import os os.system("pip uninstall -y gradio") os.system("pip install gradio==3.50") os.system('wget "https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/RetinaFace-R50.pth" -O weights/RetinaFace-R50.pth') os.system('wget "https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-BFR-512.pth" -O weights/GPEN-512.pth') os.system('wget "https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-Colorization-1024.pth" -O weights/GPEN-1024-Color.pth ') os.system('wget "https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/realesrnet_x2.pth" -O weights/realesrnet_x2.pth ') os.system('wget "https://public-vigen-video.oss-cn-shanghai.aliyuncs.com/robin/models/GPEN-Inpainting-1024.pth" -O weights/GPEN-Inpainting-1024.pth ') jksp= os.environ['SELFIE'] os.system(f'wget "{jksp}" -O weights/GPEN-BFR-2048.pth') import gradio as gr ''' @paper: GAN Prior Embedded Network for Blind Face Restoration in the Wild (CVPR2021) @author: yangxy (yangtao9009@gmail.com) ''' import os import cv2 import glob import time import math import imutils import argparse import numpy as np from PIL import Image, ImageDraw import __init_paths from face_enhancement import FaceEnhancement from face_colorization import FaceColorization from face_inpainting import FaceInpainting def brush_stroke_mask(img, color=(255,255,255)): min_num_vertex = 8 max_num_vertex = 28 mean_angle = 2*math.pi / 5 angle_range = 2*math.pi / 15 min_width = 12 max_width = 80 def generate_mask(H, W, img=None): average_radius = math.sqrt(H*H+W*W) / 8 mask = Image.new('RGB', (W, H), 0) if img is not None: mask = img #Image.fromarray(img) for _ in range(np.random.randint(1, 4)): num_vertex = np.random.randint(min_num_vertex, max_num_vertex) angle_min = mean_angle - np.random.uniform(0, angle_range) angle_max = mean_angle + np.random.uniform(0, angle_range) angles = [] vertex = [] for i in range(num_vertex): if i % 2 == 0: angles.append(2*math.pi - np.random.uniform(angle_min, angle_max)) else: angles.append(np.random.uniform(angle_min, angle_max)) h, w = mask.size vertex.append((int(np.random.randint(0, w)), int(np.random.randint(0, h)))) for i in range(num_vertex): r = np.clip( np.random.normal(loc=average_radius, scale=average_radius//2), 0, 2*average_radius) new_x = np.clip(vertex[-1][0] + r * math.cos(angles[i]), 0, w) new_y = np.clip(vertex[-1][1] + r * math.sin(angles[i]), 0, h) vertex.append((int(new_x), int(new_y))) draw = ImageDraw.Draw(mask) width = int(np.random.uniform(min_width, max_width)) draw.line(vertex, fill=color, width=width) for v in vertex: draw.ellipse((v[0] - width//2, v[1] - width//2, v[0] + width//2, v[1] + width//2), fill=color) return mask width, height = img.size mask = generate_mask(height, width, img) return mask def resize(image, width = 1024): aspect_ratio = float(image.shape[1])/float(image.shape[0]) height = width/aspect_ratio image = cv2.resize(image, (int(height),int(width))) return image def inference(file, mode): im = cv2.imread(file, cv2.IMREAD_COLOR) im = cv2.resize(im, (0,0), fx=2, fy=2) faceenhancer = FaceEnhancement(size=512, model='GPEN-512', channel_multiplier=2, device='cpu', u=False) img, orig_faces, enhanced_faces = faceenhancer.process(im) cv2.imwrite(os.path.join("e.png"), img) if mode == "enhance": return os.path.join("e.png") elif mode == "colorize": model = {'name':'GPEN-1024-Color', 'size':1024} grayf = cv2.imread("e.png", cv2.IMREAD_GRAYSCALE) grayf = cv2.cvtColor(grayf, cv2.COLOR_GRAY2BGR) # channel: 1->3 facecolorizer = FaceColorization(size=model['size'], model=model['name'], channel_multiplier=2, device='cpu') colorf = facecolorizer.process(grayf) colorf = cv2.resize(colorf, (grayf.shape[1], grayf.shape[0])) cv2.imwrite(os.path.join("output.png"), colorf) return os.path.join("output.png") elif mode == "inpainting": im1 = cv2.imread(file, cv2.IMREAD_COLOR) im2 = resize(im1, width = 1024) model = {'name':'GPEN-Inpainting-1024', 'size':1024} faceinpainter = FaceInpainting(size=model['size'], model=model['name'], channel_multiplier=2, device='cpu') im3 = np.asarray(brush_stroke_mask(Image.fromarray(im2))) inpaint = faceinpainter.process(im3) cv2.imwrite(os.path.join("output.png"), inpaint) return os.path.join("output.png") elif mode == "selfie": model = {'name':'GPEN-BFR-2048', 'size':2048} im = cv2.resize(im, (0,0), fx=2, fy=2) faceenhancer = FaceEnhancement(size=model['size'], model=model['name'], channel_multiplier=2, device='cpu') img, orig_faces, enhanced_faces = faceenhancer.process(im) cv2.imwrite(os.path.join("output.png"), img) return os.path.join("output.png") else: faceenhancer = FaceEnhancement(size=512, model='GPEN-512', channel_multiplier=2, device='cpu', u=True) img, orig_faces, enhanced_faces = faceenhancer.process(im) cv2.imwrite(os.path.join("output.png"), img) return os.path.join("output.png") title = "GPEN" description = "Gradio demo for GAN Prior Embedded Network for Blind Face Restoration in the Wild. This version of gradio demo includes face colorization from GPEN. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below." article = "

GAN Prior Embedded Network for Blind Face Restoration in the Wild | Github Repo

https://huggingface.co/spaces/akhaliq/GPEN

" gr.Interface( inference, [gr.inputs.Image(type="filepath", label="Input"),gr.inputs.Radio(["enhance", "colorize", "inpainting", "selfie", "enhanced+background"], type="value", default="enhance", label="Type")], gr.outputs.Image(type="filepath", label="Output"), title=title, description=description, article=article, examples=[ ['enhance.png', 'enhance'], ['color.png', 'colorize'], ['inpainting.png', 'inpainting'], ['selfie.png', 'selfie'] ], enable_queue=True ).launch()