import gradio as gr import PIL from PIL import Image import numpy as np import os import uuid import torch from torch import autocast import cv2 from io import BytesIO from matplotlib import pyplot as plt from torchvision import transforms import io import logging import multiprocessing import random import time import imghdr from pathlib import Path from typing import Union from loguru import logger from lama_cleaner.model_manager import ModelManager from lama_cleaner.schema import Config try: torch._C._jit_override_can_fuse_on_cpu(False) torch._C._jit_override_can_fuse_on_gpu(False) torch._C._jit_set_texpr_fuser_enabled(False) torch._C._jit_set_nvfuser_enabled(False) except: pass from lama_cleaner.helper import ( load_img, numpy_to_bytes, resize_max_size, ) NUM_THREADS = str(multiprocessing.cpu_count()) # fix libomp problem on windows https://github.com/Sanster/lama-cleaner/issues/56 os.environ["KMP_DUPLICATE_LIB_OK"] = "True" os.environ["OMP_NUM_THREADS"] = NUM_THREADS os.environ["OPENBLAS_NUM_THREADS"] = NUM_THREADS os.environ["MKL_NUM_THREADS"] = NUM_THREADS os.environ["VECLIB_MAXIMUM_THREADS"] = NUM_THREADS os.environ["NUMEXPR_NUM_THREADS"] = NUM_THREADS if os.environ.get("CACHE_DIR"): os.environ["TORCH_HOME"] = os.environ["CACHE_DIR"] HF_TOKEN_SD = os.environ.get('HF_TOKEN_SD') device = "cuda" if torch.cuda.is_available() else "cpu" print(f'device = {device}') def get_image_ext(img_bytes): w = imghdr.what("", img_bytes) if w is None: w = "jpeg" return w def read_content(file_path): """read the content of target file """ with open(file_path, 'rb') as f: content = f.read() return content def get_image_enhancer(scale = 2, device='cuda:0'): from basicsr.archs.rrdbnet_arch import RRDBNet from realesrgan import RealESRGANer from realesrgan.archs.srvgg_arch import SRVGGNetCompact from gfpgan import GFPGANer realesrgan_model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4 ) netscale = scale model_realesrgan = 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth' upsampler = RealESRGANer( scale=netscale, model_path=model_realesrgan, model=realesrgan_model, tile=0, tile_pad=10, pre_pad=0, half=False if device=='cpu' else True, device=device ) model_GFPGAN = 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth' img_enhancer = GFPGANer( model_path=model_GFPGAN, upscale=scale, arch='clean', channel_multiplier=2, bg_upsampler=upsampler, device=device ) return img_enhancer image_enhancer = get_image_enhancer(scale = 1, device=device) model = None def model_process(image, mask, img_enhancer): global model,image_enhancer if mask.shape[0] == image.shape[1] and mask.shape[1] == image.shape[0] and mask.shape[0] != mask.shape[1]: # rotate image image = np.transpose(image[::-1, ...][:, ::-1], axes=(1, 0, 2))[::-1, ...] original_shape = image.shape interpolation = cv2.INTER_CUBIC size_limit = 1080 #1080 # "Original" if size_limit == "Original": size_limit = max(image.shape) else: size_limit = int(size_limit) config = Config( ldm_steps=25, ldm_sampler='plms', zits_wireframe=True, hd_strategy='Original', hd_strategy_crop_margin=196, hd_strategy_crop_trigger_size=1280, hd_strategy_resize_limit=2048, prompt='', use_croper=False, croper_x=0, croper_y=0, croper_height=512, croper_width=512, sd_mask_blur=5, sd_strength=0.75, sd_steps=50, sd_guidance_scale=7.5, sd_sampler='ddim', sd_seed=42, cv2_flag='INPAINT_NS', cv2_radius=5, ) if config.sd_seed == -1: config.sd_seed = random.randint(1, 999999999) logger.info(f"Origin image shape_0_: {original_shape} / {size_limit}") image = resize_max_size(image, size_limit=size_limit, interpolation=interpolation) logger.info(f"Resized image shape_1_: {image.shape}") logger.info(f"mask image shape_0_: {mask.shape} / {type(mask)}") mask = resize_max_size(mask, size_limit=size_limit, interpolation=interpolation) logger.info(f"mask image shape_1_: {mask.shape} / {type(mask)}") if model is None: return None res_np_img = model(image, mask, config) torch.cuda.empty_cache() image = Image.open(io.BytesIO(numpy_to_bytes(res_np_img, 'png'))) if image_enhancer is not None and img_enhancer: start = time.time() input_img_rgb = np.array(image) input_img_bgr = input_img_rgb[...,[2,1,0]] _, _, enhance_img = image_enhancer.enhance(input_img_bgr, has_aligned=False, only_center_face=False, paste_back=True) input_img_rgb = enhance_img[...,[2,1,0]] img_enhance = Image.fromarray(np.uint8(input_img_rgb)) image = img_enhance log_info = f"image_enhancer_: {(time.time() - start) * 1000}ms, {res_np_img.shape} " logger.info(log_info) return image # image model = ModelManager( name='lama', device=device, ) image_type = 'pil' # filepath' def predict(input, img_enhancer): if input is None: return None if image_type == 'filepath': # input: {'image': '/tmp/tmp8mn9xw93.png', 'mask': '/tmp/tmpn5ars4te.png'} origin_image_bytes = read_content(input["image"]) print(f'origin_image_bytes = ', type(origin_image_bytes), len(origin_image_bytes)) image, _ = load_img(origin_image_bytes) mask, _ = load_img(read_content(input["mask"]), gray=True) elif image_type == 'pil': # input: {'image': pil, 'mask': pil} image_pil = input['image'] mask_pil = input['mask'] image = np.array(image_pil) mask = np.array(mask_pil.convert("L")) output = model_process(image, mask, img_enhancer) return output css = ''' .container {max-width: 100%;margin: auto;padding-top: 1.5rem} .output-image, .input-image, .image-preview {height: 600px !important;object-fit: contain} #work-container {min-width: min(160px, 100%) !important;flex-grow: 0 !important} #image_upload{min-height:610px} #image_upload [data-testid="image"], #image_upload [data-testid="image"] > div{min-height: 620px} #image_output{margin: 0 auto; text-align: center;width:640px} #erase-container{margin: 0 auto; text-align: center;width:150px;border-width:5px;border-color:#2c9748} #enhancer-checkbox{width:520px} #enhancer-tip{width:450px} #enhancer-tip-div{text-align: left} #prompt-container{margin: 0 auto; text-align: center;width:fit-content;min-width: min(150px, 100%);flex-grow: 0; flex-wrap: nowrap;} .footer {margin-bottom: 45px;margin-top: 35px;text-align: center;border-bottom: 1px solid #e5e5e5} .footer>p {font-size: .8rem; display: inline-block; padding: 0 10px;transform: translateY(10px);background: white} .dark .footer {border-color: #303030} .dark .footer>p {background: #0b0f19} #image_upload .touch-none{display: flex} @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } ''' image_blocks = gr.Blocks(css=css) with image_blocks as demo: with gr.Group(): with gr.Box(elem_id="work-container"): with gr.Row(elem_id="input-container"): with gr.Column(): image = gr.Image(source='upload', elem_id="image_upload",tool='sketch', type=f'{image_type}', label="Upload(载入图片)", show_label=True).style(mobile_collapse=False) with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True): with gr.Column(elem_id="erase-container"): btn_erase = gr.Button(value = "Erase(擦除↓)",elem_id="erase_btn").style( margin=True, rounded=(True, True, True, True), full_width=True, ).style(width=100) with gr.Column(elem_id="enhancer-checkbox"): enhancer_label = 'Enhanced image(processing is very slow, please check only for blurred images)【增强图像(处理很慢，请仅针对模糊图像做勾选)】' img_enhancer = gr.Checkbox(label=enhancer_label).style(width=150) with gr.Row(elem_id="output-container"): with gr.Column(): image_out = gr.Image(label="Result", elem_id="image_output", visible=True).style(width=640) btn_erase.click(fn=predict, inputs=[image, img_enhancer], outputs=[image_out]) image_blocks.launch()