running

title = '''
# Unconstrained & Detailed Clothed Human Digitization (ECON + ControlNet) 
### ECON: Explicit Clothed humans Optimized via Normal integration (CVPR 2023, Highlight)
'''

bottom = '''


#### Citation
```
@inproceedings{xiu2023econ,
  title     = {{ECON: Explicit Clothed humans Optimized via Normal integration}},
  author    = {Xiu, Yuliang and Yang, Jinlong and Cao, Xu and Tzionas, Dimitrios and Black, Michael J.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  year      = {2023},
} 
```


<details>

<summary>More</summary>

#### Acknowledgments:
- [controlnet-openpose](https://huggingface.co/spaces/diffusers/controlnet-openpose)
- [TEXTure](https://huggingface.co/spaces/TEXTurePaper/TEXTure)


#### Image Credits

* [Pinterest](https://www.pinterest.com/search/pins/?q=parkour&rs=sitelinks_searchbox)

#### Related works

* [ICON @ MPI-IS](https://icon.is.tue.mpg.de/)
* [MonoPort @ USC](https://xiuyuliang.cn/monoport)
* [Phorhum @ Google](https://phorhum.github.io/)
* [PIFuHD @ Meta](https://shunsukesaito.github.io/PIFuHD/)
* [PaMIR @ Tsinghua](http://www.liuyebin.com/pamir/pamir.html)

</details>

<center>
<a href="https://huggingface.co/spaces/Yuliang/ECON?duplicate=true"><img src="https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-lg-dark.svg"/></a>
<h2> Generate pose & prompt-guided images / Upload photos /  Use examples &rarr; Submit Image (~3min) &rarr; Generate Video (~3min) </h2>
<h2><span style="color:red">ECON is only suitable for "humanoid images" and will not work well on cartoons with non-human shapes.</span></h2>
</center>
'''

description = '''
<table>
<th width="20%">
<ul>
<li><strong>Homepage</strong> <a href="https://econ.is.tue.mpg.de/">econ.is.tue.mpg.de</a></li>
<li><strong>Code</strong> <a href="https://github.com/YuliangXiu/ECON">YuliangXiu/ECON</a></li>
<li><strong>Paper</strong> <a href="https://arxiv.org/abs/2212.07422">arXiv</a>, <a href="https://readpaper.com/paper/4736821012688027649">ReadPaper</a></li>
<li><strong>Chatroom</strong> <a href="https://discord.gg/Vqa7KBGRyk">Discord</a></li>
</ul>
<br>
<ul>
<li><strong>Colab Notebook</strong> <a href='https://colab.research.google.com/drive/1YRgwoRCZIrSB2e7auEWFyG10Xzjbrbno?usp=sharing'><img style="display: inline-block;" src='https://colab.research.google.com/assets/colab-badge.svg' alt='Google Colab'></a></li>
<li><strong>Blender Plugin</strong> <a href='https://carlosedubarreto.gumroad.com/l/CEB_ECON'><img style="display: inline-block;" src='https://img.shields.io/badge/Blender-F6DDCC.svg?logo=Blender' alt='Blender'></a></li>
<li><strong>Docker Image</strong> <a href='https://github.com/YuliangXiu/ECON/blob/master/docs/installation-docker.md'><img style="display: inline-block;" src='https://img.shields.io/badge/Docker-9cf.svg?logo=Docker' alt='Docker'></a></li>
<li><strong>Windows Setup</strong> <a href="https://github.com/YuliangXiu/ECON/blob/master/docs/installation-windows.md"><img style="display: inline-block;" src='https://img.shields.io/badge/Windows-00a2ed.svg?logo=Windows' akt='Windows'></a></li>
</ul>

