-
Notifications
You must be signed in to change notification settings - Fork 392
/
gradio_demo_face.py
411 lines (369 loc) · 21.9 KB
/
gradio_demo_face.py
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
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
import os
import gradio as gr
from gradio_imageslider import ImageSlider
import argparse
from SUPIR.util import HWC3, upscale_image, fix_resize, convert_dtype
import numpy as np
import torch
from SUPIR.util import create_SUPIR_model, load_QF_ckpt
from PIL import Image
from llava.llava_agent import LLavaAgent
from CKPT_PTH import LLAVA_MODEL_PATH
import einops
import copy
import time
from omegaconf import OmegaConf
from SUPIR.utils.face_restoration_helper import FaceRestoreHelper
parser = argparse.ArgumentParser()
parser.add_argument("--ip", type=str, default='127.0.0.1')
parser.add_argument("--port", type=int, default='6688')
parser.add_argument("--no_llava", action='store_true', default=False)
parser.add_argument("--use_image_slider", action='store_true', default=False)
parser.add_argument("--log_history", action='store_true', default=False)
parser.add_argument("--loading_half_params", action='store_true', default=False)
parser.add_argument("--use_tile_vae", action='store_true', default=False)
parser.add_argument("--load_8bit_llava", action='store_true', default=False)
parser.add_argument("--local_prompt", action='store_true', default=False)
args = parser.parse_args()
server_ip = args.ip
server_port = args.port
use_llava = not args.no_llava
if torch.cuda.device_count() >= 2:
SUPIR_device = 'cuda:0'
LLaVA_device = 'cuda:1'
elif torch.cuda.device_count() == 1:
SUPIR_device = 'cuda:0'
LLaVA_device = 'cuda:0'
else:
raise ValueError('Currently support CUDA only.')
# load SUPIR
config_path = 'options/SUPIR_v0.yaml'
config = OmegaConf.load(config_path)
model = create_SUPIR_model(config_path, SUPIR_sign='Q')
if args.loading_half_params:
model = model.half()
if args.use_tile_vae:
model.init_tile_vae(encoder_tile_size=512, decoder_tile_size=64)
model = model.to(SUPIR_device)
model.first_stage_model.denoise_encoder_s1 = copy.deepcopy(model.first_stage_model.denoise_encoder)
model.current_model = 'v0-Q'
ckpt_Q, ckpt_F = load_QF_ckpt('options/SUPIR_v0.yaml')
# load LLaVA
if use_llava:
llava_agent = LLavaAgent(LLAVA_MODEL_PATH, device=LLaVA_device, load_8bit=args.load_8bit_llava, load_4bit=False)
else:
llava_agent = None
# load face helper
face_helper = FaceRestoreHelper(
device=SUPIR_device,
upscale_factor=1,
face_size=1024,
use_parse=True,
det_model='retinaface_resnet50'
)
# only exhibit the overall quality of the stage1 output
def stage1_process(input_image, gamma_correction):
torch.cuda.set_device(SUPIR_device)
LQ = HWC3(input_image)
LQ = fix_resize(LQ, 512)
# stage1
LQ = np.array(LQ) / 255 * 2 - 1
LQ = torch.tensor(LQ, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(SUPIR_device)[:, :3, :, :]
LQ = model.batchify_denoise(LQ, is_stage1=True)
LQ = (LQ[0].permute(1, 2, 0) * 127.5 + 127.5).cpu().numpy().round().clip(0, 255).astype(np.uint8)
# gamma correction
LQ = LQ / 255.0
LQ = np.power(LQ, gamma_correction)
LQ *= 255.0
LQ = LQ.round().clip(0, 255).astype(np.uint8)
return LQ
def llave_process(input_image, upscale, temperature, top_p, qs=None):
torch.cuda.set_device(SUPIR_device)
input_image = HWC3(input_image)
input_image = upscale_image(input_image, upscale, unit_resolution=32,
min_size=1024)
LQ = np.array(input_image) / 255 * 2 - 1
LQ = torch.tensor(LQ, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(SUPIR_device)[:, :3, :, :]
LQ = model.batchify_denoise(LQ, is_stage1=True)
LQ = (LQ[0].permute(1, 2, 0) * 127.5 + 127.5).cpu().numpy().round().clip(0, 255).astype(np.uint8)
LQs = [Image.fromarray(LQ)]
face_helper.clean_all()
face_helper.read_image(LQ)
# get face landmarks for each face
face_helper.get_face_landmarks_5(only_center_face=False, resize=640, eye_dist_threshold=5)
face_helper.align_warp_face()
for face in face_helper.cropped_faces:
LQs.append(Image.fromarray(face))
captions = []
torch.cuda.set_device(LLaVA_device)
if use_llava:
for LQ in LQs:
captions += llava_agent.gen_image_caption([LQ], temperature=temperature, top_p=top_p, qs=qs)
else:
captions = ['LLaVA is not available. Please add text manually.']
