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") @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 = 1, 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] return image_paths_r3, image_paths_r4,image_paths_r5, seed examples = [ "A realistic family photograph with a mother, a father, and 2 young daughters", "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=1, ) 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)") image_outputs = [image_r3, image_r4, image_r5] 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)