app.py

import spaces
import gradio as gr
import numpy as np
import PIL.Image
from PIL import Image
import random
from diffusers import ControlNetModel, StableDiffusionXLPipeline, AutoencoderKL
from diffusers import DDIMScheduler, EulerAncestralDiscreteScheduler
import torch
import os
import uuid

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

pipe = StableDiffusionXLPipeline.from_single_file(
    "https://huggingface.co/Laxhar/noob_sdxl_beta/noob_hercules3/checkpoint/checkpoint-e2_s109089.safetensors/checkpoint-e2_s109089.safetensors",
    use_safetensors=True,
    torch_dtype=torch.float16,
)
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to(device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1216

@spaces.GPU
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)

    output_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]

    # PNGに変換する
    output_image = output_image.convert("RGBA")

    return output_image  # 画像オブジェクトを直接返す

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

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

    with gr.Column(elem_id="col-container"):
        gr.Markdown("""
         Text-to-Image Demo
        using [Noob SDXL beta model](https://huggingface.co/Laxhar)
        """)
        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)

        # show_download_button=True でPNG形式でダウンロードできるようにする
        result = gr.Image(label="Result", show_label=False, type="pil", elem_id="output_image", show_download_button=True)
        
        with gr.Accordion("Advanced Settings", open=False):

            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                value="nsfw, (low quality, worst quality:1.2), very displeasing, 3d, watermark, signature, ugly, poorly drawn"
            )

            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=1024,
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=20.0,
                    step=0.1,
                    value=7,
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=28,
                    step=1,
                    value=28,
                )

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

demo.queue().launch()