单图换脸roop源码与环境配置

前言

1.roop是新开源了一个单图就可以进行视频换脸的项目,只需要一张所需面部的图像。不需要数据集,不需要训练。

2.大概的测试了一下,正脸换脸效果还不错,融合也比较自然。但如果人脸比较大,最终换出的效果可能会有些模糊。侧脸部分的幅度不宜过大,否则会出现人脸乱飘的情况。在多人场景下,也容易出现混乱。

3.使用简单,在处理单人视频和单人图像还是的换脸效果还是可以的,融合得也不错,适合制作一些小视频或单人图像。

4.效果如下:

 环境安装

1.我这里部署部署环境是win 10、cuda 11.7、cudnn 8.5、GPU是N卡的3060(6G显存),加anaconda3.

2.源码下载,如果用不了git,可以下载打包好的源码和模型。

git clone https://github.com/s0md3v/roop.git
cd roop

3.创建环境

conda create --name roop python=3.10
activate roop
conda install pytorch==2.0.0 torchvision==0.15.0 torchaudio==2.0.0 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install -r requirements.txt

4.安装onnxruntime-gpu推理库

pip install onnxruntime-gpu

5.运行程序

python run.py

运行,它会下载一个500多m的模型,国内的网可能下载得很慢,也可以单独下载之后放到roop根目录下。

7.报错

ffmpeg is not installed!

这个是缺少了FFmpeg,FFmpeg是一套可以用来记录、转换数字音频、视频,并能将其转化为流的开源计算机程序。简单说来就是我们可以用它来进行视频的编解码,可以将视频文件转化为视频流,也可以将视频流转存储为视频文件。还有一个重点就是它是开源的。去官网下载后,加到环境变量就可以了。

8.如果在本地的机子跑起来很慢,把它做成服务器的方式运行,这样就可以在网页或者以微信公众 号或者小程序的方式访问,服务器端代码:

#!/usr/bin/env python3

import os
import sys
# single thread doubles performance of gpu-mode - needs to be set before torch import
if any(arg.startswith('--gpu-vendor') for arg in sys.argv):
    os.environ['OMP_NUM_THREADS'] = '1'
import platform
import signal
import shutil
import glob
import argparse
import psutil
import torch
import tensorflow
from pathlib import Path
import multiprocessing as mp
from opennsfw2 import predict_video_frames, predict_image
from flask import Flask, request
# import base64
import numpy as np
from gevent import pywsgi
import cv2, argparse
import time
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

import roop.globals
from roop.swapper import process_video, process_img, process_faces, process_frames
from roop.utils import is_img, detect_fps, set_fps, create_video, add_audio, extract_frames, rreplace
from roop.analyser import get_face_single
import roop.ui as ui

signal.signal(signal.SIGINT, lambda signal_number, frame: quit())
parser = argparse.ArgumentParser()
parser.add_argument('-f', '--face', help='use this face', dest='source_img')
parser.add_argument('-t', '--target', help='replace this face', dest='target_path')
parser.add_argument('-o', '--output', help='save output to this file', dest='output_file')
parser.add_argument('--keep-fps', help='maintain original fps', dest='keep_fps', action='store_true', default=False)
parser.add_argument('--keep-frames', help='keep frames directory', dest='keep_frames', action='store_true', default=False)
parser.add_argument('--all-faces', help='swap all faces in frame', dest='all_faces', action='store_true', default=False)
parser.add_argument('--max-memory', help='maximum amount of RAM in GB to be used', dest='max_memory', type=int)
parser.add_argument('--cpu-cores', help='number of CPU cores to use', dest='cpu_cores', type=int, default=max(psutil.cpu_count() / 2, 1))
parser.add_argument('--gpu-threads', help='number of threads to be use for the GPU', dest='gpu_threads', type=int, default=8)
parser.add_argument('--gpu-vendor', help='choice your GPU vendor', dest='gpu_vendor', default='nvidia', choices=['apple', 'amd', 'intel', 'nvidia'])

args = parser.parse_known_args()[0]

if 'all_faces' in args:
    roop.globals.all_faces = True

if args.cpu_cores:
    roop.globals.cpu_cores = int(args.cpu_cores)

# cpu thread fix for mac
if sys.platform == 'darwin':
    roop.globals.cpu_cores = 1

if args.gpu_threads:
    roop.globals.gpu_threads = int(args.gpu_threads)

