from diffusers import StableDiffusionXLInpaintPipeline from PIL import Image, ImageFilter import gradio as gr import numpy as np import time import math import random import imageio import torch max_64_bit_int = 2**63 - 1 device = "cuda" if torch.cuda.is_available() else "cpu" floatType = torch.float16 if torch.cuda.is_available() else torch.float32 variant = "fp16" if torch.cuda.is_available() else None pipe = StableDiffusionXLInpaintPipeline.from_pretrained("diffusers/stable-diffusion-xl-1.0-inpainting-0.1", torch_dtype = floatType, variant = variant) pipe = pipe.to(device) def check( source_img, prompt, uploaded_mask, negative_prompt, denoising_steps, num_inference_steps, guidance_scale, image_guidance_scale, strength, randomize_seed, seed, debug_mode, progress = gr.Progress() ): if source_img is None: raise gr.Error("Please provide an image.") if prompt is None or prompt == "": raise gr.Error("Please provide a prompt input.") def inpaint( source_img, prompt, uploaded_mask, negative_prompt, denoising_steps, num_inference_steps, guidance_scale, image_guidance_scale, strength, randomize_seed, seed, debug_mode, progress = gr.Progress() ): check( source_img, prompt, uploaded_mask, negative_prompt, denoising_steps, num_inference_steps, guidance_scale, image_guidance_scale, strength, randomize_seed, seed, debug_mode ) start = time.time() progress(0, desc = "Preparing data...") if negative_prompt is None: negative_prompt = "" if denoising_steps is None: denoising_steps = 1000 if num_inference_steps is None: num_inference_steps = 25 if guidance_scale is None: guidance_scale = 7 if image_guidance_scale is None: image_guidance_scale = 1.1 if strength is None: strength = 0.99 if randomize_seed: seed = random.randint(0, max_64_bit_int) random.seed(seed) #pipe = pipe.manual_seed(seed) input_image = source_img["image"].convert("RGB") original_height, original_width, original_channel = np.array(input_image).shape output_width = original_width output_height = original_height if uploaded_mask is None: mask_image = source_img["mask"].convert("RGB") else: mask_image = uploaded_mask.convert("RGB") mask_image = mask_image.resize((original_width, original_height)) # Limited to 1 million pixels if 1024 * 1024 < output_width * output_height: factor = ((1024 * 1024) / (output_width * output_height))**0.5 process_width = math.floor(output_width * factor) process_height = math.floor(output_height * factor) limitation = " Due to technical limitation, the image have been downscaled and then upscaled."; else: process_width = output_width process_height = output_height limitation = ""; # Width and height must be multiple of 8 if (process_width % 8) != 0 or (process_height % 8) != 0: if ((process_width - (process_width % 8) + 8) * (process_height - (process_height % 8) + 8)) <= (1024 * 1024): process_width = process_width - (process_width % 8) + 8 process_height = process_height - (process_height % 8) + 8 elif (process_height % 8) <= (process_width % 8) and ((process_width - (process_width % 8) + 8) * process_height) <= (1024 * 1024): process_width = process_width - (process_width % 8) + 8 process_height = process_height - (process_height % 8) elif (process_width % 8) <= (process_height % 8) and (process_width * (process_height - (process_height % 8) + 8)) <= (1024 * 1024): process_width = process_width - (process_width % 8) process_height = process_height - (process_height % 8) + 8 else: process_width = process_width - (process_width % 8) process_height = process_height - (process_height % 8) progress(None, desc = "Processing...") output_image = pipe( seeds = [seed], width = process_width, height = process_height, prompt = prompt, negative_prompt = negative_prompt, image = input_image, mask_image = mask_image, num_inference_steps = num_inference_steps, guidance_scale = guidance_scale, image_guidance_scale = image_guidance_scale, strength = strength, denoising_steps = denoising_steps, show_progress_bar = True ).images[0] if limitation != "": output_image = output_image.resize((output_width, output_height)) if debug_mode == False: input_image = None mask_image = None end = time.time() secondes = int(end - start) minutes = secondes // 60 secondes = secondes - (minutes * 60) hours = minutes // 60 minutes = minutes - (hours * 60) return [ output_image, "Start again to get a different result. The new image is " + str(output_width) + " pixels large and " + str(output_height) + " pixels high, so an image of " + f'{output_width * output_height:,}' + " pixels. The image have been generated in " + str(hours) + " h, " + str(minutes) + " min, " + str(secondes) + " sec." + limitation, input_image, mask_image ] def toggle_debug(is_debug_mode): if is_debug_mode: return [gr.update(visible = True)] * 2 else: return [gr.update(visible = False)] * 2 with gr.Blocks() as interface: gr.Markdown( """
Inpaint
Modifies one detail of your image, at any resolution, freely, without account, without watermark, without installation, which can be downloaded