app.py

import gradio as gr
import numpy as np
import random
from diffusers import StableDiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "hakurei/waifu-diffusion"

torch_dtype = torch.float16 if device == "cuda" else torch.float32

pipe = StableDiffusionPipeline.from_pretrained(
    model_repo_id,
    torch_dtype=torch_dtype
)

pipe = pipe.to(device)

if device == "cuda":
    pipe.enable_xformers_memory_efficient_attention()

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 512  # stable diffusion ideal size

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(device).manual_seed(seed)

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

    return image, seed

examples = [
    "A fantasy portrait of a warrior woman, detailed and dramatic lighting",
    "A cute anime character with blue hair and big eyes"
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

power_device = "GPU" if device == "cuda" else "CPU"

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"# Waifu Diffusion Text-to-Image Generator\nRunning 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, variant="primary")

        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=64,
                    value=512,
                )
                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=64,
                    value=512,
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=15.0,
                    step=0.1,
                    value=7.5,
                )
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=20,
                )

        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, seed],
    )

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

demo.queue().launch()