from diffusers import LatentDiffusionUncondPipeline import torch import PIL.Image import gradio as gr pipeline = LatentDiffusionUncondPipeline.from_pretrained("CompVis/latent-diffusion-celeba-256") def predict(seed): torch.manual_seed(seed) image = pipeline(generator=generator, num_inference_steps=1)["sample"] image_processed = image.cpu().permute(0, 2, 3, 1) image_processed = (image_processed + 1.0) * 127.5 image_processed = image_processed.clamp(0, 255).numpy().astype(np.uint8) return PIL.Image.fromarray(image_processed[0]) gr.Interface( predict, inputs=[ gr.inputs.Slider(0, 1000, label='Seed', default=42), ], outputs="image", ).launch()