Spaces:
Runtime error
Runtime error
File size: 11,024 Bytes
9f33108 a814f75 9f33108 a814f75 67b38e7 9f33108 c428187 9f33108 13cd654 |
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 |
import spaces
import gradio as gr
from gradio_imageslider import ImageSlider
import torch
torch.jit.script = lambda f: f
from diffusers import (
ControlNetModel,
StableDiffusionXLControlNetImg2ImgPipeline,
DDIMScheduler,
)
from controlnet_aux import AnylineDetector
from compel import Compel, ReturnedEmbeddingsType
from PIL import Image
import os
import time
import numpy as np
IS_SPACES_ZERO = os.environ.get("SPACES_ZERO_GPU", "0") == "1"
IS_SPACE = os.environ.get("SPACE_ID", None) is not None
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16
LOW_MEMORY = os.getenv("LOW_MEMORY", "0") == "1"
print(f"device: {device}")
print(f"dtype: {dtype}")
print(f"low memory: {LOW_MEMORY}")
model = "stabilityai/stable-diffusion-xl-base-1.0"
# model = "stabilityai/sdxl-turbo"
# vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=dtype)
scheduler = DDIMScheduler.from_pretrained(model, subfolder="scheduler")
# controlnet = ControlNetModel.from_pretrained(
# "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
# )
controlnet = ControlNetModel.from_pretrained(
"TheMistoAI/MistoLine",
torch_dtype=torch.float16,
revision="refs/pr/3",
variant="fp16",
)
pipe = StableDiffusionXLControlNetImg2ImgPipeline.from_pretrained(
model,
controlnet=controlnet,
torch_dtype=dtype,
variant="fp16",
use_safetensors=True,
scheduler=scheduler,
)
compel = Compel(
tokenizer=[pipe.tokenizer, pipe.tokenizer_2],
text_encoder=[pipe.text_encoder, pipe.text_encoder_2],
returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED,
requires_pooled=[False, True],
)
pipe = pipe.to(device)
anyline = AnylineDetector.from_pretrained(
"TheMistoAI/MistoLine", filename="MTEED.pth", subfolder="Anyline"
).to(device)
def pad_image(image):
w, h = image.size
if w == h:
return image
elif w > h:
new_image = Image.new(image.mode, (w, w), (0, 0, 0))
pad_w = 0
pad_h = (w - h) // 2
new_image.paste(image, (0, pad_h))
return new_image
else:
new_image = Image.new(image.mode, (h, h), (0, 0, 0))
pad_w = (h - w) // 2
pad_h = 0
new_image.paste(image, (pad_w, 0))
return new_image
@spaces.GPU
def predict(
input_image,
prompt,
negative_prompt,
seed,
guidance_scale=8.5,
controlnet_conditioning_scale=0.5,
strength=1.0,
controlnet_start=0.0,
controlnet_end=1.0,
guassian_sigma=2.0,
intensity_threshold=3,
progress=gr.Progress(track_tqdm=True),
):
if input_image is None:
raise gr.Error("Please upload an image.")
padded_image = pad_image(input_image).resize((1024, 1024)).convert("RGB")
conditioning, pooled = compel([prompt, negative_prompt])
generator = torch.manual_seed(seed)
last_time = time.time()
anyline_image = anyline(
padded_image,
detect_resolution=1280,
guassian_sigma=max(0.01, guassian_sigma),
intensity_threshold=intensity_threshold,
)
images = pipe(
image=padded_image,
control_image=anyline_image,
strength=strength,
prompt_embeds=conditioning[0:1],
pooled_prompt_embeds=pooled[0:1],
negative_prompt_embeds=conditioning[1:2],
negative_pooled_prompt_embeds=pooled[1:2],
width=1024,
height=1024,
controlnet_conditioning_scale=float(controlnet_conditioning_scale),
controlnet_start=float(controlnet_start),
controlnet_end=float(controlnet_end),
generator=generator,
num_inference_steps=30,
guidance_scale=guidance_scale,
eta=1.0,
)
print(f"Time taken: {time.time() - last_time}")
return (padded_image, images.images[0]), padded_image, anyline_image
css = """
#intro{
# max-width: 32rem;
# text-align: center;
# margin: 0 auto;
}
"""
with gr.Blocks(css=css) as demo:
gr.Markdown(
"""
# MistoLine ControlNet demo
You can upload an initial image and prompt to generate an enhanced version.
