app.py

import gradio as gr
from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler, LCMScheduler, AutoencoderKL,DiffusionPipeline
import torch
from typing import Tuple
import numpy as np
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
import spaces
import os
import random
import uuid

def save_image(img):
    unique_name = str(uuid.uuid4()) + ".png"
    img.save(unique_name)
    return unique_name

def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed

MAX_SEED = np.iinfo(np.int32).max
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
# by PixArt-alpha/PixArt-Sigma    
style_list = [
    {
        "name": "(No style)",
        "prompt": "{prompt}",
        "negative_prompt": "",
    },
    {
        "name": "Cinematic",
        "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
    },
    {
        "name": "Photographic",
        "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed",
        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly",
    },
    {
        "name": "Anime",
        "prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime,  highly detailed",
        "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast",
    },
    {
        "name": "Manga",
        "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style",
        "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style",
    },
    {
        "name": "Digital Art",
        "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed",
        "negative_prompt": "photo, photorealistic, realism, ugly",
    },
    {
        "name": "Pixel art",
        "prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics",
        "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
    },
    {
        "name": "Fantasy art",
        "prompt": "ethereal fantasy concept art of  {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy",
        "negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white",
    },
    {
        "name": "Neonpunk",
        "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional",
        "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured",
    },
    {
        "name": "3D Model",
        "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting",
        "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting",
    },
]   
styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "(No style)"

def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]:
    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
    if not negative:
        negative = ""
    return p.replace("{prompt}", positive), n + negative

JX_pipe = StableDiffusionXLPipeline.from_pretrained(
        "RunDiffusion/Juggernaut-X-Hyper",
        vae=vae,
        torch_dtype=torch.float16,
    )
JX_pipe.to("cuda")


J10_pipe = StableDiffusionXLPipeline.from_pretrained(
        "RunDiffusion/Juggernaut-X-v10",
        vae=vae,
        torch_dtype=torch.float16,
    )
J10_pipe.to("cuda")


J9_pipe = StableDiffusionXLPipeline.from_pretrained(
        "RunDiffusion/Juggernaut-XL-v9",
        vae=vae,
        torch_dtype=torch.float16,
        custom_pipeline="lpw_stable_diffusion_xl",
        use_safetensors=True,
        add_watermarker=False,
        variant="fp16",
    )
J9_pipe.to("cuda")

J8_pipe = StableDiffusionXLPipeline.from_pretrained(
        "RunDiffusion/Juggernaut-XL-v8",
        vae=vae,
        torch_dtype=torch.float16,
        custom_pipeline="lpw_stable_diffusion_xl",
    )
J8_pipe.to("cuda")

J7_pipe = StableDiffusionXLPipeline.from_pretrained(
        "RunDiffusion/Juggernaut-XL-v7",
        vae=vae,
        torch_dtype=torch.float16,
        custom_pipeline="lpw_stable_diffusion_xl",
    )
J7_pipe.to("cuda")

J_pipe = StableDiffusionXLPipeline.from_pretrained(
        "RunDiffusion/Juggernaut-XL",
        vae=vae,
        torch_dtype=torch.float16,
        custom_pipeline="lpw_stable_diffusion_xl",
    )
J_pipe.to("cuda")

@spaces.GPU
def run_comparison(prompt: str,
    negative_prompt: str = "",
    style: str = DEFAULT_STYLE_NAME,
    use_negative_prompt: bool = False,
    num_inference_steps: int = 30,
    num_images_per_prompt: int = 2,
    seed: int = 0,
    width: int = 1024,
    height: int = 1024,
    guidance_scale: float = 3,
    randomize_seed: bool = False,
    progress=gr.Progress(track_tqdm=True),
):
    seed = int(randomize_seed_fn(seed, randomize_seed))
    if not use_negative_prompt:
        negative_prompt = ""
    prompt, negative_prompt = apply_style(style, prompt, negative_prompt)
    
    image_r3 = JX_pipe(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
    ).images
    image_paths_r3 = [save_image(img) for img in image_r3]

    image_r4 = J10_pipe(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
    ).images
    image_paths_r4 = [save_image(img) for img in image_r4]

    image_r5 = J9_pipe(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
    ).images
    image_paths_r5 = [save_image(img) for img in image_r5]

    image_r6 = J8_pipe(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
    ).images
    image_paths_r6 = [save_image(img) for img in image_r6]

    image_r7 = J7_pipe(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
    ).images
    image_paths_r7 = [save_image(img) for img in image_r7]

