import gradio as gr import numpy as np import random import spaces #[uncomment to use ZeroGPU] from diffusers import StableDiffusionXLPipeline, AutoencoderKL, StableDiffusionXLImg2ImgPipeline import torch from typing import Tuple device = "cuda" if torch.cuda.is_available() else "cpu" model_repo_id = "RunDiffusion/Juggernaut-XL-v9" # Replace to the model you would like to use vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16) if torch.cuda.is_available(): torch_dtype = torch.float16 else: torch_dtype = torch.float32 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", ) pipe.to(device) pipe_img2img = StableDiffusionXLImg2ImgPipeline.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", ) pipe_img2img.to(device) MAX_SEED = np.iinfo(np.int32).max MAX_IMAGE_SIZE = 4096 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 @spaces.GPU #[uncomment to use ZeroGPU] def infer( prompt, negative_prompt, style, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, input_image=None, # New parameter for input image strength=0.8, # New parameter for img2img strength progress=gr.Progress(track_tqdm=True), ): if randomize_seed: seed = random.randint(0, MAX_SEED) prompt, negative_prompt = apply_style(style, prompt, negative_prompt) generator = torch.Generator().manual_seed(seed) if input_image is not None: # Use img2img pipeline if an image is provided image = pipe_img2img( prompt=prompt, image=input_image, # Pass the input image strength=strength, # Control how much the image is changed negative_prompt=negative_prompt, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps, generator=generator, ).images[0] else: # Use text2img pipeline otherwise 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] return image, seed examples = [ "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", "An astronaut riding a green horse", "A delicious ceviche cheesecake slice", ] css = """ #col-container { margin: 0 auto; max-width: 640px; } """ with gr.Blocks(css=css) as demo: with gr.Column(elem_id="col-container"): gr.Markdown(" # ImageGen, the fastest and most precise image generator") 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, variant="primary") result = gr.Image(label="Result", show_label=False) # Add image input and strength slider with gr.Row(): input_image = gr.Image(type="pil", label="Input Image (Optional)", show_label=True, height=200) with gr.Column(): strength = gr.Slider( label="Image Strength", minimum=0.0, maximum=1.0, step=0.01, value=0.8, # Default strength for img2img visible=True, # Make it visible if you want it always there, or toggle visibility with JS ) 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 Settings", open=False): negative_prompt = gr.Text( 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=32, value=4096, # Replace with defaults that work for your model ) height = gr.Slider( label="Height", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=4096, # Replace with defaults that work for your model ) with gr.Row(): guidance_scale = gr.Slider( label="Guidance scale", minimum=0.0, maximum=10.0, step=0.1, value=0.0, # Replace with defaults that work for your model ) num_inference_steps = gr.Slider( label="Number of inference steps", minimum=1, maximum=500, step=1, value=500, # Replace with defaults that work for your model ) gr.Examples(examples=examples, inputs=[prompt]) gr.on( triggers=[run_button.click, prompt.submit], fn=infer, inputs=[ prompt, negative_prompt, style_selection, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, input_image, # Add input_image to inputs strength, # Add strength to inputs ], outputs=[result, seed], ) if __name__ == "__main__": demo.launch(share=True)