Zz-ww/SadTalker-Video-Lip-Sync
本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形,设置面部区域可配置的增强方式进行合成唇形(人脸)区域画面增强,提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧,补充帧间合成唇形的动作过渡,使合成的唇形更为流畅、真实以及自然。
Python
Issues
- 0
生成的头像部分和身体部分错位了
#96 opened by Mou-Mou-L - 0
error
#74 opened by zhangnn520 - 1
download error!
#95 opened by arash-aut - 0
不是正脸视频,嘴部会歪
#94 opened by liyuli1997 - 7
分享经验:分辨率低的解决方法
#73 opened by shirubei - 1
输入图片和音频,输出还是静态图片、无音频,请问是什么原因呢?
#93 opened by sunyclj - 0
- 0
<command-line>: fatal error: cuda_runtime.h: No such file or directory compilation terminated. ninja: build stopped: subcommand failed.
#91 opened by sunyclj - 0
ImportError: libOpenGL.so.0: cannot open shared object file: No such file or directory 应该如何选择opencv和Python版本?
#90 opened by SKRY1412 - 0
How to add long audio
#89 opened by khushalcodiste - 1
建立的视频有长度限制吗?
#76 opened by sherryliaoQNAP - 1
Who needs high-quality lip sync - contact me!
#88 opened by Chechgroup - 7
效果还是不错的,大家用的时候注意这个关键点
#50 opened by lzw504504 - 9
- 1
微调后的wav2lip模型可以直接在项目中使用吗,如果需要使用要如何进行更改?
#87 opened by danyow-cheung - 0
How to generate 30fps, instead of 25fps?
#86 opened by MoonEese - 0
ModuleNotFoundError: No module named 'skimage'
#85 opened by 20246688 - 1
程序被kill了,有人遇到过什么原因吗
#81 opened by icomefrom - 0
希望可以搞一个在webui上面可以使用的谢谢~
#84 opened by ihuangke777 - 0
enhancer lip 视频脸部出现光条
#83 opened by 18756164789 - 0
scipy==1.5.3 在哪下载?pip最高版本1.3?
#82 opened by 80981818qqcom - 0
此项目支持Windows 上面运行么?
#80 opened by TzyTman - 0
用python-3.9.13终于成功
#79 opened by waney - 5
项目默认只能使用一张显卡,能否支持多GPU来生成
#53 opened by lzw504504 - 0
是否支持多显卡执行?
#78 opened by TzyTman - 0
RuntimeError: Unable to open ./checkpoints/shape_predictor_68_face_landmarks.dat
#77 opened by TzyTman - 2
- 0
使用--use_DAIN发生了InvalidArgumentError相关错误
#75 opened by wanghx1121 - 9
Paddle and CUDA version conflicts?, and missing file "cudnn64_7.dll" and question about the DAIN algorithm
#72 opened by APISeeker - 2
大佬,生成的视频太模糊咋整?
#67 opened by zhuxiu1234 - 3
- 2
- 1
音频时长大于源视频时长是不是就只能生成视频长度的结果
#66 opened by pipashu1 - 3
Hello! I have a problem.
#51 opened by NeuroDonu - 0
这个和ernerf比哪个效果更好?
#70 opened by lzhchina - 1
头部晃动的动作比较大会有部分嘴型有问题
#60 opened by lzhchina - 6
留了个vx群在这里 有兴趣的话 方便大家交流优化思路
#65 opened by pipashu1 - 0
is there a Google Collab for this?
#69 opened by AIhasArrived - 0
Training script
#68 opened by thibaudart - 1
有大佬会把facerender的OcclusionAwareSPADEGenerator转onnx模型吗,facerender太慢了,想加个速试试,呜呜呜
#64 opened by xyh19960622 - 2
- 0
If in my original video the character doesn't open his mouth, can I still use this technique? Thank you
#63 opened by D-Mad - 0
请问有DSW或CLABO的环境镜像吗,没装了几天也没能运行成功
#61 opened by 1887952 - 1
torch_extensions/py38_cu113/fused/fused.so: cannot open shared object file: No such file or directory
#55 opened by cousin-wang - 0
ValueError: needs one of codec_name or template
#57 opened by Rudy34160 - 0
DLib error
#56 opened by Rudy34160 - 1
Problem with the working environment
#54 opened by kubbistar - 2
如何使用GPU启动
#52 opened by Mrdownshifter - 0
- 1
效果较差
#47 opened by lucasjinreal