File size: 19,593 Bytes
9842c28 2be5a87 ab88106 9842c28 7782ea8 9842c28 5f19d85 9842c28 c68f812 9842c28 7782ea8 2be5a87 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 |
import os
import random
import zipfile
import findfile
import PIL.Image
import autocuda
from pyabsa.utils.pyabsa_utils import fprint
try:
for z_file in findfile.find_cwd_files(and_key=['.zip'],
exclude_key=['.ignore', 'git', 'SuperResolutionAnimeDiffusion'],
recursive=10):
fprint(f"Extracting {z_file}...")
with zipfile.ZipFile(z_file, 'r') as zip_ref:
zip_ref.extractall(os.path.dirname(z_file))
except Exception as e:
os.system('unzip random_examples.zip')
from diffusers import (
AutoencoderKL,
UNet2DConditionModel,
StableDiffusionPipeline,
StableDiffusionImg2ImgPipeline,
DPMSolverMultistepScheduler,
)
import gradio as gr
import torch
from PIL import Image
import utils
import datetime
import time
import psutil
from Waifu2x.magnify import ImageMagnifier
from RealESRGANv030.interface import realEsrgan
magnifier = ImageMagnifier()
start_time = time.time()
is_colab = utils.is_google_colab()
CUDA_VISIBLE_DEVICES = ""
device = autocuda.auto_cuda()
dtype = torch.float16 if device != "cpu" else torch.float32
class Model:
def __init__(self, name, path="", prefix=""):
self.name = name
self.path = path
self.prefix = prefix
self.pipe_t2i = None
self.pipe_i2i = None
models = [
# Model("anything v3", "Linaqruf/anything-v3.0", "anything v3 style"),
Model("anything v5", "stablediffusionapi/anything-v5", "anything v5 style"),
]
# Model("Spider-Verse", "nitrosocke/spider-verse-diffusion", "spiderverse style "),
# Model("Balloon Art", "Fictiverse/Stable_Diffusion_BalloonArt_Model", "BalloonArt "),
# Model("Elden Ring", "nitrosocke/elden-ring-diffusion", "elden ring style "),
# Model("Tron Legacy", "dallinmackay/Tron-Legacy-diffusion", "trnlgcy ")
# Model("Pokémon", "lambdalabs/sd-pokemon-diffusers", ""),
# Model("Pony Diffusion", "AstraliteHeart/pony-diffusion", ""),
# Model("Robo Diffusion", "nousr/robo-diffusion", ""),
scheduler = DPMSolverMultistepScheduler(
beta_start=0.00085,
beta_end=0.012,
beta_schedule="scaled_linear",
num_train_timesteps=1000,
trained_betas=None,
predict_epsilon=True,
thresholding=False,
algorithm_type="dpmsolver++",
solver_type="midpoint",
solver_order=2,
# lower_order_final=True,
)
custom_model = None
if is_colab:
models.insert(0, Model("Custom model"))
custom_model = models[0]
last_mode = "txt2img"
current_model = models[1] if is_colab else models[0]
current_model_path = current_model.path
if is_colab:
pipe = StableDiffusionPipeline.from_pretrained(
current_model.path,
torch_dtype=dtype,
scheduler=scheduler,
safety_checker=lambda images, clip_input: (images, False),
)
else: # download all models
print(f"{datetime.datetime.now()} Downloading vae...")
vae = AutoencoderKL.from_pretrained(
current_model.path, subfolder="vae", torch_dtype=dtype
)
for model in models:
try:
print(f"{datetime.datetime.now()} Downloading {model.name} model...")
