Spaces:
Running
Running
| 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 = "<p style='text-align: center;'>Enlarges the point of view of your image, up to 1 million pixels, freely, without account, without watermark, which can be downloaded</p><br/><br/>Powered by <i>SDXL 1.0</i> artificial intellingence<br/><ul><li>If you need to change the <b>view angle</b> of your image, I recommend you to use <i>Zero123</i>,</li><li>If you need to <b>upscale</b> your image, I recommend you to use <i>Ilaria Upscaler</i>,</li><li>If you need to <b>slightly change</b> your image, I recommend you to use <i>Image-to-Image SDXL</i>,</li><li>If you need to change <b>one detail</b> on your image, I recommend you to use <i>Inpaint SDXL</i>.</li></ul><br/>🐌 Slow process... ~20 min with 20 inference steps, ~6 hours with 25 inference steps.<br>You can duplicate this space on a free account, it works on CPU.<br/><a href='https://huggingface.co/spaces/Fabrice-TIERCELIN/Uncrop?duplicate=true'><img src='https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14'></a><br/><br/>⚖️ 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) |