File size: 5,979 Bytes
f366c08
 
36b95af
 
f366c08
36b95af
f366c08
 
36b95af
 
9199c0d
36b95af
 
 
 
f366c08
36b95af
 
f366c08
 
36b95af
f366c08
36b95af
15a7c48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36b95af
 
 
 
 
 
 
 
 
 
 
 
 
 
f366c08
 
15a7c48
36b95af
 
 
f366c08
36b95af
 
 
 
 
 
 
 
 
 
f366c08
 
36b95af
 
 
 
f366c08
 
36b95af
f366c08
 
36b95af
 
 
 
f366c08
36b95af
f366c08
36b95af
 
 
 
 
 
 
 
 
 
 
 
 
822c939
36b95af
822c939
36b95af
822c939
36b95af
 
 
 
 
 
f366c08
36b95af
 
 
 
 
 
 
f366c08
 
36b95af
15a7c48
36b95af
 
 
 
 
 
 
 
f366c08
36b95af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f366c08
36b95af
 
f366c08
 
 
 
36b95af
f366c08
 
 
36b95af
15a7c48
f366c08
 
 
d588458
f366c08
36b95af
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
import gradio as gr
import numpy as np
import random

import spaces
from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/stable-diffusion-3.5-large-turbo"

if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
else:
    torch_dtype = torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024

# Define styles
style_list = [
    {
        "name": "3840 x 2160",
        "prompt": "hyper-realistic 8K image of {prompt}. ultra-detailed, lifelike, high-resolution, sharp, vibrant colors, photorealistic",
        "negative_prompt": "cartoonish, low resolution, blurry, simplistic, abstract, deformed, ugly",
    },
    {
        "name": "2560 x 1440",
        "prompt": "hyper-realistic 4K image of {prompt}. ultra-detailed, lifelike, high-resolution, sharp, vibrant colors, photorealistic",
        "negative_prompt": "cartoonish, low resolution, blurry, simplistic, abstract, deformed, ugly",
    },
    {
        "name": "HD+",
        "prompt": "hyper-realistic 2K image of {prompt}. ultra-detailed, lifelike, high-resolution, sharp, vibrant colors, photorealistic",
        "negative_prompt": "cartoonish, low resolution, blurry, simplistic, abstract, deformed, ugly",
    },
    {
        "name": "Style Zero",
        "prompt": "{prompt}",
        "negative_prompt": "",
    },
]

STYLE_NAMES = [style["name"] for style in style_list]
DEFAULT_STYLE_NAME = STYLE_NAMES[0]

@spaces.GPU
def infer(
    prompt,
    negative_prompt="",
    seed=42,
    randomize_seed=False,
    width=1024,
    height=1024,
    guidance_scale=0.0,
    num_inference_steps=4,
    style="Style Zero",
    progress=gr.Progress(track_tqdm=True),
):
    
    selected_style = next(s for s in style_list if s["name"] == style)
    styled_prompt = selected_style["prompt"].format(prompt=prompt)
    styled_negative_prompt = selected_style["negative_prompt"]

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    generator = torch.Generator().manual_seed(seed)

    image = pipe(
        prompt=styled_prompt,
        negative_prompt=styled_negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    return image, seed

examples = [
    "A capybara wearing a suit holding a sign that reads Hello World",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # [Stable Diffusion 3.5 Large Turbo (8B)](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo)")
        gr.Markdown("[Learn more](https://stability.ai/news/introducing-stable-diffusion-3-5) about the Stable Diffusion 3.5 series. Try on [Stability AI API](https://platform.stability.ai/docs/api-reference#tag/Generate/paths/~1v2beta~1stable-image~1generate~1sd3/post), or [download model](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo) to run locally with ComfyUI or diffusers.")
        
        with gr.Row():
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )

            run_button = gr.Button("Run", scale=0, variant="primary")

        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=False,
            )

            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )

            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

            style_selection = gr.Radio(
                show_label=True,
                container=True,
                interactive=True,
                choices=STYLE_NAMES,
                value=DEFAULT_STYLE_NAME,
                label="Quality Style",
            )

            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=512,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )

                height = gr.Slider(
                    label="Height",
                    minimum=512,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=7.5,
                    step=0.1,
                    value=0.0,
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=4,
                )

        gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=True, cache_mode="lazy")
        
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            prompt,
            negative_prompt,
            seed,
            randomize_seed,
            width,
            height,
            guidance_scale,
            num_inference_steps,
            style_selection,
        ],
        outputs=[result, seed],
    )

if __name__ == "__main__":
    demo.launch()