SDXL Controlnet [TheMistoAI/MistoLine](https://huggingface.co/TheMistoAI/MistoLine)
[Anyline with Controlnet Aux ](https://github.com/huggingface/controlnet_aux)
For upscaling see [Enhance This Demo](https://huggingface.co/spaces/radames/Enhance-This-HiDiffusion-SDXL)
""",
elem_id="intro",
)
with gr.Row():
with gr.Column(scale=1):
image_input = gr.Image(type="pil", label="Input Image")
prompt = gr.Textbox(
label="Prompt",
info="The prompt is very important to get the desired results. Please try to describe the image as best as you can. Accepts Compel Syntax",
)
negative_prompt = gr.Textbox(
label="Negative Prompt",
value="blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
)
seed = gr.Slider(
minimum=0,
maximum=2**64 - 1,
value=1415926535897932,
step=1,
label="Seed",
randomize=True,
)
with gr.Accordion(label="Advanced", open=False):
guidance_scale = gr.Slider(
minimum=0,
maximum=50,
value=8.5,
step=0.001,
label="Guidance Scale",
)
controlnet_conditioning_scale = gr.Slider(
minimum=0,
maximum=1,
step=0.001,
value=0.5,
label="ControlNet Conditioning Scale",
)
strength = gr.Slider(
minimum=0,
maximum=1,
step=0.001,
value=1,
label="Strength",
)
controlnet_start = gr.Slider(
minimum=0,
maximum=1,
step=0.001,
value=0.0,
label="ControlNet Start",
)
controlnet_end = gr.Slider(
minimum=0.0,
maximum=1.0,
step=0.001,
value=1.0,
label="ControlNet End",
)
guassian_sigma = gr.Slider(
minimum=0.01,
maximum=10.0,
step=0.1,
value=2.0,
label="(Anyline) Guassian Sigma",
)
intensity_threshold = gr.Slider(
minimum=0,
maximum=255,
step=1,
value=3,
label="(Anyline) Intensity Threshold",
)
btn = gr.Button()
with gr.Column(scale=2):
with gr.Group():
image_slider = ImageSlider(position=0.5)
with gr.Row():
padded_image = gr.Image(type="pil", label="Padded Image")
anyline_image = gr.Image(type="pil", label="Anyline Image")
inputs = [
image_input,
prompt,
negative_prompt,
seed,
guidance_scale,
controlnet_conditioning_scale,
strength,
controlnet_start,
controlnet_end,
guassian_sigma,
intensity_threshold,
]
outputs = [image_slider, padded_image, anyline_image]
btn.click(lambda x: None, inputs=None, outputs=image_slider).then(
fn=predict, inputs=inputs, outputs=outputs
)
gr.Examples(
fn=predict,
inputs=inputs,
outputs=outputs,
examples=[
[
"./examples/city.png",
"hyperrealistic surreal cityscape scene at sunset, buildings",
"blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
13113544138610326000,
8.5,
0.481,
1.0,
0.0,
0.9,
2,
3,
],
[
"./examples/lara.jpeg",
"photography of lara croft 8k high definition award winning",
"blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
5436236241,
8.5,
0.8,
1.0,
0.0,
0.9,
2,
3,
],
[
"./examples/cybetruck.jpeg",
"photo of tesla cybertruck futuristic car 8k high definition on a sand dune in mars, future",
"blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
383472451451,
8.5,
0.8,
0.8,
0.0,
0.9,
2,
3,
],
[
"./examples/jesus.png",
"a photorealistic painting of Jesus Christ, 4k high definition",
"blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
13317204146129588000,
8.5,
0.8,
0.8,
0.0,
0.9,
2,
3,
],
[
"./examples/anna-sullivan-DioLM8ViiO8-unsplash.jpg",
"A crowded stadium with enthusiastic fans watching a daytime sporting event, the stands filled with colorful attire and the sun casting a warm glow",
"blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
5623124123512,
8.5,
0.8,
0.8,
0.0,
0.9,
2,
3,
],
[
"./examples/img_aef651cb-2919-499d-aa49-6d4e2e21a56e_1024.jpg",
"a large red flower on a black background 4k high definition",
"blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
23123412341234,
8.5,
0.8,
0.8,
0.0,
0.9,
2,
3,
],
[
"./examples/huggingface.jpg",
"photo realistic huggingface human emoji costume, round, yellow, (human skin)+++ (human texture)+++",
"blurry, ugly, duplicate, poorly drawn, deformed, mosaic, emoji cartoon, drawing, pixelated",
12312353423,
15.206,
0.364,
0.8,
0.0,
0.9,
2,
3,
],
],
cache_examples="lazy",
)
demo.queue(api_open=True)
demo.launch(show_api=True)
|