File size: 5,966 Bytes
42d7985
 
 
 
bc2e792
42d7985
 
 
 
 
 
 
 
 
bc2e792
 
 
 
42d7985
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bc2e792
42d7985
6c3ac85
42d7985
 
 
 
 
 
 
bc2e792
42d7985
 
 
 
 
 
 
bc2e792
42d7985
 
 
bc2e792
42d7985
 
 
 
 
 
 
 
 
 
 
bc2e792
 
42d7985
 
 
 
 
 
 
 
 
 
bc2e792
 
42d7985
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bc2e792
42d7985
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bc2e792
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42d7985
bc2e792
42d7985
 
 
 
 
 
 
 
 
 
bc2e792
42d7985
 
 
 
 
 
 
 
 
 
 
 
 
bc2e792
42d7985
 
 
 
 
 
 
 
 
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
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_nag import NAGFluxPipeline
from src.transformer_flux import NAGFluxTransformer2DModel


MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048


theme = gr.themes.Base(
    font=[gr.themes.GoogleFont('Libre Franklin'), gr.themes.GoogleFont('Public Sans'), 'system-ui', 'sans-serif'],
)

transformer = NAGFluxTransformer2DModel.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    subfolder="transformer",
    torch_dtype=torch.bfloat16,
)
pipe = NAGFluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    transformer=transformer,
    torch_dtype=torch.bfloat16,
)

device = "cuda"
pipe = pipe.to(device)

examples = [
    ["Portrait of AI researcher.", "Glasses.", 5],
    ["Portrait of AI researcher.", "Male.", 5],
    ["A baby phoenix made of fire and flames is born from the smoking ashes.", "Low resolution, blurry, lack of details, illustration, cartoon, painting.", 5],
    ["A tiny astronaut hatching from an egg on the moon.", "Low resolution, blurry, lack of details, illustration, cartoon, painting.", 9]
]

@spaces.GPU
def sample(
        prompt,
        negative_prompt=None, guidance_scale=3.5,
        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)

    generator = torch.Generator(device="cuda").manual_seed(seed)
    image_nag = pipe(
        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)
        image_normal = pipe(
            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(
        prompt,
        nag_negative_prompt,
        nag_scale,
):
    outputs, seed = sample(
        prompt=prompt,
        nag_negative_prompt=nag_negative_prompt,
        nag_scale=nag_scale,
    )
    return outputs, 3.5, 1024, 1024, 25, seed, True


css = '''
.gradio-container{
max-width: 768px !important;
margin: 0 auto;
}
'''

with gr.Blocks(css=css, theme=theme) as demo:
    gr.Markdown('''# Normalized Attention Guidance (NAG) Flux-Dev
    Implementation of [Normalized Attention Guidance](https://chendaryen.github.io/NAG.github.io/)
    ''')
    with gr.Group():
        prompt = gr.Textbox(
            label="Prompt",
            max_lines=1,
            placeholder="Enter your prompt",
        )
        nag_negative_prompt = gr.Textbox(
            label="Negative Prompt for NAG",
            value="Low resolution, blurry, lack of details, illustration, cartoon, painting.",
            max_lines=1,
        )
        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)
        output = gr.ImageSlider(label="Left: Baseline, Right: With NAG", interactive=False)
        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=3.5)
            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)

        gr.Examples(
            examples=examples,
            fn=sample_example,
            inputs=[
                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=[
            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)