AI 算法让图片动起来，深情演唱 Unravel

项目地址：https://github.com/anandpawara/Real_Time_Image_Animation

实验环境：Google Colab

Step1: Clone Repo

!git clone https://github.com/anandpawara/Real_Time_Image_Animation.git
%cd Real_Time_Image_Animation

Step2: Install required modules

在安装前，需要修改 requirements.txt 文件，因为我们实验的环境是 linux，而 requirements.txt 中下载了一些 windows 的库

删除 requirements.txt 以下两行

pywin32==227
pywinpty==0.5.7

然后执行以下代码

!pip install -r requirements.txt
!pip install torch===1.0.0 torchvision===0.2.1 -f https://download.pytorch.org/whl/cu100/torch_stable.html

Step3: Modify image_animation.py

这个项目只能处理图像，不能保留音频。所以我们需要先将音频保存，再将处理好的视频和音频进行合成

修改 image_animation.py 文件

import imageio
import torch
from tqdm import tqdm
from animate import normalize_kp
from demo import load_checkpoints
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.animation as animation
from skimage import img_as_ubyte
from skimage.transform import resize
import cv2
import os
import argparse
 
import subprocess
import os
from PIL import Image
 
def video2mp3(file_name):
    outfile_name = file_name.split('.')[0] + '.mp3'
    cmd = 'ffmpeg -i ' + file_name + ' -f mp3 ' + outfile_name
    print(cmd)
    subprocess.call(cmd, shell=True)
 
 
def video_add_mp3(file_name, mp3_file):
    outfile_name = file_name.split('.')[0] + '-f.mp4'
    subprocess.call('ffmpeg -i ' + file_name
                    + ' -i ' + mp3_file + ' -strict -2 -f mp4 '
                    + outfile_name, shell=True)
 
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--input_image", required=True,help="Path to image to animate")
ap.add_argument("-c", "--checkpoint", required=True,help="Path to checkpoint")
ap.add_argument("-v","--input_video", required=False, help="Path to video input")
 
args = vars(ap.parse_args())
 
print("[INFO] loading source image and checkpoint...")
source_path = args['input_image']
checkpoint_path = args['checkpoint']
if args['input_video']:
    video_path = args['input_video']
else:
    video_path = None
source_image = imageio.imread(source_path)
source_image = resize(source_image,(256,256))[..., :3]
 
generator, kp_detector = load_checkpoints(config_path='config/vox-256.yaml', checkpoint_path=checkpoint_path)
 
if not os.path.exists('output'):
    os.mkdir('output')
 
 
relative=True
adapt_movement_scale=True
cpu=False
 
if video_path:
    cap = cv2.VideoCapture(video_path) 
    print("[INFO] Loading video from the given path")
else:
    cap = cv2.VideoCapture(0)
    print("[INFO] Initializing front camera...")
 
fps = cap.get(cv2.CAP_PROP_FPS)
size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)), int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))

video2mp3(file_name = video_path)
 
fourcc = cv2.VideoWriter_fourcc('M','P','E','G')
#out1 = cv2.VideoWriter('output/test.avi', fourcc, fps, (256*3 , 256), True)
out1 = cv2.VideoWriter('output/test.mp4', fourcc, fps, size, True)
 
cv2_source = cv2.cvtColor(source_image.astype('float32'),cv2.COLOR_BGR2RGB)
with torch.no_grad() :
    predictions = []
    source = torch.tensor(source_image[np.newaxis].astype(np.float32)).permute(0, 3, 1, 2)
    if not cpu:
        source = source.cuda()
    kp_source = kp_detector(source)
    count = 0
    while(True):
        ret, frame = cap.read()
        frame = cv2.flip(frame,1)
        if ret == True:
            
            if not video_path:
                x = 143
                y = 87
                w = 322
                h = 322 
                frame = frame[y:y+h,x:x+w]
            frame1 = resize(frame,(256,256))[..., :3]
            
            if count == 0:
                source_image1 = frame1
                source1 = torch.tensor(source_image1[np.newaxis].astype(np.float32)).permute(0, 3, 1, 2)
                kp_driving_initial = kp_detector(source1)
            
            frame_test = torch.tensor(frame1[np.newaxis].astype(np.float32)).permute(0, 3, 1, 2)
 
            driving_frame = frame_test
            if not cpu:
                driving_frame = driving_frame.cuda()
            kp_driving = kp_detector(driving_frame)
            kp_norm = normalize_kp(kp_source=kp_source,
                                kp_driving=kp_driving,
                                kp_driving_initial=kp_driving_initial, 
                                use_relative_movement=relative,
                                use_relative_jacobian=relative, 
                                adapt_movement_scale=adapt_movement_scale)
            out = generator(source, kp_source=kp_source, kp_driving=kp_norm)
            predictions.append(np.transpose(out['prediction'].data.cpu().numpy(), [0, 2, 3, 1])[0])
            im = np.transpose(out['prediction'].data.cpu().numpy(), [0, 2, 3, 1])[0]
            im = cv2.cvtColor(im,cv2.COLOR_RGB2BGR)
            #joinedFrame = np.concatenate((cv2_source,im,frame1),axis=1)
            #joinedFrame = np.concatenate((cv2_source,im,frame1),axis=1)
            
            #cv2.imshow('Test',joinedFrame)
            #out1.write(img_as_ubyte(joinedFrame))
            out1.write(img_as_ubyte(im))
            count += 1
#            if cv2.waitKey(20) & 0xFF == ord('q'):
#                break
        else:
            break
        
    cap.release()
    out1.release()
    cv2.destroyAllWindows()
    
video_add_mp3(file_name='output/test.mp4', mp3_file=video_path.split('.')[0] + '.mp3')

Step 4: Download cascade file ,weights and model and save in folder named extract

下载算法需要的模型和权重文件

!gdown --id 1wCzJP1XJNB04vEORZvPjNz6drkXm5AUK
!unzip checkpoints.zip

视频以及图片素材下载链接：https://pan.baidu.com/s/1aur-vfTSJE9ix9afIuZLRQ 提取码：p3so

将视频素材 1.mp4 上传到 Real_Time_Image_Animation 目录下

将图片素材 pdd.png 上传到 Real_Time_Image_Animation/Inputs 目录下

Step5: Run the project

命令模板：

python image_animation.py -i path_to_input_file -c path_to_checkpoint -v path_to_video_file

• path_to_input_file 是输入的模板图片
• path_to_checkpoint 是权重文件
• path_to_video_file 是输入的视频文件

具体来说，执行如下命令即可

!python image_animation.py -i Inputs/pdd.png -c vox-cpk.pth.tar -v 1.mp4

最后生成的视频会保存在 Real_Time_Image_Animation/output 目录下，名为 test-f.mp4