Spaces:
Sleeping
Sleeping
File size: 24,320 Bytes
0f61c4d bf48e0b 0f61c4d 966167e 0f61c4d 966167e 93f708e bf48e0b 0f61c4d bf48e0b 94ba4d8 cde0b82 f64d69b 0f61c4d aea387e cde0b82 2ade25e cde0b82 0a8222c cde0b82 0f61c4d 1781379 0a8222c 0f61c4d 0a8222c 0f61c4d 0a8222c 0f61c4d 93f708e 08f7d1b 0f61c4d 3a5dd2f 0f61c4d fddbcc2 0f61c4d fddbcc2 0f61c4d fddbcc2 0f61c4d f9238f7 0f61c4d f9238f7 0f61c4d 2af8ebe b3b16a3 5d34271 08f7d1b 2af8ebe 0f61c4d 2af8ebe 0f61c4d 2af8ebe 0f61c4d 2af8ebe 0f61c4d 2af8ebe f7ea271 2af8ebe 0f61c4d 2af8ebe 0f61c4d 2af8ebe f7ea271 2af8ebe f7ea271 9e4dc36 0f61c4d a1ce13a 08f7d1b a1ce13a 0a8222c 8b08967 a1ce13a 0a8222c a1ce13a ea0bceb 586de43 a1ce13a 586de43 a1ce13a ea0bceb a1ce13a 401dece a1ce13a 401dece a1ce13a ea0bceb a1ce13a 0f61c4d 4373d44 0f61c4d 08f7d1b 0f61c4d f9238f7 57a3c2d 0f61c4d e71f8a4 d147789 e71f8a4 08f7d1b 0f61c4d 7585c5c 60ba9a9 1a239a6 0f61c4d f5f6fef 4373d44 0f61c4d 5695ac1 57a3c2d 4373d44 7585c5c 0f61c4d f5f6fef 5d34271 0f61c4d d147789 cbddee5 0f61c4d f9238f7 cbddee5 4373d44 f9238f7 4373d44 cbddee5 f9238f7 cbddee5 0f61c4d d147789 0f61c4d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 |
import os
import re
import zipfile
import torch
import gradio as gr
import time
from transformers import CLIPTextModel, CLIPTokenizer
from diffusers import AutoencoderKL, DDPMScheduler, StableDiffusionPipeline, UNet2DConditionModel, DiffusionPipeline, LCMScheduler
from tqdm import tqdm
from PIL import Image
from PIL import Image, ImageDraw, ImageFont
import random
import copy
import string
alphabet = string.digits + string.ascii_lowercase + string.ascii_uppercase + string.punctuation + ' ' # len(aphabet) = 95
'''alphabet
0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~
'''
if not os.path.exists('images2'):
os.system('wget https://huggingface.co/datasets/JingyeChen22/TextDiffuser/resolve/main/images2.zip')
with zipfile.ZipFile('images2.zip', 'r') as zip_ref:
zip_ref.extractall('.')