# gpu thread fix for amd
if args.gpu_vendor == 'amd':
    roop.globals.gpu_threads = 1

if args.gpu_vendor:
    roop.globals.gpu_vendor = args.gpu_vendor
else:
    roop.globals.providers = ['CPUExecutionProvider']

sep = "/"
if os.name == "nt":
    sep = "\"


def limit_resources():
    # prevent tensorflow memory leak
    gpus = tensorflow.config.experimental.list_physical_devices('GPU')
    for gpu in gpus:
        tensorflow.config.experimental.set_memory_growth(gpu, True)
    if args.max_memory:
        memory = args.max_memory * 1024 * 1024 * 1024
        if str(platform.system()).lower() == 'windows':
            import ctypes
            kernel32 = ctypes.windll.kernel32
            kernel32.SetProcessWorkingSetSize(-1, ctypes.c_size_t(memory), ctypes.c_size_t(memory))
        else:
            import resource
            resource.setrlimit(resource.RLIMIT_DATA, (memory, memory))


def pre_check():
    if sys.version_info < (3, 9):
        quit('Python version is not supported - please upgrade to 3.9 or higher')
    if not shutil.which('ffmpeg'):
        quit('ffmpeg is not installed!')
    model_path = os.path.join(os.path.abspath(os.path.dirname(__file__)), '../inswapper_128.onnx')
    if not os.path.isfile(model_path):
        quit('File "inswapper_128.onnx" does not exist!')
    if roop.globals.gpu_vendor == 'apple':
        if 'CoreMLExecutionProvider' not in roop.globals.providers:
            quit("You are using --gpu=apple flag but CoreML isn't available or properly installed on your system.")
    if roop.globals.gpu_vendor == 'amd':
        if 'ROCMExecutionProvider' not in roop.globals.providers:
            quit("You are using --gpu=amd flag but ROCM isn't available or properly installed on your system.")
    if roop.globals.gpu_vendor == 'nvidia':
        CUDA_VERSION = torch.version.cuda
        CUDNN_VERSION = torch.backends.cudnn.version()
        if not torch.cuda.is_available():
            quit("You are using --gpu=nvidia flag but CUDA isn't available or properly installed on your system.")
        if CUDA_VERSION > '11.8':
            quit(f"CUDA version {CUDA_VERSION} is not supported - please downgrade to 11.8")
        if CUDA_VERSION < '11.4':
            quit(f"CUDA version {CUDA_VERSION} is not supported - please upgrade to 11.8")
        if CUDNN_VERSION < 8220:
            quit(f"CUDNN version {CUDNN_VERSION} is not supported - please upgrade to 8.9.1")
        if CUDNN_VERSION > 8910:
            quit(f"CUDNN version {CUDNN_VERSION} is not supported - please downgrade to 8.9.1")


def get_video_frame(video_path, frame_number = 1):
    cap = cv2.VideoCapture(video_path)
    amount_of_frames = cap.get(cv2.CAP_PROP_FRAME_COUNT)
    cap.set(cv2.CAP_PROP_POS_FRAMES, min(amount_of_frames, frame_number-1))
    if not cap.isOpened():
        print("Error opening video file")
        return
    ret, frame = cap.read()
    if ret:
        return cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

    cap.release()


def preview_video(video_path):
    cap = cv2.VideoCapture(video_path)
    if not cap.isOpened():
        print("Error opening video file")
        return 0
    amount_of_frames = cap.get(cv2.CAP_PROP_FRAME_COUNT)
    ret, frame = cap.read()
    if ret:
        frame = get_video_frame(video_path)

    cap.release()
    return (amount_of_frames, frame)


def status(string):
    value = "Status: " + string
    if 'cli_mode' in args:
        print(value)
    else:
        ui.update_status_label(value)


def process_video_multi_cores(source_img, frame_paths):
    n = len(frame_paths) // roop.globals.cpu_cores
    if n > 2:
        processes = []
        for i in range(0, len(frame_paths), n):
            p = POOL.apply_async(process_video, args=(source_img, frame_paths[i:i + n],))
            processes.append(p)
        for p in processes:
            p.get()
        POOL.close()
        POOL.join()



def select_face_handler(path: str):
    args.source_img = path


def select_target_handler(path: str):
    args.target_path = path
    return preview_video(args.target_path)


def toggle_all_faces_handler(value: int):
    roop.globals.all_faces = True if value == 1 else False


def toggle_fps_limit_handler(value: int):
    args.keep_fps = int(value != 1)