<br>
<a href="https://twitter.com/yuliangxiu"><img alt="Twitter Follow" src="https://img.shields.io/twitter/follow/yuliangxiu?style=social"></a><br>
<iframe src="https://ghbtns.com/github-btn.html?user=yuliangxiu&repo=ECON&type=star&count=true&v=2&size=small" frameborder="0" scrolling="0" width="100" height="20"></iframe>
</th>
<th width="40%">
<iframe width="560" height="315" src="https://www.youtube.com/embed/5PEd_p90kS0" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
</th>
<th width="40%">
<iframe width="560" height="315" src="https://www.youtube.com/embed/sbWZbTf6ZYk" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
</th>
</table>
'''

from controlnet_aux import OpenposeDetector
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
from diffusers import UniPCMultistepScheduler
import gradio as gr
import torch
import base64
from io import BytesIO
from PIL import Image

# live conditioning
canvas_html = "<pose-canvas id='canvas-root' style='display:flex;max-width: 500px;margin: 0 auto;'></pose-canvas>"
load_js = """
async () => {
  const url = "https://huggingface.co/datasets/radames/gradio-components/raw/main/pose-gradio.js"
  fetch(url)
    .then(res => res.text())
    .then(text => {
      const script = document.createElement('script');
      script.type = "module"
      script.src = URL.createObjectURL(new Blob([text], { type: 'application/javascript' }));
      document.head.appendChild(script);
    });
}
"""
get_js_image = """
async (image_in_img, prompt, image_file_live_opt, live_conditioning) => {
  const canvasEl = document.getElementById("canvas-root");
  const data = canvasEl? canvasEl._data : null;
  return [image_in_img, prompt, image_file_live_opt, data]
}
"""

# Constants
cached = False

# Models
pose_model = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
controlnet = ControlNetModel.from_pretrained(
    "lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16
)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    controlnet=controlnet,
    safety_checker=None,
    torch_dtype=torch.float16
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)

# This command loads the individual model components on GPU on-demand. So, we don't
# need to explicitly call pipe.to("cuda").
pipe.enable_model_cpu_offload()

# xformers
pipe.enable_xformers_memory_efficient_attention()

# Generator seed,
generator = torch.manual_seed(0)

hint_prompts = '''
<strong>Hints</strong>: <br>
best quality, extremely detailed, solid color background, 
super detail, high detail, edge lighting, soft focus, 
light and dark contrast, 8k, edge lighting, 3d, c4d, 
blender, oc renderer, ultra high definition, 3d rendering
'''


def get_pose(image):
    return pose_model(image)

import sys

def read_logs():
    sys.stdout.flush()
    with open("output.log", "r") as f:
        return f.read()


def generate_images(image, prompt, image_file_live_opt='file', live_conditioning=None):
    if image is None and 'image' not in live_conditioning:
        raise gr.Error("Please provide an image")
    try:
        if image_file_live_opt == 'file':
            pose = get_pose(image)
        elif image_file_live_opt == 'webcam':
            base64_img = live_conditioning['image']
            image_data = base64.b64decode(base64_img.split(',')[1])
            pose = Image.open(BytesIO(image_data)).convert('RGB').resize((512, 512))
        output = pipe(
            prompt,
            pose,
            generator=generator,
            num_images_per_prompt=3,
            num_inference_steps=50,
        )
        all_outputs = []
        all_outputs.append(pose)
        for image in output.images:
            all_outputs.append(image)
        return all_outputs, all_outputs
    except Exception as e:
        raise gr.Error(str(e))


def toggle(choice):
    if choice == "file":
        return gr.update(visible=True, value=None), gr.update(visible=False, value=None)
    elif choice == "webcam":
        return gr.update(visible=False, value=None), gr.update(visible=True, value=canvas_html)


examples_pose = 'examples/pose'
examples_cloth = 'examples/cloth'

def show_video():
    return gr.update(visible=True), gr.update(visible=True)

with gr.Blocks() as demo:
    
    gr.Markdown(title)
    gr.HTML(description)
    gr.Markdown(bottom)

    out_lst = []
    with gr.Row():
        with gr.Column():
            with gr.Row():

                live_conditioning = gr.JSON(value={}, visible=False)

                with gr.Column():
                    image_file_live_opt = gr.Radio(["file", "webcam"],
                                                   value="file",
                                                   label="How would you like to upload your image?")

