from diffusers import AutoencoderKL, UNet2DConditionModel, StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, UniPCMultistepScheduler from diffusers import StableDiffusionXLPipeline from diffusers import StableDiffusionXLImg2ImgPipeline import gradio as gr import torch from PIL import Image import os scheduler = UniPCMultistepScheduler( beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000, trained_betas=None, thresholding=False, predict_x0=True, solver_type="bh2", lower_order_final=True, disable_corrector=[0], ) 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-XL", "stabilityai/stable-diffusion-xl-base-1.0", "The XL version of official stable-diffusion"), Model("Stable-Diffusion-v1.4", "CompVis/stable-diffusion-v1-4", "The 1.4 version of official stable-diffusion"), Model("Waifu", "hakurei/waifu-diffusion", "anime style"), ] 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: if 'XL'in model.name: PipeClass = StableDiffusionXLPipeline PipeI2IClass = StableDiffusionXLImg2ImgPipeline else: PipeClass = StableDIffusionXPipeline PipeI2IClass = StableDiffusionImg2ImgPipeline unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet", torch_dtype=torch.float16, use_auth_token=auth_token) model.pipe_t2i = PipeClass.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler, use_auth_token=auth_token) model.pipe_i2i = PipeI2IClass.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, 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)): try: if results.nsfw_content_detected[i]: results.images[i] = Image.open("nsfw.png") except: pass return results.images[0] css = """ """ with gr.Blocks(css=css) as demo: gr.HTML( f"""
❤️ Acknowledgement: Hardware resources of this demo are supported by HuggingFace 🤗 . Many thanks for the help!
This is a demo of sampling by UniPC with two variants of Stable Diffusion models, including Stable-Diffusion-v1.4 and Waifu.
UniPC is a training-free framework designed for the fast sampling of diffusion models, which consists of a corrector (UniC) and a predictor (UniP) that share a unified analytical form and support arbitrary orders.
We use Diffusers 🧨 to implement this demo, which currently supports the multistep UniPC scheduler. For more details of UniPC with Diffusers, check this pull request.
Running on {device}