app.py

import gradio as gr
import numpy as np
import random

# import spaces #[uncomment to use ZeroGPU]
from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_id_default = "CompVis/stable-diffusion-v1-4"  # Replace to the model you would like to use

if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

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


# @spaces.GPU #[uncomment to use ZeroGPU]
def infer(
    prompt,
    negative_prompt,
    width,
    height,
    model_id=model_id_default,
    seed=42,
    guidance_scale=7.0,
    num_inference_steps=20,
    progress=gr.Progress(track_tqdm=True),
):  
    generator = torch.Generator().manual_seed(seed)
    pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype)
    pipe = pipe.to(device)
    
    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

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(" # Text-to-Image demo")

        with gr.Row():
            model_id = gr.Textbox(
                label="Model ID",
                max_lines=1,
                placeholder="Enter model id",
                value=model_id_default,
            )

        prompt = gr.Textbox(
            label="Prompt",
            max_lines=1,
            placeholder="Enter your prompt",
        )

        negative_prompt = gr.Textbox(
            label="Negative prompt",
            max_lines=1,
            placeholder="Enter your negative prompt",
        )

        with gr.Row():
            seed = gr.Number(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=42,
            )

        with gr.Row():
            guidance_scale = gr.Slider(
                label="Guidance scale",
                minimum=0.0,
                maximum=10.0,
                step=0.1,
                value=7.0,  # Replace with defaults that work for your model
            )

            num_inference_steps = gr.Slider(
                label="Number of inference steps",
                minimum=1,
                maximum=50,
                step=1,
                value=20,  # Replace with defaults that work for your model
            )

        with gr.Accordion("Optional Settings", open=False):
            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,  # Replace with defaults that work for your model
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,  # Replace with defaults that work for your model
                )
        
        run_button = gr.Button("Run", scale=0, variant="primary")
        result = gr.Image(label="Result", show_label=False)
        
    gr.on(
        triggers=[run_button.click],
        fn=infer,
        inputs=[
            prompt,
            negative_prompt,
            width,
            height,
            model_id,
            seed,
            guidance_scale,
            num_inference_steps,       
        ],
        outputs=[result],
    )

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