del LQs[0]
return str(captions), [np.array(face) for face in LQs]
def stage2_process(input_image, prompt, a_prompt, n_prompt, num_samples, upscale, edm_steps, s_stage1, s_stage2,
s_cfg, seed, s_churn, s_noise, color_fix_type, diff_dtype, ae_dtype, gamma_correction,
linear_CFG, linear_s_stage2, spt_linear_CFG, spt_linear_s_stage2, model_select,
face_resolution, apply_bg, apply_face):
torch.cuda.set_device(SUPIR_device)
event_id = str(time.time_ns())
event_dict = {'event_id': event_id, 'localtime': time.ctime(), 'prompt': prompt, 'a_prompt': a_prompt,
'n_prompt': n_prompt, 'num_samples': num_samples, 'upscale': upscale, 'edm_steps': edm_steps,
's_stage1': s_stage1, 's_stage2': s_stage2, 's_cfg': s_cfg, 'seed': seed, 's_churn': s_churn,
's_noise': s_noise, 'color_fix_type': color_fix_type, 'diff_dtype': diff_dtype, 'ae_dtype': ae_dtype,
'gamma_correction': gamma_correction, 'linear_CFG': linear_CFG, 'linear_s_stage2': linear_s_stage2,
'spt_linear_CFG': spt_linear_CFG, 'spt_linear_s_stage2': spt_linear_s_stage2,
'model_select': model_select}
if model_select != model.current_model:
if model_select == 'v0-Q':
print('load v0-Q')
model.load_state_dict(ckpt_Q, strict=False)
model.current_model = 'v0-Q'
elif model_select == 'v0-F':
print('load v0-F')
model.load_state_dict(ckpt_F, strict=False)
model.current_model = 'v0-F'
input_image = HWC3(input_image)
input_image = upscale_image(input_image, upscale, unit_resolution=32,
min_size=1024)
LQ = np.array(input_image)
face_helper.clean_all()
face_helper.read_image(LQ)
# get face landmarks for each face
face_helper.get_face_landmarks_5(only_center_face=False, resize=640, eye_dist_threshold=5)
face_helper.align_warp_face()
LQ = LQ / 255 * 2 - 1
LQ = torch.tensor(LQ, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(SUPIR_device)[:, :3, :, :]
if use_llava and prompt != '':
captions = eval(prompt)
else:
captions = [''] * (1 + len(face_helper.cropped_faces))
bg_caption, face_captions = captions[0], captions[1:]
model.ae_dtype = convert_dtype(ae_dtype)
model.model.dtype = convert_dtype(diff_dtype)
_faces = []
if apply_face:
faces = []
for face in face_helper.cropped_faces:
_faces.append(face)
face = np.array(face) / 255 * 2 - 1
face = torch.tensor(face, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(SUPIR_device)[:, :3, :, :]
faces.append(face)
for face, caption in zip(faces, face_captions):
caption = [caption]
from torch.nn.functional import interpolate
face = interpolate(face, size=face_resolution, mode='bilinear', align_corners=False)
if face_resolution < 1024:
face = torch.nn.functional.pad(face, (512-face_resolution//2, 512-face_resolution//2,
512-face_resolution//2, 512-face_resolution//2), 'constant', 0)
samples = model.batchify_sample(face, caption, num_steps=edm_steps, restoration_scale=s_stage1, s_churn=s_churn,
s_noise=s_noise, cfg_scale=s_cfg, control_scale=s_stage2, seed=seed,
num_samples=num_samples, p_p=a_prompt, n_p=n_prompt, color_fix_type=color_fix_type,
use_linear_CFG=linear_CFG, use_linear_control_scale=linear_s_stage2,
cfg_scale_start=spt_linear_CFG, control_scale_start=spt_linear_s_stage2)
if face_resolution < 1024:
samples = samples[:, :, 512-face_resolution//2:512+face_resolution//2,
512-face_resolution//2:512+face_resolution//2]
samples = interpolate(samples, size=face_helper.face_size, mode='bilinear', align_corners=False)
x_samples = (einops.rearrange(samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().round().clip(
0, 255).astype(np.uint8)
face_helper.add_restored_face(x_samples[0])