os.system('nvidia-smi')
os.system('ls')
#### import m1
from fastchat.model import load_model, get_conversation_template
from transformers import AutoTokenizer, AutoModelForCausalLM
m1_model_path = 'JingyeChen22/textdiffuser2_layout_planner'
# m1_model, m1_tokenizer = load_model(
# m1_model_path,
# 'cuda',
# 1,
# None,
# False,
# False,
# revision="main",
# debug=False,
# )
m1_tokenizer = AutoTokenizer.from_pretrained(m1_model_path, use_fast=False)
m1_model = AutoModelForCausalLM.from_pretrained(
m1_model_path, torch_dtype=torch.float16, low_cpu_mem_usage=True
).cuda()
#### import diffusion models
text_encoder = CLIPTextModel.from_pretrained(
'JingyeChen22/textdiffuser2-full-ft', subfolder="text_encoder"
).cuda().half()
tokenizer = CLIPTokenizer.from_pretrained(
'runwayml/stable-diffusion-v1-5', subfolder="tokenizer"
)
#### additional tokens are introduced, including coordinate tokens and character tokens
print('***************')
print(len(tokenizer))
for i in range(520):
tokenizer.add_tokens(['l' + str(i) ]) # left
tokenizer.add_tokens(['t' + str(i) ]) # top
tokenizer.add_tokens(['r' + str(i) ]) # width
tokenizer.add_tokens(['b' + str(i) ]) # height
for c in alphabet:
tokenizer.add_tokens([f'[{c}]'])
print(len(tokenizer))
print('***************')
vae = AutoencoderKL.from_pretrained('runwayml/stable-diffusion-v1-5', subfolder="vae").half().cuda()
unet = UNet2DConditionModel.from_pretrained(
'JingyeChen22/textdiffuser2-full-ft', subfolder="unet"
).half().cuda()
text_encoder.resize_token_embeddings(len(tokenizer))
#### load lcm components
model_id = "lambdalabs/sd-pokemon-diffusers"
lcm_lora_id = "latent-consistency/lcm-lora-sdv1-5"
pipe = DiffusionPipeline.from_pretrained(model_id, unet=copy.deepcopy(unet), tokenizer=tokenizer, text_encoder=copy.deepcopy(text_encoder), torch_dtype=torch.float16)
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights(lcm_lora_id)
pipe.to(device="cuda")
#### for interactive
stack = []
state = 0
font = ImageFont.truetype("./Arial.ttf", 32)
def skip_fun(i, t):
global state
state = 0
def exe_undo(i, t):
global stack
global state
state = 0
stack = []
image = Image.open(f'./gray256.jpg')
print('stack', stack)
return image
def exe_redo(i, t):
global state
state = 0
if len(stack) > 0:
stack.pop()
image = Image.open(f'./gray256.jpg')
draw = ImageDraw.Draw(image)
for items in stack:
# print('now', items)
text_position, t = items
if len(text_position) == 2:
x, y = text_position
text_color = (255, 0, 0)
draw.text((x+2, y), t, font=font, fill=text_color)
r = 4
leftUpPoint = (x-r, y-r)
rightDownPoint = (x+r, y+r)
draw.ellipse((leftUpPoint,rightDownPoint), fill='red')
elif len(text_position) == 4:
x0, y0, x1, y1 = text_position
text_color = (255, 0, 0)
draw.text((x0+2, y0), t, font=font, fill=text_color)
r = 4
leftUpPoint = (x0-r, y0-r)
rightDownPoint = (x0+r, y0+r)
draw.ellipse((leftUpPoint,rightDownPoint), fill='red')
draw.rectangle((x0,y0,x1,y1), outline=(255, 0, 0) )
print('stack', stack)
return image
def get_pixels(i, t, evt: gr.SelectData):
global state
text_position = evt.index
if state == 0:
stack.append(
(text_position, t)
)
print(text_position, stack)
state = 1
else:
(_, t) = stack.pop()
x, y = _
stack.append(
((x,y,text_position[0],text_position[1]), t)
)
state = 0
image = Image.open(f'./gray256.jpg')
draw = ImageDraw.Draw(image)
for items in stack:
# print('now', items)
text_position, t = items
if len(text_position) == 2:
x, y = text_position
text_color = (255, 0, 0)
draw.text((x+2, y), t, font=font, fill=text_color)
r = 4
leftUpPoint = (x-r, y-r)
rightDownPoint = (x+r, y+r)
draw.ellipse((leftUpPoint,rightDownPoint), fill='red')
elif len(text_position) == 4:
x0, y0, x1, y1 = text_position
text_color = (255, 0, 0)
draw.text((x0+2, y0), t, font=font, fill=text_color)
r = 4
leftUpPoint = (x0-r, y0-r)
rightDownPoint = (x0+r, y0+r)
draw.ellipse((leftUpPoint,rightDownPoint), fill='red')
draw.rectangle((x0,y0,x1,y1), outline=(255, 0, 0) )
print('stack', stack)
return image
