File size: 4,362 Bytes
a130ca1
 
 
1d944c8
a130ca1
1d944c8
53be099
 
 
 
a130ca1
1d944c8
 
 
 
a130ca1
 
53be099
1d944c8
a130ca1
 
1d944c8
 
 
 
 
a130ca1
 
1d944c8
 
 
 
 
a130ca1
 
53be099
 
 
 
 
a130ca1
 
 
 
 
 
 
1d944c8
a130ca1
1d944c8
 
 
 
 
 
 
 
a130ca1
 
 
 
 
 
 
 
 
1d944c8
a130ca1
 
 
 
 
 
1d944c8
a130ca1
 
 
 
 
 
 
 
 
1d944c8
a130ca1
 
 
 
 
 
 
 
 
 
 
1d944c8
a130ca1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1d944c8
 
a130ca1
 
 
1d944c8
 
 
a130ca1
 
1d944c8
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
import gradio as gr
import numpy as np
import random
from diffusers import StableDiffusionPipeline
import torch
import os
import logging

logging.basicConfig(level=logging.INFO)


# Retrieve Hugging Face access token from environment variables
access_token = os.getenv("HF_ACCESS_TOKEN")

# Set device
device = "cuda" if torch.cuda.is_available() else "cpu"


# Load the Stable Diffusion model
if torch.cuda.is_available():
    torch.cuda.max_memory_allocated(device=device)
    pipe = StableDiffusionPipeline.from_pretrained(
        "stabilityai/stable-diffusion-3-medium",
        torch_dtype=torch.float16,
        use_auth_token=access_token  # Use the token here
    )
    pipe.enable_xformers_memory_efficient_attention()
    pipe = pipe.to(device)
else:
    pipe = StableDiffusionPipeline.from_pretrained(
        "stabilityai/stable-diffusion-3-medium",
        use_auth_token=access_token  # Use the token here
    )
    pipe = pipe.to(device)

logging.info("Loading the model...")

# Load model
logging.info("Model loaded successfully.")

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

def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    generator = torch.Generator().manual_seed(seed)

    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]
    
    return image

examples = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 520px;
}
"""

power_device = "GPU" if torch.cuda.is_available() else "CPU"

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""
        # Text-to-Image Gradio Template
        Currently running on {power_device}.
        """)
        
        with gr.Row():
            prompt = gr.Textbox(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )
            run_button = gr.Button("Run", scale=0)
        
        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            negative_prompt = gr.Textbox(
                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=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=0.0,
                )
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=12,
                    step=1,
                    value=2,
                )
        
        gr.Examples(
            examples=examples,
            inputs=[prompt]
        )

    run_button.click(
        fn=infer,
        inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
        outputs=[result]
    )

demo.queue().launch()