import gradio as gr import numpy as np import time import math import random import torch import spaces from diffusers import StableDiffusionXLInpaintPipeline from PIL import Image, ImageFilter from pillow_heif import register_heif_opener register_heif_opener() max_64_bit_int = np.iinfo(np.int32).max if torch.cuda.is_available(): device = "cuda" floatType = torch.float16 variant = "fp16" else: device = "cpu" floatType = torch.float32 variant = None pipe = StableDiffusionXLInpaintPipeline.from_pretrained("diffusers/stable-diffusion-xl-1.0-inpainting-0.1", torch_dtype = floatType, variant = variant) pipe = pipe.to(device) def update_seed(is_randomize_seed, seed): if is_randomize_seed: return random.randint(0, max_64_bit_int) return seed def toggle_debug(is_debug_mode): return [gr.update(visible = is_debug_mode)] * 3 def noise_color(color, noise): return color + random.randint(- noise, noise) def check( input_image, enlarge_top, enlarge_right, enlarge_bottom, enlarge_left, prompt, negative_prompt, smooth_border, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, is_randomize_seed, seed, debug_mode, progress = gr.Progress()): if input_image is None: raise gr.Error("Please provide an image.") if prompt is None or prompt == "": raise gr.Error("Please provide a prompt input.") if (not (enlarge_top is None)) and enlarge_top < 0: raise gr.Error("Please provide positive top margin.") if (not (enlarge_right is None)) and enlarge_right < 0: raise gr.Error("Please provide positive right margin.") if (not (enlarge_bottom is None)) and enlarge_bottom < 0: raise gr.Error("Please provide positive bottom margin.") if (not (enlarge_left is None)) and enlarge_left < 0: raise gr.Error("Please provide positive left margin.") if ( (enlarge_top is None or enlarge_top == 0) and (enlarge_right is None or enlarge_right == 0) and (enlarge_bottom is None or enlarge_bottom == 0) and (enlarge_left is None or enlarge_left == 0) ): raise gr.Error("At least one border must be enlarged.") def uncrop( input_image, enlarge_top, enlarge_right, enlarge_bottom, enlarge_left, prompt, negative_prompt, smooth_border, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, is_randomize_seed, seed, debug_mode, progress = gr.Progress()): check( input_image, enlarge_top, enlarge_right, enlarge_bottom, enlarge_left, prompt, negative_prompt, smooth_border, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, is_randomize_seed, seed, debug_mode ) start = time.time() progress(0, desc = "Preparing data...") if enlarge_top is None or enlarge_top == "": enlarge_top = 0 if enlarge_right is None or enlarge_right == "": enlarge_right = 0 if enlarge_bottom is None or enlarge_bottom == "": enlarge_bottom = 0 if enlarge_left is None or enlarge_left == "": enlarge_left = 0 if negative_prompt is None: negative_prompt = "" if smooth_border is None: smooth_border = 0 if num_inference_steps is None: num_inference_steps = 50 if guidance_scale is None: guidance_scale = 7 if image_guidance_scale is None: image_guidance_scale = 1.5 if strength is None: strength = 0.99 if denoising_steps is None: denoising_steps = 1000 if seed is None: seed = random.randint(0, max_64_bit_int) random.seed(seed) torch.manual_seed(seed) original_height, original_width, original_channel = np.array(input_image).shape output_width = enlarge_left + original_width + enlarge_right output_height = enlarge_top + original_height + enlarge_bottom # Enlarged image enlarged_image = Image.new(mode = input_image.mode, size = (original_width, original_height), color = "black") enlarged_image.paste(input_image, (0, 0)) enlarged_image = enlarged_image.resize((output_width, output_height)) enlarged_image = enlarged_image.filter(ImageFilter.BoxBlur(20)) enlarged_image.paste(input_image, (enlarge_left, enlarge_top)) horizontally_mirrored_input_image = input_image.transpose(Image.FLIP_LEFT_RIGHT).resize((original_width * 2, original_height)) enlarged_image.paste(horizontally_mirrored_input_image, (enlarge_left - (original_width * 2), enlarge_top)) enlarged_image.paste(horizontally_mirrored_input_image, (enlarge_left + original_width, enlarge_top)) vertically_mirrored_input_image = input_image.transpose(Image.FLIP_TOP_BOTTOM).resize((original_width, original_height * 2)) enlarged_image.paste(vertically_mirrored_input_image, (enlarge_left, enlarge_top - (original_height * 2))) enlarged_image.paste(vertically_mirrored_input_image, (enlarge_left, enlarge_top + original_height)) returned_input_image = input_image.transpose(Image.ROTATE_180).resize((original_width * 2, original_height * 2)) enlarged_image.paste(returned_input_image, (enlarge_left - (original_width * 2), enlarge_top - (original_height * 2))) enlarged_image.paste(returned_input_image, (enlarge_left - (original_width * 2), enlarge_top + original_height)) enlarged_image.paste(returned_input_image, (enlarge_left + original_width, enlarge_top - (original_height * 2))) enlarged_image.paste(returned_input_image, (enlarge_left + original_width, enlarge_top + original_height)) enlarged_image = enlarged_image.filter(ImageFilter.BoxBlur(20)) # Noise image noise_image = Image.new(mode = input_image.mode, size = (output_width, output_height), color = "black") enlarged_pixels = enlarged_image.load() for i in range(output_width): for j in range(output_height): enlarged_pixel = enlarged_pixels[i, j] noise = min(max(enlarge_left - i, i - (enlarge_left + original_width), enlarge_top - j, j - (enlarge_top + original_height), 0), 255) noise_image.putpixel((i, j), (noise_color(enlarged_pixel[0], noise), noise_color(enlarged_pixel[1], noise), noise_color(enlarged_pixel[2], noise), 255)) enlarged_image.paste(noise_image, (0, 0)) enlarged_image.paste(input_image, (enlarge_left, enlarge_top)) # Mask mask_image = Image.new(mode = input_image.mode, size = (output_width, output_height), color = (255, 255, 255, 0)) black_mask = Image.new(mode = input_image.mode, size = (original_width - smooth_border, original_height - smooth_border), color = (0, 0, 0, 0)) mask_image.paste(black_mask, (enlarge_left + (smooth_border // 2), enlarge_top + (smooth_border // 2))) mask_image = mask_image.filter(ImageFilter.BoxBlur((smooth_border // 2))) # 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) if torch.cuda.is_available(): progress(None, desc = "Searching a GPU...") output_image = uncrop_on_gpu( seed, process_width, process_height, prompt, negative_prompt, enlarged_image, mask_image, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, progress ) if limitation != "": output_image = output_image.resize((output_width, output_height)) if debug_mode == False: input_image = None enlarged_image = None mask_image = None end = time.time() secondes = int(end - start) minutes = math.floor(secondes / 60) secondes = secondes - (minutes * 60) hours = math.floor(minutes / 60) minutes = minutes - (hours * 60) return [ output_image, ("Start again to get a different result. " if is_randomize_seed else "") + "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 has been generated in " + ((str(hours) + " h, ") if hours != 0 else "") + ((str(minutes) + " min, ") if hours != 0 or minutes != 0 else "") + str(secondes) + " sec." + limitation, input_image, enlarged_image, mask_image ] @spaces.GPU(duration=420) def uncrop_on_gpu( seed, process_width, process_height, prompt, negative_prompt, enlarged_image, mask_image, num_inference_steps, guidance_scale, image_guidance_scale, strength, denoising_steps, progress): progress(None, desc = "Processing...") return pipe( seeds = [seed], width = process_width, height = process_height, prompt = prompt, negative_prompt = negative_prompt, image = enlarged_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] with gr.Blocks() as interface: gr.HTML( """
Enlarges the point of view of your image, freely, without account, without watermark, without installation, which can be downloaded