                    with gr.Row():
                        image_in_img = gr.Image(
                            visible=True, type="pil", label="Image for Pose"
                        )
                        canvas = gr.HTML(None, elem_id="canvas_html", visible=False)

                    image_file_live_opt.change(
                        fn=toggle,
                        inputs=[image_file_live_opt],
                        outputs=[image_in_img, canvas],
                        queue=False
                    )
                    prompt = gr.Textbox(
                        label="Enter your prompt to synthesise the image",
                        max_lines=10,
                        placeholder="best quality, extremely detailed",
                    )

                    gr.Markdown(hint_prompts)

                with gr.Column():
                    gallery = gr.Gallery(label="Generated Images", columns=[2],rows=[2])
                    gallery_cache = gr.State()

                    gr.Markdown(
                        '''
                                <center>
                                <strong>Click the target generated image for Reconstruction.</strong> <br>
                                &darr;
                                </center>
                                '''
                    )

                    inp = gr.Image(type="filepath", label="Input Image for Reconstruction")
                    fitting_step = gr.Slider(
                        10,
                        100,
                        step=10,
                        label='Fitting steps (Slower yet Better-aligned SMPL-X)',
                        value=50
                    )

            with gr.Row():
                btn_sample = gr.Button("Generate Image")
                btn_submit = gr.Button("Submit Image (~3min)")

            btn_sample.click(
                fn=generate_images,
                inputs=[image_in_img, prompt, image_file_live_opt, live_conditioning],
                outputs=[gallery, gallery_cache],
                js=get_js_image
            )

            def get_select_index(cache, evt: gr.SelectData):
                return cache[evt.index]

            gallery.select(
                fn=get_select_index,
                inputs=[gallery_cache],
                outputs=[inp],
            )

            with gr.Row():
                
                gr.Examples(
                    examples=examples_pose,
                    inputs=[inp],
                    cache_examples=cached,
                    fn=generate_model,
                    outputs=out_lst,
                    label="Hard Pose Examples"
                )

                gr.Examples(
                    examples=examples_cloth,
                    inputs=[inp],
                    cache_examples=cached,
                    fn=generate_model,
                    outputs=out_lst,
                    label="Loose Cloth Examples"
                )


        with gr.Column():
            overlap_inp = gr.Image(type="filepath", label="Image Normal Overlap")
            out_final = gr.Model3D(
                clear_color=[0.0, 0.0, 0.0, 0.0], label="Clothed human", elem_id="avatar"
            )
            out_smpl = gr.Model3D(
                clear_color=[0.0, 0.0, 0.0, 0.0], label="SMPL-X body (via PIXIE)", elem_id="avatar"
            )

            vis_tensor_path = gr.State()
            

            # logs = gr.Textbox(max_lines=10, label="Logs")
            btn_video = gr.Button("Generate Video (~3min)", visible=False)
            out_vid = gr.Video(label="Shared on Twitter with #ECON", visible=False)

    out_lst = [out_smpl, out_final, overlap_inp, vis_tensor_path]

    btn_video.click(
        fn=generate_video,
        inputs=[vis_tensor_path],
        outputs=[out_vid],
    )

    btn_submit.click(fn=generate_model, inputs=[inp, fitting_step], outputs=out_lst)
    btn_submit.click(fn=show_video, outputs=[btn_video, out_vid])
    # demo.load(read_logs, None, logs, every=1, queue=True, scroll_to_output=True)
    demo.load(None, None, None, js=load_js)

if __name__ == "__main__":

    demo.queue()
    demo.launch(max_threads=4)
    # demo.launch(max_threads=2, debug=True, server_port=8888, server_name="0.0.0.0")