_faces.append(x_samples[0])
if apply_bg:
caption = [bg_caption]
samples = model.batchify_sample(LQ, caption, num_steps=edm_steps, restoration_scale=s_stage1,
s_churn=s_churn,
s_noise=s_noise, cfg_scale=s_cfg, control_scale=s_stage2, seed=seed,
num_samples=num_samples, p_p=a_prompt, n_p=n_prompt,
color_fix_type=color_fix_type,
use_linear_CFG=linear_CFG, use_linear_control_scale=linear_s_stage2,
cfg_scale_start=spt_linear_CFG, control_scale_start=spt_linear_s_stage2)
else:
samples = LQ
_bg = (einops.rearrange(samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().round().clip(
0, 255).astype(np.uint8)
face_helper.get_inverse_affine(None)
results = [face_helper.paste_faces_to_input_image(upsample_img=_bg[0])]
else:
caption = [bg_caption]
samples = model.batchify_sample(LQ, caption, num_steps=edm_steps, restoration_scale=s_stage1,
s_churn=s_churn,
s_noise=s_noise, cfg_scale=s_cfg, control_scale=s_stage2, seed=seed,
num_samples=num_samples, p_p=a_prompt, n_p=n_prompt,
color_fix_type=color_fix_type,
use_linear_CFG=linear_CFG, use_linear_control_scale=linear_s_stage2,
cfg_scale_start=spt_linear_CFG, control_scale_start=spt_linear_s_stage2)
x_samples = (einops.rearrange(samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().round().clip(
0, 255).astype(np.uint8)
results = [x_samples[0]]
if args.log_history:
os.makedirs(f'./history/{event_id[:5]}/{event_id[5:]}', exist_ok=True)
with open(f'./history/{event_id[:5]}/{event_id[5:]}/logs.txt', 'w') as f:
f.write(str(event_dict))
f.close()
Image.fromarray(input_image).save(f'./history/{event_id[:5]}/{event_id[5:]}/LQ.png')
for i, result in enumerate(results):
Image.fromarray(result).save(f'./history/{event_id[:5]}/{event_id[5:]}/HQ_{i}.png')
return [input_image] + results, event_id, 3, '', _faces
def load_and_reset(param_setting):
edm_steps = 50
s_stage2 = 1.0
s_stage1 = -1.0
s_churn = 5
s_noise = 1.003
a_prompt = 'Cinematic, High Contrast, highly detailed, taken using a Canon EOS R camera, hyper detailed photo - ' \
'realistic maximum detail, 32k, Color Grading, ultra HD, extreme meticulous detailing, skin pore ' \
'detailing, hyper sharpness, perfect without deformations.'
n_prompt = 'painting, oil painting, illustration, drawing, art, sketch, oil painting, cartoon, CG Style, ' \
'3D render, unreal engine, blurring, dirty, messy, worst quality, low quality, frames, watermark, ' \
'signature, jpeg artifacts, deformed, lowres, over-smooth'
color_fix_type = 'Wavelet'
spt_linear_s_stage2 = 0.0
linear_s_stage2 = False
linear_CFG = True
if param_setting == "Quality":
s_cfg = 7.5
spt_linear_CFG = 4.0
elif param_setting == "Fidelity":
s_cfg = 4.0
spt_linear_CFG = 1.0
else:
raise NotImplementedError
return edm_steps, s_cfg, s_stage2, s_stage1, s_churn, s_noise, a_prompt, n_prompt, color_fix_type, linear_CFG, \
linear_s_stage2, spt_linear_CFG, spt_linear_s_stage2
def submit_feedback(event_id, fb_score, fb_text):
if args.log_history:
with open(f'./history/{event_id[:5]}/{event_id[5:]}/logs.txt', 'r') as f:
event_dict = eval(f.read())
f.close()
event_dict['feedback'] = {'score': fb_score, 'text': fb_text}
with open(f'./history/{event_id[:5]}/{event_id[5:]}/logs.txt', 'w') as f:
f.write(str(event_dict))
f.close()
return 'Submit successfully, thank you for your comments!'
else:
return 'Submit failed, the server is not set to log history.'
title_md = """
# **SUPIR: Practicing Model Scaling for Photo-Realistic Image Restoration**
⚠️SUPIR is still a research project under tested and is not yet a stable commercial product.
