app.py

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()