app.py

import gradio as gr
import numpy as np
import random
import spaces
import torch
from diffusers import DiffusionPipeline

MODEL_ID = "sd2-community/stable-diffusion-2-1"
DEFAULT_WIDTH = 768
DEFAULT_HEIGHT = 768
DEFAULT_GUIDANCE = 7.5
DEFAULT_STEPS = 30

dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"

pipe = DiffusionPipeline.from_pretrained(
    MODEL_ID, torch_dtype=dtype, variant="fp16", use_safetensors=True
).to(device)
pipe.safety_checker = None

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


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

    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt or None,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    return image, seed


examples = [
    "a tiny astronaut hatching from an egg on the moon",
    "a cat holding a sign that says hello world",
    "a photo of a beautiful mountain landscape at sunset",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 680px;
}
"""

with gr.Blocks(css=css) as demo:

    with gr.Column(elem_id="col-container"):
        gr.Markdown("""# Stable Diffusion 2.1
865M-param latent text-to-image diffusion model, native 768×768.
[[model](https://huggingface.co/sd2-community/stable-diffusion-2-1)] [[license: CreativeML OpenRAIL++-M](https://huggingface.co/stabilityai/stable-diffusion-2-1/blob/main/LICENSE-MODEL)]
        """)

        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)

        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",
            )

            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=DEFAULT_WIDTH,
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=DEFAULT_HEIGHT,
                )

            with gr.Row():

                guidance_scale = gr.Slider(
                    label="Guidance Scale",
                    minimum=1,
                    maximum=15,
                    step=0.1,
                    value=DEFAULT_GUIDANCE,
                )

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

        gr.Examples(
            examples=examples,
            fn=infer,
            inputs=[prompt],
            outputs=[result, seed],
            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],
    )

demo.launch()