unet = UNet2DConditionModel.from_pretrained(
model.path, subfolder="unet", torch_dtype=dtype
)
model.pipe_t2i = StableDiffusionPipeline.from_pretrained(
model.path,
unet=unet,
vae=vae,
torch_dtype=dtype,
scheduler=scheduler,
safety_checker=None,
)
model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(
model.path,
unet=unet,
vae=vae,
torch_dtype=dtype,
scheduler=scheduler,
safety_checker=None,
)
except Exception as e:
print(
f"{datetime.datetime.now()} Failed to load model "
+ model.name
+ ": "
+ str(e)
)
models.remove(model)
pipe = models[0].pipe_t2i
# model.pipe_i2i = torch.compile(model.pipe_i2i)
# model.pipe_t2i = torch.compile(model.pipe_t2i)
if torch.cuda.is_available():
pipe = pipe.to(device)
# device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"
def error_str(error, title="Error"):
return (
f"""#### {title}
{error}"""
if error
else ""
)
def custom_model_changed(path):
models[0].path = path
global current_model
current_model = models[0]
def on_model_change(model_name):
prefix = (
'Enter prompt. "'
+ next((m.prefix for m in models if m.name == model_name), None)
+ '" is prefixed automatically'
if model_name != models[0].name
else "Don't forget to use the custom model prefix in the prompt!"
)
return (
gr.update(visible=model_name == models[0].name),
gr.update(placeholder=prefix),
)
def inference(
model_name,
prompt,
guidance,
steps,
width=512,
height=512,
seed=0,
img=None,
strength=0.5,
neg_prompt="",
scale="ESRGAN4x",
scale_factor=2,
):
fprint(psutil.virtual_memory()) # print memory usage
fprint(f"Prompt: {prompt}")
global current_model
for model in models:
if model.name == model_name:
current_model = model
model_path = current_model.path
generator = torch.Generator(device).manual_seed(seed) if seed != 0 else None
try:
if img is not None:
return (
img_to_img(
model_path,
prompt,
neg_prompt,
img,
strength,
guidance,
steps,
width,
height,
generator,
scale,
scale_factor,
),
None,
)
else:
return (
txt_to_img(
model_path,
prompt,
neg_prompt,
guidance,
steps,
width,
height,
generator,
scale,
scale_factor,
),
None,
)
except Exception as e:
return None, error_str(e)
# if img is not None:
# return img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height,
# generator, scale, scale_factor), None
# else:
# return txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator, scale, scale_factor), None
def txt_to_img(
model_path,
prompt,
neg_prompt,
guidance,
steps,
width,
height,
generator,
scale,
scale_factor,
):
print(f"{datetime.datetime.now()} txt_to_img, model: {current_model.name}")
global last_mode
global pipe
global current_model_path
if model_path != current_model_path or last_mode != "txt2img":
current_model_path = model_path
if is_colab or current_model == custom_model:
pipe = StableDiffusionPipeline.from_pretrained(
current_model_path,
torch_dtype=dtype,
scheduler=scheduler,
safety_checker=lambda images, clip_input: (images, False),
)
else:
# pipe = pipe.to("cpu")
pipe = current_model.pipe_t2i
if torch.cuda.is_available():
pipe = pipe.to(device)
last_mode = "txt2img"
prompt = current_model.prefix + prompt
result = pipe(
prompt,
negative_prompt=neg_prompt,
# num_images_per_prompt=n_images,
num_inference_steps=int(steps),
guidance_scale=guidance,
width=width,
height=height,
generator=generator,
)
# result.images[0] = magnifier.magnify(result.images[0], scale_factor=scale_factor)
# enhance resolution
if scale_factor > 1:
if scale == "ESRGAN4x":
fp32 = True if device == "cpu" else False
result.images[0] = realEsrgan(
input_dir=result.images[0],
suffix="",
output_dir="imgs",
fp32=fp32,