def text_to_image(prompt,keywords,positive_prompt,radio,slider_step,slider_guidance,slider_batch,slider_temperature,slider_natural):
global stack
global state
if len(positive_prompt.strip()) != 0:
prompt += positive_prompt
with torch.no_grad():
time1 = time.time()
user_prompt = prompt
if slider_natural:
user_prompt = f'{user_prompt}'
composed_prompt = user_prompt
prompt = tokenizer.encode(user_prompt)
else:
if len(stack) == 0:
if len(keywords.strip()) == 0:
template = f'Given a prompt that will be used to generate an image, plan the layout of visual text for the image. The size of the image is 128x128. Therefore, all properties of the positions should not exceed 128, including the coordinates of top, left, right, and bottom. All keywords are included in the caption. You dont need to specify the details of font styles. At each line, the format should be keyword left, top, right, bottom. So let us begin. Prompt: {user_prompt}'
else:
keywords = keywords.split('/')
keywords = [i.strip() for i in keywords]
template = f'Given a prompt that will be used to generate an image, plan the layout of visual text for the image. The size of the image is 128x128. Therefore, all properties of the positions should not exceed 128, including the coordinates of top, left, right, and bottom. In addition, we also provide all keywords at random order for reference. You dont need to specify the details of font styles. At each line, the format should be keyword left, top, right, bottom. So let us begin. Prompt: {prompt}. Keywords: {str(keywords)}'
msg = template
conv = get_conversation_template(m1_model_path)
conv.append_message(conv.roles[0], msg)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
inputs = m1_tokenizer([prompt], return_token_type_ids=False)
inputs = {k: torch.tensor(v).to('cuda') for k, v in inputs.items()}
output_ids = m1_model.generate(
**inputs,
do_sample=True,
temperature=slider_temperature,
repetition_penalty=1.0,
max_new_tokens=512,
)
if m1_model.config.is_encoder_decoder:
output_ids = output_ids[0]
else:
output_ids = output_ids[0][len(inputs["input_ids"][0]) :]
outputs = m1_tokenizer.decode(
output_ids, skip_special_tokens=True, spaces_between_special_tokens=False
)
print(f"[{conv.roles[0]}]\n{msg}")
print(f"[{conv.roles[1]}]\n{outputs}")
ocrs = outputs.split('\n')
time2 = time.time()
print(time2-time1)
# user_prompt = prompt
current_ocr = ocrs
ocr_ids = []
print('user_prompt', user_prompt)
print('current_ocr', current_ocr)
for ocr in current_ocr:
ocr = ocr.strip()
if len(ocr) == 0 or '###' in ocr or '.com' in ocr:
continue
items = ocr.split()
pred = ' '.join(items[:-1])
box = items[-1]
l,t,r,b = box.split(',')
l,t,r,b = int(l), int(t), int(r), int(b)
ocr_ids.extend(['l'+str(l), 't'+str(t), 'r'+str(r), 'b'+str(b)])
char_list = list(pred)
char_list = [f'[{i}]' for i in char_list]
ocr_ids.extend(char_list)
ocr_ids.append(tokenizer.eos_token_id)
caption_ids = tokenizer(
user_prompt, truncation=True, return_tensors="pt"
).input_ids[0].tolist()
try:
ocr_ids = tokenizer.encode(ocr_ids)
prompt = caption_ids + ocr_ids
except:
prompt = caption_ids
user_prompt = tokenizer.decode(prompt)
composed_prompt = tokenizer.decode(prompt)
else:
user_prompt += ' <|endoftext|>'
for items in stack:
position, text = items
if len(position) == 2:
x, y = position
x = x // 4
y = y // 4
text_str = ' '.join([f'[{c}]' for c in list(text)])
user_prompt += f'<|startoftext|> l{x} t{y} {text_str} <|endoftext|>'
elif len(position) == 4:
x0, y0, x1, y1 = position
x0 = x0 // 4
y0 = y0 // 4
x1 = x1 // 4
y1 = y1 // 4
text_str = ' '.join([f'[{c}]' for c in list(text)])
user_prompt += f'<|startoftext|> l{x0} t{y0} r{x1} b{y1} {text_str} <|endoftext|>'
# composed_prompt = user_prompt
prompt = tokenizer.encode(user_prompt)
composed_prompt = tokenizer.decode(prompt)
prompt = prompt[:77]
while len(prompt) < 77:
prompt.append(tokenizer.pad_token_id)
if radio == 'TextDiffuser-2':
prompts_cond = prompt
prompts_nocond = [tokenizer.pad_token_id]*77
prompts_cond = [prompts_cond] * slider_batch