[[Paper](https://arxiv.org/abs/2401.13627)]   [[Project Page](http://supir.xpixel.group/)]   [[How to play](https://github.com/Fanghua-Yu/SUPIR/blob/master/assets/DemoGuide.png)]
"""
claim_md = """
## **Terms of use**
By using this service, users are required to agree to the following terms: The service is a research preview intended for non-commercial use only. It only provides limited safety measures and may generate offensive content. It must not be used for any illegal, harmful, violent, racist, or sexual purposes. The service may collect user dialogue data for future research. Please submit a feedback to us if you get any inappropriate answer! We will collect those to keep improving our models. For an optimal experience, please use desktop computers for this demo, as mobile devices may compromise its quality.
## **License**
The service is a research preview intended for non-commercial use only, subject to the model [License](https://github.com/Fanghua-Yu/SUPIR) of SUPIR.
"""
block = gr.Blocks(title='SUPIR').queue()
with block:
with gr.Row():
gr.Markdown(title_md)
with gr.Row():
with gr.Column():
with gr.Row(equal_height=True):
with gr.Column():
gr.Markdown("<center>Input</center>")
input_image = gr.Image(type="numpy", elem_id="image-input", height=400, width=400)
with gr.Column():
gr.Markdown("<center>Stage1 Output</center>")
denoise_image = gr.Image(type="numpy", elem_id="image-s1", height=400, width=400)
prompt = gr.Textbox(label="Prompt", value="")
with gr.Accordion("Stage1 options", open=False):
gamma_correction = gr.Slider(label="Gamma Correction", minimum=0.1, maximum=2.0, value=1.0, step=0.1)
with gr.Accordion("LLaVA options", open=False):
temperature = gr.Slider(label="Temperature", minimum=0., maximum=1.0, value=0.2, step=0.1)
top_p = gr.Slider(label="Top P", minimum=0., maximum=1.0, value=0.7, step=0.1)
qs = gr.Textbox(label="Question", value="Describe this image and its style in a very detailed manner. "
"The image is a realistic photography, not an art painting.")
with gr.Accordion("Stage2 options", open=False):
num_samples = gr.Slider(label="Num Samples", minimum=1, maximum=4 if not args.use_image_slider else 1
, value=1, step=1)
upscale = gr.Slider(label="Upscale", minimum=1, maximum=8, value=1, step=1)
edm_steps = gr.Slider(label="Steps", minimum=20, maximum=200, value=50, step=1)
s_cfg = gr.Slider(label="Text Guidance Scale", minimum=1.0, maximum=15.0, value=7.5, step=0.1)
s_stage2 = gr.Slider(label="Stage2 Guidance Strength", minimum=0., maximum=1., value=1., step=0.05)
s_stage1 = gr.Slider(label="Stage1 Guidance Strength", minimum=-1.0, maximum=6.0, value=-1.0, step=1.0)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
s_churn = gr.Slider(label="S-Churn", minimum=0, maximum=40, value=5, step=1)
s_noise = gr.Slider(label="S-Noise", minimum=1.0, maximum=1.1, value=1.003, step=0.001)
a_prompt = gr.Textbox(label="Default Positive Prompt",
value='Cinematic, High Contrast, highly detailed, taken using a Canon EOS R '
'camera, hyper detailed photo - realistic maximum detail, 32k, Color '
'Grading, ultra HD, extreme meticulous detailing, skin pore detailing, '
'hyper sharpness, perfect without deformations.')
