Spaces:
Paused
Paused
File size: 10,879 Bytes
ef6c3c2 74045df ef6c3c2 74045df ef6c3c2 74045df ef6c3c2 20c21fe ef6c3c2 74045df ef6c3c2 b7b4c25 ef6c3c2 b7b4c25 ef6c3c2 b7b4c25 ef6c3c2 74045df ef6c3c2 b7b4c25 ef6c3c2 74045df ef6c3c2 b7b4c25 ef6c3c2 b7b4c25 ef6c3c2 74045df ef6c3c2 74045df ef6c3c2 b7b4c25 ef6c3c2 b7b4c25 ef6c3c2 b7b4c25 ef6c3c2 b7b4c25 ef6c3c2 b7b4c25 ef6c3c2 |
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 |
import gradio as gr
import numpy as np
import random
import torch
from PIL import Image
import os
from huggingface_hub import hf_hub_download
from pathlib import Path
import sys
# Add src directory to Python path
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from src import model_loader
from src import pipeline
from src.config import Config, DeviceConfig
from transformers import CLIPTokenizer
# Create data directory if it doesn't exist
data_dir = Path("data")
data_dir.mkdir(exist_ok=True)
# Model configuration
MODEL_REPO = "stable-diffusion-v1-5/stable-diffusion-v1-5"
MODEL_FILENAME = "v1-5-pruned-emaonly.ckpt"
model_file = data_dir / MODEL_FILENAME
# Download model if it doesn't exist
if not model_file.exists():
print(f"Downloading model from {MODEL_REPO}...")
model_file = hf_hub_download(
repo_id=MODEL_REPO,
filename=MODEL_FILENAME,
local_dir=data_dir,
local_dir_use_symlinks=False
)
print("Model downloaded successfully!")
# Device configuration
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using device: {device}")
# Initialize configuration
config = Config(
device=DeviceConfig(device=device),
tokenizer=CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")
)
# Load models
config.models = model_loader.load_models(str(model_file), device)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
def txt2img(
prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
progress=gr.Progress(track_tqdm=True),
):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
# Update config with user settings
config.seed = seed
config.diffusion.cfg_scale = guidance_scale
config.diffusion.n_inference_steps = num_inference_steps
config.model.width = width
config.model.height = height
# Generate image
output_image = pipeline.generate(
prompt=prompt,
uncond_prompt=negative_prompt,
input_image=None,
config=config
)
# Convert numpy array to PIL Image
image = Image.fromarray(output_image)
return image, seed
def img2img(
prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
input_image,
strength,
progress=gr.Progress(track_tqdm=True),
):
try:
if randomize_seed:
seed = random.randint(0, MAX_SEED)
if input_image is None:
return None, seed
# Update config with user settings
config.seed = seed
config.diffusion.cfg_scale = guidance_scale
config.diffusion.n_inference_steps = num_inference_steps
config.model.width = width
config.model.height = height
config.diffusion.strength = strength
# Generate image
output_image = pipeline.generate(
prompt=prompt,
uncond_prompt=negative_prompt,
input_image=input_image,
config=config
)
# Convert numpy array to PIL Image
image = Image.fromarray(output_image)
return image, seed
except Exception as e:
print(f"Error in img2img: {str(e)}")
gr.Warning(f"Error: {str(e)}")
return None, seed
def inpaint(
prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
input_image,
mask_image,
strength,
progress=gr.Progress(track_tqdm=True),
):
try:
if randomize_seed:
seed = random.randint(0, MAX_SEED)
if input_image is None or mask_image is None:
gr.Warning("Both input image and mask are required for inpainting")
return None, seed
# Ensure mask is in the right format
if mask_image.mode != "L":
mask_image = mask_image.convert("L")
# Update config with user settings
config.seed = seed
config.diffusion.cfg_scale = guidance_scale
config.diffusion.n_inference_steps = num_inference_steps
config.model.width = width
config.model.height = height
config.diffusion.strength = strength
# Generate image with mask
output_image = pipeline.generate(
prompt=prompt,
uncond_prompt=negative_prompt,
input_image=input_image,
mask_image=mask_image,
config=config
)
# Convert numpy array to PIL Image
image = Image.fromarray(output_image)
return image, seed
except Exception as e:
print(f"Error in inpainting: {str(e)}")
gr.Warning(f"Error: {str(e)}")
return None, seed
examples = [
"A ultra sharp photorealtici painting of a futuristic cityscape at night with neon lights and flying cars",
"A serene mountain landscape at sunset with snow-capped peaks and a clear lake reflection",
"A detailed portrait of a cyberpunk character with glowing neon implants and holographic tattoos",
]
css = """
#col-container {
margin: 0 auto;
max-width: 640px;
}
.tabs {
margin-top: 10px;
margin-bottom: 10px;
}
.disclaimer {
font-size: 0.8em;
color: #666;
margin-top: 20px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(" # LiteDiffusion")
with gr.Tabs(elem_classes="tabs") as tabs:
with gr.TabItem("Text-to-Image"):
txt2img_prompt = gr.Text(
label="Prompt",
max_lines=1,
placeholder="Enter your prompt",
)
txt2img_run = gr.Button("Generate", variant="primary")
txt2img_result = gr.Image(label="Result")
with gr.TabItem("Image-to-Image"):
img2img_prompt = gr.Text(
label="Prompt",
max_lines=1,
placeholder="Enter your prompt",
)
with gr.Row():
with gr.Column(scale=1):
input_image = gr.Image(label="Input Image", type="pil")
strength_slider = gr.Slider(
label="Strength",
minimum=0.0,
maximum=1.0,
step=0.01,
value=0.8,
)
img2img_run = gr.Button("Generate", variant="primary")
with gr.Column(scale=1):
img2img_result = gr.Image(label="Result")
with gr.TabItem("Inpainting"):
inpaint_prompt = gr.Text(
label="Prompt",
max_lines=1,
placeholder="Enter your prompt",
)
with gr.Row():
with gr.Column(scale=1):
inpaint_image = gr.Image(label="Input Image", type="pil")
inpaint_mask = gr.Image(label="Mask (White areas will be inpainted)", type="pil")
inpaint_strength = gr.Slider(
label="Strength",
minimum=0.0,
maximum=1.0,
step=0.01,
value=0.8,
)
inpaint_run = gr.Button("Generate", variant="primary")
with gr.Column(scale=1):
inpaint_result = gr.Image(label="Result")
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=42,
)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
with gr.Row():
width = gr.Slider(
label="Width",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512,
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=10.0,
step=0.1,
value=7.5,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=50,
)
gr.Markdown(
"By using LiteDiffusion, you agree to the terms in our [disclaimer](disclaimer.md).",
elem_classes="disclaimer"
)
# Example prompts for text to image
gr.Examples(examples=examples, inputs=[txt2img_prompt])
# Text-to-Image generation
txt2img_run.click(
fn=txt2img,
inputs=[
txt2img_prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
],
outputs=[txt2img_result, seed],
)
# Image-to-Image generation
img2img_run.click(
fn=img2img,
inputs=[
img2img_prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
input_image,
strength_slider,
],
outputs=[img2img_result, seed],
)
# Inpainting
inpaint_run.click(
fn=inpaint,
inputs=[
inpaint_prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
inpaint_image,
inpaint_mask,
inpaint_strength,
],
outputs=[inpaint_result, seed],
)
if __name__ == "__main__":
demo.launch() |