outscale=scale_factor,
)[0]
else:
result.images[0] = magnifier.magnify(
result.images[0], scale_factor=scale_factor
)
# save image
result.images[0].save(
"imgs/result-{}.png".format(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
)
return replace_nsfw_images(result)
def img_to_img(
model_path,
prompt,
neg_prompt,
img,
strength,
guidance,
steps,
width,
height,
generator,
scale,
scale_factor,
):
fprint(f"{datetime.datetime.now()} img_to_img, model: {model_path}")
global last_mode
global pipe
global current_model_path
if model_path != current_model_path or last_mode != "img2img":
current_model_path = model_path
if is_colab or current_model == custom_model:
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
current_model_path,
torch_dtype=dtype,
scheduler=scheduler,
safety_checker=lambda images, clip_input: (images, False),
)
else:
# pipe = pipe.to("cpu")
pipe = current_model.pipe_i2i
if torch.cuda.is_available():
pipe = pipe.to(device)
last_mode = "img2img"
prompt = current_model.prefix + prompt
ratio = min(height / img.height, width / img.width)
img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
result = pipe(
prompt,
negative_prompt=neg_prompt,
# num_images_per_prompt=n_images,
image=img,
num_inference_steps=int(steps),
strength=strength,
guidance_scale=guidance,
# width=width,
# height=height,
generator=generator,
)
if scale_factor > 1:
if scale == "ESRGAN4x":
fp32 = True if device == "cpu" else False
result.images[0] = realEsrgan(
input_dir=result.images[0],
suffix="",
output_dir="imgs",
fp32=fp32,
outscale=scale_factor,
)[0]
else:
result.images[0] = magnifier.magnify(
result.images[0], scale_factor=scale_factor
)
# save image
result.images[0].save(
"imgs/result-{}.png".format(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
)
return replace_nsfw_images(result)
def replace_nsfw_images(results):
if is_colab:
return results.images[0]
if hasattr(results, "nsfw_content_detected") and results.nsfw_content_detected:
for i in range(len(results.images)):
if results.nsfw_content_detected[i]:
results.images[i] = Image.open("nsfw.png")
return results.images[0]
css = """.finetuned-diffusion-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.finetuned-diffusion-div div h1{font-weight:900;margin-bottom:7px}.finetuned-diffusion-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
"""
with gr.Blocks(css=css) as demo:
if not os.path.exists("imgs"):
os.mkdir("imgs")
gr.Markdown("# Super Resolution Anime Diffusion")
gr.Markdown(
"## Author: [yangheng95](https://github.com/yangheng95) Github:[Github](https://github.com/yangheng95/stable-diffusion-webui)"
)
gr.Markdown(
"### This demo is running on a CPU, so it will take at least 20 minutes. "
"If you have a GPU, you can clone from [Github](https://github.com/yangheng95/SuperResolutionAnimeDiffusion) and run it locally."
)
gr.Markdown(
"### FYI: to generate a 512*512 image and magnify 4x, it only takes 5~8 seconds on a RTX 2080 GPU"
)
gr.Markdown(
"### You can duplicate this demo on HuggingFace Spaces, click [here](https://huggingface.co/spaces/yangheng/Super-Resolution-Anime-Diffusion?duplicate=true)"
)
with gr.Row():
with gr.Column(scale=55):
with gr.Group():
gr.Markdown("Text to image")
model_name = gr.Dropdown(
label="Model",
choices=[m.name for m in models],
value=current_model.name,
)
with gr.Box(visible=False) as custom_model_group:
custom_model_path = gr.Textbox(
label="Custom model path",
placeholder="Path to model, e.g. nitrosocke/Arcane-Diffusion",
interactive=True,
)
gr.HTML(
"<div><font size='2'>Custom models have to be downloaded first, so give it some time.</font></div>"