n_prompt = gr.Textbox(label="Default Negative Prompt",
value='painting, oil painting, illustration, drawing, art, sketch, oil painting, '
'cartoon, CG Style, 3D render, unreal engine, blurring, dirty, messy, '
'worst quality, low quality, frames, watermark, signature, jpeg artifacts, '
'deformed, lowres, over-smooth')
with gr.Row():
with gr.Column():
linear_CFG = gr.Checkbox(label="Linear CFG", value=True)
spt_linear_CFG = gr.Slider(label="CFG Start", minimum=1.0,
maximum=9.0, value=4.0, step=0.5)
with gr.Column():
linear_s_stage2 = gr.Checkbox(label="Linear Stage2 Guidance", value=False)
spt_linear_s_stage2 = gr.Slider(label="Guidance Start", minimum=0.,
maximum=1., value=0., step=0.05)
with gr.Row():
with gr.Column():
diff_dtype = gr.Radio(['fp32', 'fp16', 'bf16'], label="Diffusion Data Type", value="fp16",
interactive=True)
with gr.Column():
ae_dtype = gr.Radio(['fp32', 'bf16'], label="Auto-Encoder Data Type", value="bf16",
interactive=True)
with gr.Column():
color_fix_type = gr.Radio(["None", "AdaIn", "Wavelet"], label="Color-Fix Type", value="Wavelet",
interactive=True)
with gr.Column():
model_select = gr.Radio(["v0-Q", "v0-F"], label="Model Selection", value="v0-Q",
interactive=True)
with gr.Column():
gr.Markdown("<center>Stage2 Output</center>")
if not args.use_image_slider:
result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery1")
else:
result_gallery = ImageSlider(label='Output', show_label=False, elem_id="gallery1")
with gr.Row():
with gr.Column():
denoise_button = gr.Button(value="Stage1 Run")
with gr.Column():
llave_button = gr.Button(value="LlaVa Run")
with gr.Column():
diffusion_button = gr.Button(value="Stage2 Run")
with gr.Row():
with gr.Column():
param_setting = gr.Dropdown(["Quality", "Fidelity"], interactive=True, label="Param Setting",
value="Quality")
with gr.Column():
restart_button = gr.Button(value="Reset Param", scale=2)
with gr.Accordion("Face Options", open=True):
face_resolution = gr.Slider(label="Text Guidance Scale", minimum=256, maximum=2048, value=1024, step=32)
with gr.Row():
with gr.Column():
apply_bg = gr.Checkbox(label="BG restoration", value=True)
with gr.Column():
apply_face = gr.Checkbox(label="Face restoration", value=True)
with gr.Accordion("Feedback", open=False):
fb_score = gr.Slider(label="Feedback Score", minimum=1, maximum=5, value=3, step=1,
interactive=True)
fb_text = gr.Textbox(label="Feedback Text", value="", placeholder='Please enter your feedback here.')
submit_button = gr.Button(value="Submit Feedback")
face_gallery = gr.Gallery(label='Faces', show_label=False, elem_id="gallery2")
with gr.Row():
gr.Markdown(claim_md)
event_id = gr.Textbox(label="Event ID", value="", visible=False)
llave_button.click(fn=llave_process, inputs=[input_image, upscale, temperature, top_p, qs], outputs=[prompt, face_gallery])
denoise_button.click(fn=stage1_process, inputs=[input_image, gamma_correction],
outputs=[denoise_image])
stage2_ips = [input_image, prompt, a_prompt, n_prompt, num_samples, upscale, edm_steps, s_stage1, s_stage2,
s_cfg, seed, s_churn, s_noise, color_fix_type, diff_dtype, ae_dtype, gamma_correction,
linear_CFG, linear_s_stage2, spt_linear_CFG, spt_linear_s_stage2, model_select, face_resolution, apply_bg, apply_face]
diffusion_button.click(fn=stage2_process, inputs=stage2_ips, outputs=[result_gallery, event_id, fb_score, fb_text, face_gallery])
restart_button.click(fn=load_and_reset, inputs=[param_setting],
outputs=[edm_steps, s_cfg, s_stage2, s_stage1, s_churn, s_noise, a_prompt, n_prompt,
color_fix_type, linear_CFG, linear_s_stage2, spt_linear_CFG, spt_linear_s_stage2])
submit_button.click(fn=submit_feedback, inputs=[event_id, fb_score, fb_text], outputs=[fb_text])
block.launch(server_name=server_ip, server_port=server_port)