prompts_nocond = [prompts_nocond] * slider_batch
prompts_cond = torch.Tensor(prompts_cond).long().cuda()
prompts_nocond = torch.Tensor(prompts_nocond).long().cuda()
scheduler = DDPMScheduler.from_pretrained('runwayml/stable-diffusion-v1-5', subfolder="scheduler")
scheduler.set_timesteps(slider_step)
noise = torch.randn((slider_batch, 4, 64, 64)).to("cuda").half()
input = noise
encoder_hidden_states_cond = text_encoder(prompts_cond)[0].half()
encoder_hidden_states_nocond = text_encoder(prompts_nocond)[0].half()
for t in tqdm(scheduler.timesteps):
with torch.no_grad(): # classifier free guidance
noise_pred_cond = unet(sample=input, timestep=t, encoder_hidden_states=encoder_hidden_states_cond[:slider_batch]).sample # b, 4, 64, 64
noise_pred_uncond = unet(sample=input, timestep=t, encoder_hidden_states=encoder_hidden_states_nocond[:slider_batch]).sample # b, 4, 64, 64
noisy_residual = noise_pred_uncond + slider_guidance * (noise_pred_cond - noise_pred_uncond) # b, 4, 64, 64
input = scheduler.step(noisy_residual, t, input).prev_sample
del noise_pred_cond
del noise_pred_uncond
torch.cuda.empty_cache()
# decode
input = 1 / vae.config.scaling_factor * input
images = vae.decode(input, return_dict=False)[0]
width, height = 512, 512
results = []
new_image = Image.new('RGB', (2*width, 2*height))
for index, image in enumerate(images.cpu().float()):
image = (image / 2 + 0.5).clamp(0, 1).unsqueeze(0)
image = image.cpu().permute(0, 2, 3, 1).numpy()[0]
image = Image.fromarray((image * 255).round().astype("uint8")).convert('RGB')
results.append(image)
row = index // 2
col = index % 2
new_image.paste(image, (col*width, row*height))
os.system('nvidia-smi')
torch.cuda.empty_cache()
os.system('nvidia-smi')
return tuple(results), composed_prompt
elif radio == 'TextDiffuser-2-LCM':
generator = torch.Generator(device=pipe.device).manual_seed(random.randint(0,1000))
image = pipe(
prompt=user_prompt,
generator=generator,
# negative_prompt=negative_prompt,
num_inference_steps=slider_step,
guidance_scale=1,
# num_images_per_prompt=slider_batch,
).images
os.system('nvidia-smi')
torch.cuda.empty_cache()
os.system('nvidia-smi')
return tuple(image), composed_prompt
with gr.Blocks() as demo:
gr.HTML(
"""
<div style="text-align: center; max-width: 1600px; margin: 20px auto;">
<h2 style="font-weight: 900; font-size: 2.3rem; margin: 0rem">
TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering
</h2>
<h2 style="font-weight: 460; font-size: 1.1rem; margin: 0rem">
<a href="https://jingyechen.github.io/">Jingye Chen</a>, <a href="https://hypjudy.github.io/website/">Yupan Huang</a>, <a href="https://scholar.google.com/citations?user=0LTZGhUAAAAJ&hl=en">Tengchao Lv</a>, <a href="https://www.microsoft.com/en-us/research/people/lecu/">Lei Cui</a>, <a href="https://cqf.io/">Qifeng Chen</a>, <a href="https://thegenerality.com/">Furu Wei</a>
</h2>
<h2 style="font-weight: 460; font-size: 1.1rem; margin: 0rem">
HKUST, Sun Yat-sen University, Microsoft Research
</h2>
<h3 style="font-weight: 450; font-size: 1rem; margin: 0rem">
[<a href="https://arxiv.org/abs/2311.16465" style="color:blue;">arXiv</a>]
[<a href="https://github.com/microsoft/unilm/tree/master/textdiffuser-2" style="color:blue;">Code</a>]
</h3>
<h2 style="text-align: left; font-weight: 450; font-size: 1rem; margin-top: 0.5rem; margin-bottom: 0.5rem">
We propose <b>TextDiffuser-2</b>, aiming at unleashing the power of language models for text rendering. Specifically, we <b>tame a language model into a layout planner</b> to transform user prompt into a layout using the caption-OCR pairs. The language model demonstrates flexibility and automation by inferring keywords from user prompts or incorporating user-specified keywords to determine their positions. Secondly, we <b>leverage the language model in the diffusion model as the layout encoder</b> to represent the position and content of text at the line level. This approach enables diffusion models to generate text images with broader diversity.
