Spaces:
Runtime error
Runtime error
File size: 15,834 Bytes
b3478e4 cd9ed02 b3478e4 fb6c2da b3478e4 fb6c2da b3478e4 fb6c2da 547889c b3478e4 547889c b3478e4 0817ca0 b3478e4 fb6c2da b3478e4 8d1725b b3478e4 fb6c2da b3478e4 8b3dbc5 fb6c2da b3478e4 fb6c2da b3478e4 a892d67 b3478e4 a892d67 b3478e4 fb6c2da b3478e4 fb6c2da b3478e4 fb6c2da b3478e4 2aa90ca b3478e4 2aa90ca b3478e4 fb6c2da b3478e4 0817ca0 b3478e4 4d64269 8b3dbc5 4d64269 8b3dbc5 4d64269 547889c |
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 |
# demo inspired by https://huggingface.co/spaces/lambdalabs/image-mixer-demo
import argparse
import copy
import os
import shlex
import subprocess
from functools import partial
from itertools import chain
import cv2
import gradio as gr
import torch
from basicsr.utils import tensor2img
from huggingface_hub import hf_hub_url
from pytorch_lightning import seed_everything
from torch import autocast
from ldm.inference_base import (DEFAULT_NEGATIVE_PROMPT, diffusion_inference, get_adapters, get_sd_models)
from ldm.modules.extra_condition import api
from ldm.modules.extra_condition.api import (ExtraCondition, get_adapter_feature, get_cond_model)
torch.set_grad_enabled(False)
supported_cond = ['style', 'color', 'sketch', 'openpose', 'depth', 'canny']
# download the checkpoints
urls = {
'TencentARC/T2I-Adapter': [
'models/t2iadapter_keypose_sd14v1.pth', 'models/t2iadapter_color_sd14v1.pth',
'models/t2iadapter_openpose_sd14v1.pth', 'models/t2iadapter_seg_sd14v1.pth',
'models/t2iadapter_sketch_sd14v1.pth', 'models/t2iadapter_depth_sd14v1.pth',
'third-party-models/body_pose_model.pth', "models/t2iadapter_style_sd14v1.pth",
"models/t2iadapter_canny_sd14v1.pth", 'third-party-models/table5_pidinet.pth'
],
'runwayml/stable-diffusion-v1-5': ['v1-5-pruned-emaonly.ckpt'],
'andite/anything-v4.0': ['anything-v4.0-pruned.ckpt', 'anything-v4.0.vae.pt'],
}
# download image samples
torch.hub.download_url_to_file(
'https://user-images.githubusercontent.com/52127135/223114920-cae3e723-3683-424a-bebc-0875479f2409.jpg',
'cyber_style.jpg')
torch.hub.download_url_to_file(
'https://user-images.githubusercontent.com/52127135/223114946-6ccc127f-cb58-443e-8677-805f5dbaf6f1.png',
'sword.png')
torch.hub.download_url_to_file(
'https://user-images.githubusercontent.com/52127135/223121793-20c2ac6a-5a4f-4ff8-88ea-6d007a7959dd.png',
'white.png')
torch.hub.download_url_to_file(
'https://user-images.githubusercontent.com/52127135/223127404-4a3748cf-85a6-40f3-af31-a74e206db96e.jpeg',
'scream_style.jpeg')
torch.hub.download_url_to_file(
'https://user-images.githubusercontent.com/52127135/223127433-8768913f-9872-4d24-b883-a19a3eb20623.jpg',
'motorcycle.jpg')
if os.path.exists('models') == False:
os.mkdir('models')
for repo in urls:
files = urls[repo]
for file in files:
url = hf_hub_url(repo, file)
name_ckp = url.split('/')[-1]
save_path = os.path.join('models', name_ckp)
if os.path.exists(save_path) == False:
subprocess.run(shlex.split(f'wget {url} -O {save_path}'))
# config
parser = argparse.ArgumentParser()
parser.add_argument(
'--sd_ckpt',
type=str,
default='models/v1-5-pruned-emaonly.ckpt',
help='path to checkpoint of stable diffusion model, both .ckpt and .safetensor are supported',
)
parser.add_argument(
'--vae_ckpt',
type=str,
default=None,
help='vae checkpoint, anime SD models usually have seperate vae ckpt that need to be loaded',
)
global_opt = parser.parse_args()
global_opt.config = 'configs/stable-diffusion/sd-v1-inference.yaml'
for cond_name in supported_cond:
setattr(global_opt, f'{cond_name}_adapter_ckpt', f'models/t2iadapter_{cond_name}_sd14v1.pth')
global_opt.device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
global_opt.max_resolution = 512 * 512