)
with gr.Row():
prompt = gr.Textbox(
label="Prompt",
show_label=False,
max_lines=2,
placeholder="Enter prompt. Style applied automatically",
).style(container=False)
with gr.Row():
generate = gr.Button(value="Generate")
with gr.Row():
with gr.Group():
neg_prompt = gr.Textbox(
label="Negative prompt",
value="bad result, worst, random, invalid, inaccurate, imperfect, blurry, deformed,"
" disfigured, mutation, mutated, ugly, out of focus, bad anatomy, text, error,"
" extra digit, fewer digits, worst quality, low quality, normal quality, noise, "
"jpeg artifact, compression artifact, signature, watermark, username, logo, "
"low resolution, worst resolution, bad resolution, normal resolution, bad detail,"
" bad details, bad lighting, bad shadow, bad shading, bad background,"
" worst background.",
)
image_out = gr.Image(height="auto", width="auto")
error_output = gr.Markdown()
with gr.Row():
gr.Markdown(
"# Random Image Generation Preview (512*768)x4 magnified"
)
for f_img in findfile.find_cwd_files(".png", recursive=2):
with gr.Row():
image = gr.Image(height=512, value=PIL.Image.open(f_img))
# gallery = gr.Gallery(
# label="Generated images", show_label=False, elem_id="gallery"
# ).style(grid=[1], height="auto")
with gr.Column(scale=45):
with gr.Group():
gr.Markdown("Image to Image")
with gr.Row():
with gr.Group():
image = gr.Image(
label="Image", height=256, tool="editor", type="pil"
)
strength = gr.Slider(
label="Transformation strength",
minimum=0,
maximum=1,
step=0.01,
value=0.5,
)
with gr.Row():
with gr.Group():
# n_images = gr.Slider(label="Images", value=1, minimum=1, maximum=4, step=1)
with gr.Row():
guidance = gr.Slider(
label="Guidance scale", value=7.5, maximum=15
)
steps = gr.Slider(
label="Steps", value=15, minimum=2, maximum=75, step=1
)
with gr.Row():
width = gr.Slider(
label="Width",
value=512,
minimum=64,
maximum=1024,
step=8,
)
height = gr.Slider(
label="Height",
value=768,
minimum=64,
maximum=1024,
step=8,
)
with gr.Row():
scale = gr.Radio(
label="Scale",
choices=["Waifu2x", "ESRGAN4x"],
value="Waifu2x",
)
with gr.Row():
scale_factor = gr.Slider(
1,
8,
label="Scale factor (to magnify image) (1, 2, 4, 8)",
value=1,
step=1,
)
seed = gr.Slider(
0, 2147483647, label="Seed (0 = random)", value=0, step=1
)
if is_colab:
model_name.change(
on_model_change,
inputs=model_name,
outputs=[custom_model_group, prompt],
queue=False,
)
custom_model_path.change(
custom_model_changed, inputs=custom_model_path, outputs=None
)
# n_images.change(lambda n: gr.Gallery().style(grid=[2 if n > 1 else 1], height="auto"), inputs=n_images, outputs=gallery)
gr.Markdown(
"### based on [Anything V5]"
)
inputs = [
model_name,
prompt,
guidance,
steps,
width,
height,
seed,
image,
strength,
neg_prompt,
scale,
scale_factor,
]
outputs = [image_out, error_output]
prompt.submit(inference, inputs=inputs, outputs=outputs)
generate.click(inference, inputs=inputs, outputs=outputs, api_name="generate")
prompt_keys = [
"girl",
"lovely",
"cute",
"beautiful eyes",
"cumulonimbus clouds",
random.choice(["dress"]),
random.choice(["white hair"]),
random.choice(["blue eyes"]),
random.choice(["flower meadow"]),
random.choice(["Elif", "Angel"]),
]
prompt.value = ",".join(prompt_keys)
ex = gr.Examples(
[
[models[0].name, prompt.value, 7.5, 15],
],
inputs=[model_name, prompt, guidance, steps, seed],
outputs=outputs,
fn=inference,
cache_examples=False,
)
print(f"Space built in {time.time() - start_time:.2f} seconds")
if not is_colab:
demo.queue(concurrency_count=2)
demo.launch(debug=is_colab, enable_queue=True, share=is_colab) |