</h2>
<h2 style="text-align: left; font-weight: 450; font-size: 1rem; margin-top: 0.5rem; margin-bottom: 0.5rem">
👀 <b>Tips for using this demo</b>: <b>(1)</b> Please carefully read the disclaimer in the below. <b>(2)</b> The specification of keywords is optional. If provided, the language model will do its best to plan layouts using the given keywords. <b>(3)</b> If a template is given, the layout planner (M1) is not used. <b>(4)</b> Three operations, including redo, undo, and skip are provided. When using skip, only the left-top point of a keyword will be recorded, resulting in more diversity but sometimes decreasing the accuracy. <b>(5)</b> The layout planner can produce different layouts. You can increase the temperature to enhance the diversity. ✨ <b>(6)</b> We also provide the experimental demo combining <b>TextDiffuser-2</b> and <b>LCM</b>. The inference is fast using less sampling steps, although the precision in text rendering might decrease.
</h2>
<style>
.scaled-image {
transform: scale(1);
}
</style>
<img src="https://i.ibb.co/56JVg5j/architecture.jpg" alt="textdiffuser-2" class="scaled-image">
</div>
""")
with gr.Tab("Text-to-Image"):
with gr.Row():
with gr.Column(scale=1):
prompt = gr.Textbox(label="Prompt. You can let language model automatically identify keywords, or provide them below", placeholder="A beautiful city skyline stamp of Shanghai")
keywords = gr.Textbox(label="(Optional) Keywords. Should be seperated by / (e.g., keyword1/keyword2/...)", placeholder="keyword1/keyword2")
positive_prompt = gr.Textbox(label="(Optional) Positive prompt", value=", showing different kinds of quails, digital art, very detailed, fantasy, high definition, cinematic light, dnd, trending on artstation")
with gr.Accordion("(Optional) Template - Click to paint", open=False):
with gr.Row():
with gr.Column(scale=1):
i = gr.Image(label="Canvas", type='filepath', value=f'./gray256.jpg', height=256, width=256)
with gr.Column(scale=1):
t = gr.Textbox(label="Keyword", value='input_keyword')
redo = gr.Button(value='Redo - Cancel the last keyword')
undo = gr.Button(value='Undo - Clear the canvas')
skip_button = gr.Button(value='Skip - Operate next keyword')
i.select(get_pixels,[i,t],[i])
redo.click(exe_redo, [i,t],[i])
undo.click(exe_undo, [i,t],[i])
skip_button.click(skip_fun, [i,t])
radio = gr.Radio(["TextDiffuser-2", "TextDiffuser-2-LCM"], label="Choice of models", value="TextDiffuser-2")
slider_step = gr.Slider(minimum=1, maximum=50, value=20, step=1, label="Sampling step", info="The sampling step for TextDiffuser-2. You may decease the step to 4 when using LCM.")
slider_guidance = gr.Slider(minimum=1, maximum=13, value=7.5, step=0.5, label="Scale of classifier-free guidance", info="The scale of cfg and is set to 7.5 in default. When using LCM, cfg is set to 1.")
slider_batch = gr.Slider(minimum=1, maximum=6, value=4, step=1, label="Batch size", info="The number of images to be sampled.")
slider_temperature = gr.Slider(minimum=0.1, maximum=2, value=0.7, step=0.1, label="Temperature", info="Control the diversity of layout planner. Higher value indicates more diversity.")
slider_natural = gr.Checkbox(label="Natural image generation", value=False, info="The text position and content info will not be incorporated.")