global_opt.sampler = 'ddim'
global_opt.cond_weight = 1.0
global_opt.C = 4
global_opt.f = 8
# stable-diffusion model
sd_model, sampler = get_sd_models(global_opt)
# adapters and models to processing condition inputs
adapters = {}
cond_models = {}
torch.cuda.empty_cache()
def run(*args):
with torch.inference_mode(), \
sd_model.ema_scope(), \
autocast('cuda'):
inps = []
for i in range(0, len(args) - 8, len(supported_cond)):
inps.append(args[i:i + len(supported_cond)])
opt = copy.deepcopy(global_opt)
opt.prompt, opt.neg_prompt, opt.scale, opt.n_samples, opt.seed, opt.steps, opt.resize_short_edge, opt.cond_tau \
= args[-8:]
conds = []
activated_conds = []
ims1 = []
ims2 = []
for idx, (b, im1, im2, cond_weight) in enumerate(zip(*inps)):
if idx > 1:
if b != 'Nothing' and (im1 is not None or im2 is not None):
if im1 is not None:
h, w, _ = im1.shape
else:
h, w, _ = im2.shape
break
# resize all the images to the same size
for idx, (b, im1, im2, cond_weight) in enumerate(zip(*inps)):
if idx == 0:
ims1.append(im1)
ims2.append(im2)
continue
if b != 'Nothing':
if im1 is not None:
im1 = cv2.resize(im1, (w, h), interpolation=cv2.INTER_CUBIC)
if im2 is not None:
im2 = cv2.resize(im2, (w, h), interpolation=cv2.INTER_CUBIC)
ims1.append(im1)
ims2.append(im2)
for idx, (b, _, _, cond_weight) in enumerate(zip(*inps)):
cond_name = supported_cond[idx]
if b == 'Nothing':
if cond_name in adapters:
adapters[cond_name]['model'] = adapters[cond_name]['model'].cpu()
else:
activated_conds.append(cond_name)
if cond_name in adapters:
adapters[cond_name]['model'] = adapters[cond_name]['model'].to(opt.device)
else:
adapters[cond_name] = get_adapters(opt, getattr(ExtraCondition, cond_name))
adapters[cond_name]['cond_weight'] = cond_weight
process_cond_module = getattr(api, f'get_cond_{cond_name}')
if b == 'Image':
if cond_name not in cond_models:
cond_models[cond_name] = get_cond_model(opt, getattr(ExtraCondition, cond_name))
conds.append(process_cond_module(opt, ims1[idx], 'image', cond_models[cond_name]))
else:
conds.append(process_cond_module(opt, ims2[idx], cond_name, None))
adapter_features, append_to_context = get_adapter_feature(
conds, [adapters[cond_name] for cond_name in activated_conds])
output_conds = []
for cond in conds:
output_conds.append(tensor2img(cond, rgb2bgr=False))
ims = []
seed_everything(opt.seed)
for _ in range(opt.n_samples):
result = diffusion_inference(opt, sd_model, sampler, adapter_features, append_to_context)
ims.append(tensor2img(result, rgb2bgr=False))
# Clear GPU memory cache so less likely to OOM
torch.cuda.empty_cache()
return ims, output_conds
def change_visible(im1, im2, val):
outputs = {}
if val == "Image":
outputs[im1] = gr.update(visible=True)
outputs[im2] = gr.update(visible=False)
elif val == "Nothing":
outputs[im1] = gr.update(visible=False)
outputs[im2] = gr.update(visible=False)
else:
outputs[im1] = gr.update(visible=False)
outputs[im2] = gr.update(visible=True)
return outputs
DESCRIPTION = '# [Composable T2I-Adapter](https://github.com/TencentARC/T2I-Adapter)'
DESCRIPTION += f'<p>Gradio demo for **T2I-Adapter**: [[GitHub]](https://github.com/TencentARC/T2I-Adapter), [[Paper]](https://arxiv.org/abs/2302.08453). If T2I-Adapter is helpful, please help to ⭐ the [Github Repo](https://github.com/TencentARC/T2I-Adapter) and recommend it to your friends 😊 </p>'
DESCRIPTION += f'<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/Adapter/T2I-Adapter?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a></p>'
with gr.Blocks(css='style.css') as demo:
gr.Markdown(DESCRIPTION)
btns = []
ims1 = []
ims2 = []
cond_weights = []
with gr.Row():
with gr.Column(scale=1.9):
with gr.Box():
gr.Markdown("<h5><center>Style & Color</center></h5>")
