File size: 5,293 Bytes
6e5e1d5
 
 
 
 
 
 
f11f490
6e5e1d5
 
8103535
6e5e1d5
f11f490
6e5e1d5
 
 
 
 
 
f11f490
 
 
 
 
 
 
 
 
6e5e1d5
 
 
 
 
 
 
 
 
 
 
 
 
 
f11f490
6e5e1d5
f11f490
 
 
6e5e1d5
5b25f5e
 
 
 
6e5e1d5
 
 
 
 
 
 
 
 
 
5b25f5e
 
 
6e5e1d5
 
5b25f5e
6e5e1d5
f11f490
6e5e1d5
 
 
 
 
 
 
 
 
 
 
 
f11f490
6e5e1d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5b25f5e
f11f490
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
import gradio as gr
import numpy as np
import random
import spaces
from diffusers import DiffusionPipeline
import torch

# Set device and model parameters
device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/stable-diffusion-3.5-large"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

# Load the Stable Diffusion pipeline and move it to the appropriate device.
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 a helper function to truncate text to a maximum of 77 tokens.
def truncate_text(text, max_tokens=77):
    if text.strip() == "":
        return text
    # Use the pipeline's tokenizer (CLIP tokenizer)
    tokens = pipe.tokenizer(text, truncation=True, max_length=max_tokens, add_special_tokens=True)
    truncated_text = pipe.tokenizer.decode(tokens["input_ids"], skip_special_tokens=True)
    return truncated_text

@spaces.GPU(duration=65)
def infer(
    prompt,
    negative_prompt="",
    seed=42,
    randomize_seed=False,
    width=1024,
    height=1024,
    guidance_scale=4.5,
    num_inference_steps=40,
    progress=gr.Progress(track_tqdm=True),
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    generator = torch.Generator(device=device).manual_seed(seed)

    # Truncate both prompt and negative prompt to 77 tokens.
    prompt = truncate_text(prompt, max_tokens=77)
    negative_prompt = truncate_text(negative_prompt, max_tokens=77) if negative_prompt.strip() else ""

    # Move model to GPU before inference.
    pipe.model.to("cuda")
    
    # Generate image using the truncated prompts.
    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    # Move model back to CPU after inference.
    pipe.model.to("cpu")

    return image, seed

# UI layout remains unchanged.
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 (8B)](https://huggingface.co/stabilityai/stable-diffusion-3.5-large)")
        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) 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)
            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=4.5,
                )
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=40, 
                )
        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,
        ],
        outputs=[result, seed],
    )

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