def toggle_keep_frames_handler(value: int):
    args.keep_frames = value


def save_file_handler(path: str):
    args.output_file = path


def create_test_preview(frame_number):
    return process_faces(
        get_face_single(cv2.imread(args.source_img)),
        get_video_frame(args.target_path, frame_number)
    )


app = Flask(__name__)
@app.route('/face_swap', methods=['POST'])
def face_swap():
    if request.method == 'POST':
        args.source_img=request.form.get('source_img')
        args.target_path = request.form.get('target_path')
        args.output_file = request.form.get('output_path')
        keep_fps = request.form.get('keep_fps')
        if keep_fps == '0':
            args.keep_fps = False
        else:
            args.keep_fps = True
        
        Keep_frames = request.form.get('Keep_frames')
        if Keep_frames == '0':
            args.Keep_frames = False
        else:
            args.Keep_frames = True

        all_faces = request.form.get('all_faces')
        if all_faces == '0':
            args.all_faces = False
        else:
            args.all_faces = True

    if not args.source_img or not os.path.isfile(args.source_img):
        print("n[WARNING] Please select an image containing a face.")
        return
    elif not args.target_path or not os.path.isfile(args.target_path):
        print("n[WARNING] Please select a video/image to swap face in.")
        return
    if not args.output_file:
        target_path = args.target_path
        args.output_file = rreplace(target_path, "/", "/swapped-", 1) if "/" in target_path else "swapped-" + target_path
    target_path = args.target_path
    test_face = get_face_single(cv2.imread(args.source_img))
    if not test_face:
        print("n[WARNING] No face detected in source image. Please try with another one.n")
        return
    if is_img(target_path):
        if predict_image(target_path) > 0.85:
            quit()
        process_img(args.source_img, target_path, args.output_file)
        # status("swap successful!")
        return 'ok'
    
    seconds, probabilities = predict_video_frames(video_path=args.target_path, frame_interval=100)
    if any(probability > 0.85 for probability in probabilities):
        quit()
    video_name_full = target_path.split("/")[-1]
    video_name = os.path.splitext(video_name_full)[0]
    output_dir = os.path.dirname(target_path) + "/" + video_name if os.path.dirname(target_path) else video_name
    Path(output_dir).mkdir(exist_ok=True)
    # status("detecting video's FPS...")
    fps, exact_fps = detect_fps(target_path)
    
    if not args.keep_fps and fps > 30:
        this_path = output_dir + "/" + video_name + ".mp4"
        set_fps(target_path, this_path, 30)
        target_path, exact_fps = this_path, 30
    else:
        shutil.copy(target_path, output_dir)
    # status("extracting frames...")
    extract_frames(target_path, output_dir)

    args.frame_paths = tuple(sorted(
        glob.glob(output_dir + "/*.png"),
        key=lambda x: int(x.split(sep)[-1].replace(".png", ""))
    ))

    # status("swapping in progress...")
    if roop.globals.gpu_vendor is None and roop.globals.cpu_cores > 1:
        global POOL
        POOL = mp.Pool(roop.globals.cpu_cores)
        process_video_multi_cores(args.source_img, args.frame_paths)
    else:
        process_video(args.source_img, args.frame_paths)
    # status("creating video...")
    create_video(video_name, exact_fps, output_dir)
    # status("adding audio...")
    add_audio(output_dir, target_path, video_name_full, args.keep_frames, args.output_file)
    save_path = args.output_file if args.output_file else output_dir + "/" + video_name + ".mp4"
    print("nnVideo saved as:", save_path, "nn")
    # status("swap successful!")

    return 'ok'

if __name__ == "__main__":
    print('Statrt server----------------')
    server = pywsgi.WSGIServer(('127.0.0.1', 5020), app)
    server.serve_forever()

9.客户端代码

import requests
import base64
import numpy as np
import cv2
import time

source_img = "z1.jpg" #要换的脸
target_path= "z2.mp4" #目标图像或者视频
output_path = "zface2.mp4" #保存的目录和文件名
keep_fps = '0' #视频,是否保持原帧率
Keep_frames = '0' 
all_faces = '0' #

data = {'source_img': source_img,'target_path' : target_path,'output_path':output_path,
        'keep-fps' : keep_fps,'Keep_frames':Keep_frames,'all_faces':all_faces}

resp = requests.post("http://127.0.0.1:5020/face_swap", data=data)
print(resp.content)