    image_r8 = J_pipe(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
    ).images
    image_paths_r8 = [save_image(img) for img in image_r8]
    
    return image_paths_r3, image_paths_r4,image_paths_r5, seed

examples = ["A dignified beaver wearing glasses, a vest, and colorful neck tie.",
"The spirit of a tamagotchi wandering in the city of Barcelona",
"an ornate, high-backed mahogany chair with a red cushion",
"a sketch of a camel next to a stream",
"a delicate porcelain teacup sits on a saucer, its surface adorned with intricate blue patterns",
"a baby swan grafitti",
"A bald eagle made of chocolate powder, mango, and whipped cream"
]

with gr.Blocks(theme=gr.themes.Base()) as demo:
    gr.Markdown("## One step Juggernaut-XL comparison 🦶")
    gr.Markdown('Compare Juggernaut-XL variants and distillations able to generate images in a single diffusion step')
    prompt = gr.Textbox(label="Prompt")
    run = gr.Button("Run")
    with gr.Row(visible=True):
            style_selection = gr.Radio(
                show_label=True,
                container=True,
                interactive=True,
                choices=STYLE_NAMES,
                value=DEFAULT_STYLE_NAME,
                label="Image Style",
            )
    with gr.Accordion("Advanced options", open=False):
        use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=False, visible=True)
        negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=True,
            )
        with gr.Row():
            num_inference_steps = gr.Slider(
                label="Steps",
                minimum=10,
                maximum=60,
                step=1,
                value=30,
            )
        with gr.Row():
            num_images_per_prompt = gr.Slider(
                label="Images",
                minimum=1,
                maximum=5,
                step=1,
                value=2,
            )
        seed = gr.Slider(
            label="Seed",
            minimum=0,
            maximum=MAX_SEED,
            step=1,
            value=0,
            visible=True
        )
        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
        with gr.Row(visible=True):
            width = gr.Slider(
                label="Width",
                minimum=512,
                maximum=2048,
                step=8,
                value=1024,
            )
            height = gr.Slider(
                label="Height",
                minimum=512,
                maximum=2048,
                step=8,
                value=1024,
            )
        with gr.Row():
            guidance_scale = gr.Slider(
                label="Guidance Scale",
                minimum=0.1,
                maximum=20.0,
                step=0.1,
                value=6,
            )

    with gr.Row():
        with gr.Column():
            image_r3 = gr.Gallery(label="Juggernaut-X",columns=1, preview=True,)
            gr.Markdown("## [Juggernaut-X](https://huggingface.co)")
        with gr.Column():
            image_r4 = gr.Gallery(label="Juggernaut-X-10",columns=1, preview=True,)
            gr.Markdown("## [Juggernaut-XL-10](https://huggingface.co)")
        with gr.Column():
            image_r5 = gr.Gallery(label="Juggernaut-XL-9",columns=1, preview=True,)
            gr.Markdown("## [Juggernaut-XL-9](https://huggingface.co)") 
        with gr.Column():
            image_r6 = gr.Gallery(label="Juggernaut-XL-8",columns=1, preview=True,)
            gr.Markdown("## [Juggernaut-XL-8](https://huggingface.co)")
        with gr.Column():
            image_r7 = gr.Gallery(label="Juggernaut-XL-7",columns=1, preview=True,)
            gr.Markdown("## [Juggernaut-XL-7](https://huggingface.co)")
        with gr.Column():
            image_r8 = gr.Gallery(label="Juggernaut-XL",columns=1, preview=True,)
            gr.Markdown("## [Juggernaut-XL](https://huggingface.co)")
    image_outputs = [image_r3, image_r4, image_r5, image_r6, image_r7, image_r8]
    gr.on(
        triggers=[prompt.submit, run.click],
        fn=run_comparison,
        inputs=[
           prompt,
           negative_prompt,
           style_selection,
           use_negative_prompt,
           num_inference_steps,
           num_images_per_prompt,
           seed,
           width,
           height,
           guidance_scale,
           randomize_seed,
       ],
        outputs=image_outputs
    )
    use_negative_prompt.change(
        fn=lambda x: gr.update(visible=x),
        inputs=use_negative_prompt,
        outputs=negative_prompt,
        api_name=False,
    )
    gr.Examples(
        examples=examples,
        fn=run_comparison,
        inputs=prompt,
        outputs=image_outputs,
        cache_examples=False,
        run_on_click=True
    )
if __name__ == "__main__":
    demo.queue(max_size=20).launch(show_api=False, debug=False)