import gradio as gr from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler, LCMScheduler, AutoencoderKL,DiffusionPipeline import torch 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) ### RealVisXL V3 ### RealVisXLv3_pipe = DiffusionPipeline.from_pretrained( "SG161222/RealVisXL_V3.0", torch_dtype=torch.float16, use_safetensors=True, add_watermarker=False, variant="fp16" ) RealVisXLv3_pipe.to("cuda") ### RealVisXL V4 ### RealVisXLv4_pipe = DiffusionPipeline.from_pretrained( "SG161222/RealVisXL_V4.0", torch_dtype=torch.float16, use_safetensors=True, add_watermarker=False, variant="fp16" ) RealVisXLv4_pipe.to("cuda") ## playground V2.5## playground_pipe = DiffusionPipeline.from_pretrained( "playgroundai/playground-v2.5-1024px-aesthetic", torch_dtype=torch.float16, use_safetensors=True, add_watermarker=False, variant="fp16" ) playground_pipe.to("cuda") @spaces.GPU def run_comparison(prompt: str, negative_prompt: str = "", 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 = "" image_r3 = RealVisXLv3_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 = RealVisXLv4_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 = playground_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 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() as demo: gr.Markdown("## One step SDXL comparison 🦶") gr.Markdown('Compare SDXL variants and distillations able to generate images in a single diffusion step') prompt = gr.Textbox(label="Prompt") run = gr.Button("Run") with gr.Accordion("Advanced options", open=False): use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True) negative_prompt = gr.Text( label="Negative prompt", lines=4, max_lines=6, value="""(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, (NSFW:1.25)""", 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="RealVisXL V3",columns=1, preview=True,) gr.Markdown("## [RealVisXL V3](https://huggingface.co)") with gr.Column(): image_r4 = gr.Gallery(label="RealVisXL V4",columns=1, preview=True,) gr.Markdown("## [RealVisXL V4](https://huggingface.co)") with gr.Column(): image_r5 = gr.Gallery(label="Playground v2.5",columns=1, preview=True,) gr.Markdown("## [Playground v2.5](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, 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)