from diffusers import AutoencoderKL, UNet2DConditionModel, StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler import gradio as gr import torch from PIL import Image import os scheduler = DPMSolverMultistepScheduler( beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000, trained_betas=None, predict_epsilon=True, thresholding=False, algorithm_type="dpmsolver++", solver_type="midpoint", lower_order_final=True, ) def is_google_colab(): try: import google.colab return True except: return False is_colab = is_google_colab() class Model: def __init__(self, name, path, prefix): self.name = name self.path = path self.prefix = prefix self.pipe_t2i = None self.pipe_i2i = None models = [ Model("Stable-Diffusion-v1.4", "CompVis/stable-diffusion-v1-4", "The 1.4 version of official stable-diffusion"), # Model("Stable-Diffusion-v1.5", "runwayml/stable-diffusion-v1-5", "The 1.5 version of official stable-diffusion"), # 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/mo-di-diffusion", "modern disney style "), # Model("Classic Disney", "nitrosocke/classic-anim-diffusion", "classic disney style "), # 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[0] current_model_path = current_model.path auth_token = os.getenv("HUGGING_FACE_HUB_TOKEN") print(f"Is CUDA available: {torch.cuda.is_available()}") if torch.cuda.is_available(): vae = AutoencoderKL.from_pretrained(current_model.path, subfolder="vae", torch_dtype=torch.float16, use_auth_token=auth_token) for model in models: try: unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet", torch_dtype=torch.float16, use_auth_token=auth_token) model.pipe_t2i = StableDiffusionPipeline.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler, use_auth_token=auth_token) model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler, use_auth_token=auth_token) except: models.remove(model) pipe = models[0].pipe_t2i pipe = pipe.to("cuda") else: vae = AutoencoderKL.from_pretrained(current_model.path, subfolder="vae", use_auth_token=auth_token) for model in models: try: unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet", use_auth_token=auth_token) model.pipe_t2i = StableDiffusionPipeline.from_pretrained(model.path, unet=unet, vae=vae, scheduler=scheduler, use_auth_token=auth_token) model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(model.path, unet=unet, vae=vae, scheduler=scheduler, use_auth_token=auth_token) except: models.remove(model) pipe = models[0].pipe_t2i pipe = pipe.to("cpu") device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶" 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' if torch.cuda.is_available() else 'cpu').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.to("cpu") pipe = current_model.pipe_t2i 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.to("cpu") pipe = current_model.pipe_i2i 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 with DPM-Solver (fastest sampler for diffusion models)


DPM-Solver (Neurips 2022 Oral) is a fast high-order solver customized for diffusion ODEs, which can generate high-quality samples by diffusion models within only 10-25 steps. DPM-Solver has an analytical formulation and is very easy to use for all types of Gaussian diffusion models, and includes DDIM as a first-order special case.

We use Diffusers to implement this demo, which currently supports the multistep DPM-Solver scheduler. For more details of DPM-Solver with Diffusers, check this pull request.


Demo for sampling by DPM-Solver with several fine-tuned Stable Diffusion models, trained on different styles:
Stable-Diffusion-v1.4, Elden Ring, Waifu, Pokémon, Pony Diffusion, Robo Diffusion, Cyberpunk Anime, Tron Legacy + any other custom Diffusers 🧨 SD model hosted on HuggingFace 🤗.

""" ) # TODO: the colab version is wrong. #

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

# Running on {device}{(" in a Google Colab." if is_colab else "")} #

# TODO: do not support the custom model with gr.Row(): with gr.Column(scale=55): with gr.Group(): model_name = gr.Dropdown(label="Model", choices=[m.name for m in models], value=current_model.name) 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.Column(scale=45): 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=25, 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_group) # 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) # TODO: the docs here are wrong. # ex = gr.Examples([ # [models[1].name, "jason bateman disassembling the demon core", 7.5, 50], # # [models[1+2].name, "jason bateman disassembling the demon core", 7.5, 50], # # [models[4+2].name, "portrait of dwayne johnson", 7.0, 75], # # [models[5+2].name, "portrait of a beautiful alyx vance half life", 10, 50], # # [models[6+2].name, "Aloy from Horizon: Zero Dawn, half body portrait, smooth, detailed armor, beautiful face, illustration", 7.0, 45], # # [models[5+2].name, "fantasy portrait painting, digital art", 4.0, 30], # ], [model_name, prompt, guidance, steps, seed], image_out, inference, cache_examples=False) gr.Markdown(''' Models by [@nitrosocke](https://huggingface.co/nitrosocke), [@haruu1367](https://twitter.com/haruu1367), [@Helixngc7293](https://twitter.com/DGSpitzer) and others. Code are copied from [@anzorq's fintuned_diffusion](https://huggingface.co/spaces/anzorq/finetuned_diffusion/tree/main) ❤️
Space by: [![Twitter Follow](https://img.shields.io/twitter/follow/ChengLu05671218?label=%40ChengLu&style=social)](https://twitter.com/ChengLu05671218) ![visitors](https://visitor-badge.glitch.me/badge?page_id=LuChengTHU.dpmsolver_sdm) ''') if not is_colab: demo.queue(concurrency_count=1) demo.launch(debug=is_colab, share=is_colab)