from diffusers import StableDiffusionXLInpaintPipeline import gradio as gr import numpy as np import math import random import imageio from PIL import Image from PIL import ImageFilter import torch import modin.pandas as pd max_64_bit_int = 2**63 - 1 device = "cuda" if torch.cuda.is_available() else "cpu" pipe = StableDiffusionXLInpaintPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", safety_checker = None) pipe = pipe.to(device) def noise_color(color, noise): return color + random.randint(- noise, noise) def predict(source_img, enlarge_top, enlarge_right, enlarge_bottom, enlarge_left, prompt, negative_prompt, denoising_steps, num_inference_steps, guidance_scale, randomize_seed, seed, progress=gr.Progress()): progress(0, desc = "Preparing data...") 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.") if negative_prompt is None or negative_prompt == "": raise gr.Error("Please provide a negative prompt input.") if enlarge_top < 0 or enlarge_right < 0 or enlarge_bottom < 0 or enlarge_left < 0: raise gr.Error("Please only provide positive margins.") if enlarge_top == 0 and enlarge_right == 0 and enlarge_bottom == 0 and enlarge_left == 0: raise gr.Error("At least one border must be enlarged.") if randomize_seed: seed = random.randint(0, max_64_bit_int) random.seed(seed) #pipe = pipe.manual_seed(seed) imageio.imwrite("data.png", source_img) # Input image input_image = Image.open("data.png").convert("RGB") 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_height, original_width), 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(25)) 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(25)) # 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 = max(min(abs(enlarge_left - i), abs(enlarge_top + original_width - i), abs(enlarge_top - j), abs(enlarge_top + original_height - j), 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 - 20, original_height - 20), color = (0, 0, 0, 0)) mask_image.paste(black_mask, (enlarge_left + 10, enlarge_top + 10)) mask_image = mask_image.filter(ImageFilter.BoxBlur(10)) limitation = ""; # Limited to 1 million pixels if 1024 * 1024 < output_width * output_height: factor = ((1024 * 1024) / (output_width * output_height))**0.5 output_width = math.floor(output_width * factor) output_height = math.floor(output_height * factor) limitation = " Due to technical limitation, the image have been downscaled."; # Width and height must be multiple of 8 output_width = output_width - (output_width % 8) output_height = output_height - (output_height % 8) progress(None, desc = "Processing...") output_image = pipe(seeds=[seed], width = output_width, height = output_height, prompt = prompt, negative_prompt = negative_prompt, image = enlarged_image, mask_image = mask_image, num_inference_steps = num_inference_steps, guidance_scale = guidance_scale, denoising_steps = denoising_steps, show_progress_bar = True).images[0] 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 " + str(output_width * output_height) + " pixels." + limitation, input_image, enlarged_image, mask_image] title = "Uncrop" description = "

Enlarges the point of view of your image, up to 1 million pixels, freely, without account, without watermark, which can be downloaded



Powered by SDXL 1.0 artificial intellingence

🐌 Slow process... ~20 min with 20 inference steps, ~6 hours with 25 inference steps.
You can duplicate this space on a free account, it works on CPU.


⚖️ You can use, modify and share the generated images but not for commercial uses." gr.Interface(fn = predict, inputs = [ gr.Image(label = "Your image", source = "upload", type = "numpy"), gr.Number(minimum = 0, value = 64, precision = 0, label = "Enlarge on top", info = "in pixels"), gr.Number(minimum = 0, value = 64, precision = 0, label = "Enlarge on right", info = "in pixels"), gr.Number(minimum = 0, value = 64, precision = 0, label = "Enlarge on bottom", info = "in pixels"), gr.Number(minimum = 0, value = 64, precision = 0, label = "Enlarge on left", info = "in pixels"), gr.Textbox(label = 'Prompt', info = "Describe the subject, the background and the style of image; 77 token limit", placeholder = 'Describe what you want to see in the entire image'), gr.Textbox(label = 'Negative prompt', placeholder = 'Describe what you do NOT want to see in the entire image', value = 'Border, frame, painting, scribbling, smear, noise, blur'), gr.Slider(minimum = 0, maximum = 1000, value = 1000, step = 1, label = "Denoising", info = "lower=irrelevant result, higher=relevant result"), gr.Slider(minimum = 10, maximum = 25, value = 10, step = 1, label = "Number of inference steps", info = "lower=faster, higher=image quality"), gr.Slider(minimum = 1, maximum = 13, value = 7, step = 0.1, label = "Classifier-Free Guidance Scale", info = "lower=image quality, higher=follow the prompt"), gr.Checkbox(label = "Randomize seed (not working, always checked)", value = True, info = "If checked, result is always different"), gr.Slider(minimum = 0, maximum = max_64_bit_int, step = 1, randomize = True, label = "Seed (if not randomized)") ], outputs = [ gr.Image(label = "Uncropped image"), gr.Label(), gr.Image(label = "Original image"), gr.Image(label = "Enlarged image"), gr.Image(label = "Mask image") ], title = title, description = description).launch(max_threads = True)