from diffusers import AutoencoderKL, UNet2DConditionModel, StableDiffusionPipeline, StableDiffusionImg2ImgPipeline, DPMSolverMultistepScheduler 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 self.pipe_t2i = None self.pipe_i2i = None models = [ Model("Beeple", "riccardogiorato/beeple-diffusion", "beeple style "), Model("Avatar", "riccardogiorato/avatar-diffusion", "avatartwow style "), Model("Poolsuite", "prompthero/poolsuite", "poolsuite style "), Model("Robo Diffusion", "nousr/robo-diffusion", "") ] # Model("Beksinski", "s3nh/beksinski-style-stable-diffusion", "beksinski style "), # Model("Guohua", "Langboat/Guohua-Diffusion", "guohua style ") 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, ) custom_model = None if is_colab: models.insert(0, Model("Custom model", "", "")) custom_model = models[0] last_mode = "txt2img" current_model = models[1] if is_colab else models[0] current_model_path = current_model.path if is_colab: pipe = StableDiffusionPipeline.from_pretrained(current_model.path, torch_dtype=torch.float16, scheduler=scheduler) else: # download all models vae = AutoencoderKL.from_pretrained(current_model.path, subfolder="vae", torch_dtype=torch.float16) for model in models: try: unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet", torch_dtype=torch.float16) model.pipe_t2i = StableDiffusionPipeline.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler) model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler) except: models.remove(model) pipe = models[0].pipe_t2i if torch.cuda.is_available(): pipe = pipe.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 if is_colab or current_model == custom_model: pipe = StableDiffusionPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16, scheduler=scheduler) else: 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 if is_colab or current_model == custom_model: pipe = StableDiffusionImg2ImgPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16, scheduler=scheduler) else: 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 = """.finetuned-diffusion-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.finetuned-diffusion-div div h1{font-weight:900;margin-bottom:7px}.finetuned-diffusion-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem} """ with gr.Blocks(css=css) as demo: gr.HTML( f"""
Demo for multiple fine-tuned Stable Diffusion models, trained on different styles:
Avatar,
Beeple,
Beksinski,
Diffusers 🧨 SD model hosted on HuggingFace 🤗.
Running on {device}{(" in a Google Colab." if is_colab else "")}
Models by @riccardogiorato