from diffusers import AutoencoderKL, UNet2DConditionModel from diffusers import StableDiffusionPipeline from diffusers import StableDiffusionImg2ImgPipeline import gradio as gr import torch from PIL import Image import utils is_colab = utils.is_google_colab() class Model: def __init__(self, name, path, prefix): self.name = name self.path = path self.prefix = prefix models = [ Model("Custom model", "", ""), Model("Arcane", "nitrosocke/Arcane-Diffusion", "arcane style "), Model("Archer", "nitrosocke/archer-diffusion", "archer style "), Model("Elden Ring", "nitrosocke/elden-ring-diffusion", "elden ring style "), Model("Spider-Verse", "nitrosocke/spider-verse-diffusion", "spiderverse style "), Model("Modern Disney", "nitrosocke/modern-disney-diffusion", "modern disney style "), Model("Classic Disney", "nitrosocke/classic-anim-diffusion", ""), Model("Waifu", "hakurei/waifu-diffusion", ""), Model("Pokémon", "lambdalabs/sd-pokemon-diffusers", ""), Model("Pony Diffusion", "AstraliteHeart/pony-diffusion", ""), Model("Robo Diffusion", "nousr/robo-diffusion", ""), Model("Cyberpunk Anime", "DGSpitzer/Cyberpunk-Anime-Diffusion", "dgs illustration style "), Model("Tron Legacy", "dallinmackay/Tron-Legacy-diffusion", "trnlgcy ") ] last_mode = "txt2img" current_model = models[1] current_model_path = current_model.path pipe = StableDiffusionPipeline.from_pretrained(current_model.path, torch_dtype=torch.float16) # pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(current_model.path, torch_dtype=torch.float16) if torch.cuda.is_available(): pipe = pipe.to("cuda") # pipe_i2i = pipe_i2i.to("cuda") device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶" def custom_model_changed(path): models[0].path = path global current_model current_model = models[0] def inference(model_name, prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt=""): global current_model for model in models: if model.name == model_name: current_model = model model_path = current_model.path generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None if img is not None: return img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator) else: return txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator) def txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator=None): global last_mode global pipe global current_model_path if model_path != current_model_path or last_mode != "txt2img": current_model_path = model_path pipe = StableDiffusionPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16) if torch.cuda.is_available(): pipe = pipe.to("cuda") last_mode = "txt2img" prompt = current_model.prefix + prompt result = pipe( prompt, negative_prompt = neg_prompt, # num_images_per_prompt=n_images, num_inference_steps = int(steps), guidance_scale = guidance, width = width, height = height, generator = generator) return replace_nsfw_images(result) def img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator=None): global last_mode global pipe global current_model_path if model_path != current_model_path or last_mode != "img2img": current_model_path = model_path pipe = StableDiffusionImg2ImgPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16) if torch.cuda.is_available(): pipe = pipe.to("cuda") last_mode = "img2img" prompt = current_model.prefix + prompt ratio = min(height / img.height, width / img.width) img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS) result = pipe( prompt, negative_prompt = neg_prompt, # num_images_per_prompt=n_images, init_image = img, num_inference_steps = int(steps), strength = strength, guidance_scale = guidance, width = width, height = height, generator = generator) return replace_nsfw_images(result) def replace_nsfw_images(results): for i in range(len(results.images)): if results.nsfw_content_detected[i]: results.images[i] = Image.open("nsfw.png") return results.images[0] css = """ """ with gr.Blocks(css=css) as demo: gr.HTML( f"""

Finetuned Diffusion

Demo for multiple fine-tuned Stable Diffusion models, trained on different styles:
Arcane, Archer, Elden Ring, Spiderverse, Modern Disney, Waifu, Pokemon, Fuyuko Waifu, Pony, Hergé (Tintin), Robo, Cyberpunk Anime + any other custom Diffusers 🧨 SD model hosted on HuggingFace 🤗.

Don't want to wait in queue? Open In Colab

Running on {device}

""" ) with gr.Row(): with gr.Group(): model_name = gr.Dropdown(label="Model", choices=[m.name for m in models], value=current_model.name) custom_model_path = gr.Textbox(label="Custom model path", placeholder="Path to model, e.g. nitrosocke/Arcane-Diffusion", visible=False, interactive=True) with gr.Row(): prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="Enter prompt. Style applied automatically").style(container=False) generate = gr.Button(value="Generate").style(rounded=(False, True, True, False)) image_out = gr.Image(height=512) # gallery = gr.Gallery( # label="Generated images", show_label=False, elem_id="gallery" # ).style(grid=[1], height="auto") with gr.Tab("Options"): with gr.Group(): neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image") # n_images = gr.Slider(label="Images", value=1, minimum=1, maximum=4, step=1) with gr.Row(): guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=15) steps = gr.Slider(label="Steps", value=50, minimum=2, maximum=100, step=1) with gr.Row(): width = gr.Slider(label="Width", value=512, minimum=64, maximum=1024, step=8) height = gr.Slider(label="Height", value=512, minimum=64, maximum=1024, step=8) seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1) with gr.Tab("Image to image"): with gr.Group(): image = gr.Image(label="Image", height=256, tool="editor", type="pil") strength = gr.Slider(label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5) model_name.change(lambda x: gr.update(visible = x == models[0].name), inputs=model_name, outputs=custom_model_path) custom_model_path.change(custom_model_changed, inputs=custom_model_path, outputs=None) # n_images.change(lambda n: gr.Gallery().style(grid=[2 if n > 1 else 1], height="auto"), inputs=n_images, outputs=gallery) inputs = [model_name, prompt, guidance, steps, width, height, seed, image, strength, neg_prompt] prompt.submit(inference, inputs=inputs, outputs=image_out) generate.click(inference, inputs=inputs, outputs=image_out) ex = gr.Examples([ [models[1].name, "jason bateman disassembling the demon core", 7.5, 50], [models[4].name, "portrait of dwayne johnson", 7.0, 75], [models[5].name, "portrait of a beautiful alyx vance half life", 10, 50], [models[6].name, "Aloy from Horizon: Zero Dawn, half body portrait, smooth, detailed armor, beautiful face, illustration", 7.0, 45], [models[5].name, "fantasy portrait painting, digital art", 4.0, 30], ], [model_name, prompt, guidance, steps, seed], image_out, inference, cache_examples=not is_colab and torch.cuda.is_available()) # ex.dataset.headers = [""] gr.Markdown(''' Models by [@nitrosocke](https://huggingface.co/nitrosocke), [@Helixngc7293](https://twitter.com/DGSpitzer) and others. ❤️
Space by: [![Twitter Follow](https://img.shields.io/twitter/follow/hahahahohohe?label=%40anzorq&style=social)](https://twitter.com/hahahahohohe) ![visitors](https://visitor-badge.glitch.me/badge?page_id=anzorq.finetuned_diffusion) ''') if not is_colab: demo.queue(concurrency_count=4) demo.launch(debug=is_colab, share=is_colab)