with gr.Row():
for cond_name in supported_cond[:2]:
with gr.Box():
with gr.Column():
if cond_name == 'style':
btn1 = gr.Radio(
choices=["Image", "Nothing"],
label=f"Input type for {cond_name}",
interactive=True,
value="Nothing",
)
else:
btn1 = gr.Radio(
choices=["Image", cond_name, "Nothing"],
label=f"Input type for {cond_name}",
interactive=True,
value="Nothing",
)
im1 = gr.Image(
source='upload', label="Image", interactive=True, visible=False, type="numpy")
im2 = gr.Image(
source='upload', label=cond_name, interactive=True, visible=False, type="numpy")
cond_weight = gr.Slider(
label="Condition weight",
minimum=0,
maximum=5,
step=0.05,
value=1,
interactive=True)
fn = partial(change_visible, im1, im2)
btn1.change(fn=fn, inputs=[btn1], outputs=[im1, im2], queue=False)
btns.append(btn1)
ims1.append(im1)
ims2.append(im2)
cond_weights.append(cond_weight)
with gr.Column(scale=4):
with gr.Box():
gr.Markdown("<h5><center>Structure</center></h5>")
with gr.Row():
for cond_name in supported_cond[2:6]:
with gr.Box():
with gr.Column():
if cond_name == 'openpose':
btn1 = gr.Radio(
choices=["Image", 'pose', "Nothing"],
label=f"Input type for {cond_name}",
interactive=True,
value="Nothing",
)
else:
btn1 = gr.Radio(
choices=["Image", cond_name, "Nothing"],
label=f"Input type for {cond_name}",
interactive=True,
value="Nothing",
)
im1 = gr.Image(
source='upload', label="Image", interactive=True, visible=False, type="numpy")
im2 = gr.Image(
source='upload', label=cond_name, interactive=True, visible=False, type="numpy")
cond_weight = gr.Slider(
label="Condition weight",
minimum=0,
maximum=5,
step=0.05,
value=1,
interactive=True)
fn = partial(change_visible, im1, im2)
btn1.change(fn=fn, inputs=[btn1], outputs=[im1, im2], queue=False)
btns.append(btn1)
ims1.append(im1)
ims2.append(im2)
cond_weights.append(cond_weight)
with gr.Column():
prompt = gr.Textbox(label="Prompt")
with gr.Accordion('Advanced options', open=False):
neg_prompt = gr.Textbox(label="Negative Prompt", value=DEFAULT_NEGATIVE_PROMPT)
scale = gr.Slider(
label="Guidance Scale (Classifier free guidance)", value=7.5, minimum=1, maximum=20, step=0.1)
n_samples = gr.Slider(label="Num samples", value=1, minimum=1, maximum=1, step=1)
seed = gr.Slider(label="Seed", value=42, minimum=0, maximum=10000, step=1, randomize=True)
steps = gr.Slider(label="Steps", value=50, minimum=10, maximum=100, step=1)
resize_short_edge = gr.Slider(label="Image resolution", value=512, minimum=320, maximum=1024, step=1)
cond_tau = gr.Slider(
label="timestamp parameter that determines until which step the adapter is applied",
value=1.0,
minimum=0.1,
maximum=1.0,
step=0.05)
with gr.Row():
submit = gr.Button("Generate")
output = gr.Gallery().style(grid=2, height='auto')
cond = gr.Gallery().style(grid=2, height='auto')
inps = list(chain(btns, ims1, ims2, cond_weights))
inps.extend([prompt, neg_prompt, scale, n_samples, seed, steps, resize_short_edge, cond_tau])
submit.click(fn=run, inputs=inps, outputs=[output, cond])
ex = gr.Examples([
[
"Image",
"Nothing",
"Image",
"Nothing",
"Nothing",
"Nothing",
"cyber_style.jpg",
"white.png",
"sword.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
1,
1,
1,
1,
1,
1,
"master sword",
"longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
7.5,
1,
2500,
50,
512,
1,
],
[
"Image",
"Nothing",
"Image",
"Nothing",
"Nothing",
"Nothing",
"scream_style.jpeg",
"white.png",
"motorcycle.jpg",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
"white.png",
1,
1,
1,
1,
1,
1,
"motorcycle",
"longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
7.5,
1,
2500,
50,
512,
1,
],
],
fn=run,
inputs=inps,
outputs=[output, cond],
cache_examples=True)
demo.queue().launch(debug=True, server_name='0.0.0.0')
|