# slider_seed = gr.Slider(minimum=1, maximum=10000, label="Seed", randomize=True)
button = gr.Button("Generate")
with gr.Column(scale=1):
output = gr.Gallery(label='Generated image')
with gr.Accordion("Intermediate results", open=False):
gr.Markdown("Composed prompt")
composed_prompt = gr.Textbox(label='')
button.click(text_to_image, inputs=[prompt,keywords,positive_prompt, radio,slider_step,slider_guidance,slider_batch,slider_temperature,slider_natural], outputs=[output, composed_prompt])
gr.Markdown("## Prompt Examples")
gr.Examples(
[
["A beautiful city skyline stamp of Shanghai", "", False],
["A logo of superman", "", False],
["A pencil sketch of a tree with the title nothing to tree here", "", False],
["handwritten signature of peter", "", False],
["Delicate greeting card of happy birthday to xyz", "", False],
["Book cover of good morning baby ", "", False],
["The handwritten words Hello World displayed on a wall in a neon light effect", "", False],
["Logo of winter in artistic font, made by snowflake", "", False],
["A book cover named summer vibe", "", False],
["Newspaper with the title Love Story", "", False],
["A logo for the company EcoGrow, where the letters look like plants", "EcoGrow", False],
["A poster titled 'Quails of North America', showing different kinds of quails.", "Quails/of/North/America", False],
["A detailed portrait of a fox guardian with a shield with Kung Fu written on it, by victo ngai and justin gerard, digital art, realistic painting", "kung/fu", False],
["A stamp of breath of the wild", "breath/of/the/wild", False],
["Poster of the incoming movie Transformers", "Transformers", False],
["Some apples are on a table", "", True],
["a hotdog with mustard and other toppings on it", "", True],
["a bathroom that has a slanted ceiling and a large bath tub", "", True],
["a man holding a tennis racquet on a tennis court", "", True],
["hamburger with bacon, lettuce, tomato and cheese| promotional image| hyperquality| products shot| full - color| extreme render| mouthwatering", "", True],
],
[
prompt,
keywords,
slider_natural
],
examples_per_page=20
)
gr.HTML(
"""
<div style="text-align: justify; max-width: 1100px; margin: 20px auto;">
<h3 style="font-weight: 450; font-size: 0.8rem; margin: 0rem">
<b>Version</b>: 1.0
</h3>
<h3 style="font-weight: 450; font-size: 0.8rem; margin: 0rem">
<b>Contact</b>:
For help or issues using TextDiffuser-2, please email Jingye Chen <a href="mailto:qwerty.chen@connect.ust.hk">(qwerty.chen@connect.ust.hk)</a>, Yupan Huang <a href="mailto:huangyp28@mail2.sysu.edu.cn">(huangyp28@mail2.sysu.edu.cn)</a> or submit a GitHub issue. For other communications related to TextDiffuser-2, please contact Lei Cui <a href="mailto:lecu@microsoft.com">(lecu@microsoft.com)</a> or Furu Wei <a href="mailto:fuwei@microsoft.com">(fuwei@microsoft.com)</a>.
</h3>
<h3 style="font-weight: 450; font-size: 0.8rem; margin: 0rem">
<b>Disclaimer</b>:
Please note that the demo is intended for academic and research purposes <b>ONLY</b>. Any use of the demo for generating inappropriate content is strictly prohibited. The responsibility for any misuse or inappropriate use of the demo lies solely with the users who generated such content, and this demo shall not be held liable for any such use.
</h3>
</div>
"""
)
demo.launch() |