Spaces:
Running
on
Zero
Running
on
Zero
File size: 8,627 Bytes
f106340 |
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 |
import random
import os
import spaces
import numpy as np
import torch
from PIL import Image
import huggingface_hub
import gradio as gr
from src.pipeline_flux_kontext_nag import NAGFluxKontextPipeline
from src.transformer_flux import NAGFluxTransformer2DModel
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048
DEFAULT_GUIDANCE_SCALE = 2.5
DEFAULT_NEGATIVE_PROMPT = "Low resolution, blurry, lack of details"
transformer = NAGFluxTransformer2DModel.from_pretrained(
"black-forest-labs/FLUX.1-Kontext-dev",
subfolder="transformer",
torch_dtype=torch.bfloat16,
)
pipe = NAGFluxKontextPipeline.from_pretrained(
"black-forest-labs/FLUX.1-Kontext-dev",
transformer=transformer,
torch_dtype=torch.bfloat16,
)
device = "cuda"
pipe = pipe.to(device)
examples = [
["./assets/monster.png", "Transform to 1960s pop art poster style.", "Use a bright pink, green and blue color palette.", 5],
["./assets/rabbit.jpg", "Using this elegant style, create a portrait of a cute Godzilla wearing a pearl tiara and lace collar, maintaining the same refined quality and soft color tones.", DEFAULT_NEGATIVE_PROMPT, 5],
]
def get_duration(
input_image,
prompt,
negative_prompt, guidance_scale,
nag_negative_prompt, nag_scale,
width, height,
num_inference_steps,
seed, randomize_seed,
compare,
):
duration = int(num_inference_steps) * 1.5 + 5
if compare:
duration *= 1.7
return duration
@spaces.GPU(duration=get_duration)
def sample(
input_image,
prompt,
negative_prompt=None, guidance_scale=DEFAULT_GUIDANCE_SCALE,
nag_negative_prompt=None, nag_scale=5.0,
width=1024, height=1024,
num_inference_steps=25,
seed=2025, randomize_seed=False,
compare=True,
):
prompt = prompt.strip()
negative_prompt = negative_prompt.strip() if negative_prompt and negative_prompt.strip() else None
guidance_scale = float(guidance_scale)
width, height = int(width), int(height)
num_inference_steps = int(num_inference_steps)
if (randomize_seed):
seed = random.randint(0, MAX_SEED)
else:
seed = int(seed)
if input_image is not None:
input_image = input_image.convert("RGB")
generator = torch.Generator(device="cuda").manual_seed(seed)
if input_image is not None:
image_nag = pipe(
prompt=prompt,
image=input_image,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
nag_negative_prompt=nag_negative_prompt,
nag_scale=nag_scale,
generator=generator,
width=input_image.size[0],
height=input_image.size[1],
num_inference_steps=num_inference_steps,
).images[0]
else:
image_nag = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
nag_negative_prompt=nag_negative_prompt,
nag_scale=nag_scale,
generator=generator,
width=width,
height=height,
num_inference_steps=num_inference_steps,
).images[0]
if compare:
generator = torch.Generator(device="cuda").manual_seed(seed)
if input_image is not None:
image_normal = pipe(
prompt=prompt,
image=input_image,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
generator=generator,
width=input_image.size[0],
height=input_image.size[1],
num_inference_steps=num_inference_steps,
).images[0]
else:
image_normal = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
generator=generator,
width=width,
height=height,
num_inference_steps=num_inference_steps,
).images[0]
else:
image_normal = Image.new("RGB", image_nag.size, color=(0, 0, 0))
return (image_normal, image_nag), seed
def sample_example(
input_image,
prompt,
nag_negative_prompt,
nag_scale,
):
outputs, seed = sample(
input_image=input_image,
prompt=prompt,
negative_prompt=None, guidance_scale=DEFAULT_GUIDANCE_SCALE,
nag_negative_prompt=nag_negative_prompt, nag_scale=nag_scale,
width=1024, height=1024,
num_inference_steps=25,
seed=2025, randomize_seed=False,
compare=True,
)
return outputs, DEFAULT_GUIDANCE_SCALE, 1024, 1024, 25, seed, True
css="""
#col-container {
margin: 0 auto;
max-width: 960;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown('''# Normalized Attention Guidance (NAG) Flux-Kontext-Dev
NAG demos: [LTX Video Fast](https://huggingface.co/spaces/ChenDY/NAG_ltx-video-distilled), [Wan2.1-T2V-14B](https://huggingface.co/spaces/ChenDY/NAG_wan2-1-fast), [FLUX.1-dev](https://huggingface.co/spaces/ChenDY/NAG_FLUX.1-dev)
Implementation of [Normalized Attention Guidance](https://chendaryen.github.io/NAG.github.io/)
[Paper](https://arxiv.org/abs/2505.21179), [GitHub](https://github.com/ChenDarYen/Normalized-Attention-Guidance), [ComfyUI](https://github.com/ChenDarYen/ComfyUI-NAG)
''')
with gr.Row():
with gr.Column():
input_image = gr.Image(label="Upload the image for editing", type="pil")
prompt = gr.Textbox(
label="Prompt",
max_lines=3,
placeholder="Enter your prompt",
)
nag_negative_prompt = gr.Textbox(
label="Negative Prompt for NAG",
value=DEFAULT_NEGATIVE_PROMPT,
max_lines=3,
)
nag_scale = gr.Slider(label="NAG Scale", minimum=1., maximum=20., step=0.25, value=5.)
compare = gr.Checkbox(label="Compare with baseline", info="If unchecked, only sample with NAG will be generated.", value=True)
button = gr.Button("Generate", min_width=120)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Textbox(label="Negative Prompt", value=None, visible=False)
guidance_scale = gr.Slider(label="Guidance Scale", minimum=1., maximum=15., step=0.1, value=DEFAULT_GUIDANCE_SCALE)
with gr.Row():
width = gr.Slider(
label="Width",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=1024,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=1024,
)
num_inference_steps = gr.Slider(label="Inference Steps", minimum=1, maximum=50, step=1, value=25)
seed = gr.Slider(label="Seed", minimum=1, maximum=MAX_SEED, step=1, randomize=True)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
with gr.Column():
output = gr.ImageSlider(label="Left: Baseline, Right: With NAG", interactive=False)
gr.Examples(
examples=examples,
fn=sample_example,
inputs=[
input_image,
prompt,
nag_negative_prompt,
nag_scale,
],
outputs=[output, guidance_scale, width, height, num_inference_steps, seed, compare],
cache_examples="lazy",
)
gr.on(
triggers=[
button.click,
prompt.submit
],
fn=sample,
inputs=[
input_image,
prompt,
negative_prompt, guidance_scale,
nag_negative_prompt, nag_scale,
width, height,
num_inference_steps,
seed, randomize_seed,
compare,
],
outputs=[output, seed],
)
if __name__ == "__main__":
huggingface_hub.login(os.getenv('HF_TOKEN'))
demo.launch(share=True)
|