ZiqiaoPeng/SyncTalk
[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"
PythonNOASSERTION
Issues
- 2
Can not install 3DMM model
#228 opened by nldhuyen0047 - 1
- 2
训练时加载数据killed,是不是对内存要求相当高?
#204 opened by FriendChi - 0
训练完成输出[WARN] Failed to load optimizer.
#223 opened by topshu - 0
之前有人贴过微信交流群的二维码,不过都过期了,哪位方便重新贴一下的吗?
#234 opened by smalldaidai - 2
如果我需要全身的数字人应该怎么做呀?
#193 opened by faiejir - 2
error on windows 10: extract blendshape "IndexError: list index out of range"
#225 opened by linhcentrio - 0
- 0
我开源了一个超轻量级能在移动端上运行的数字人模型快来看看吧
#232 opened by anliyuan - 1
请问GS-SyncTalk什么进展?
#230 opened by cacard - 2
嘴型不动的问题
#192 opened by xiaoqidaov2 - 4
训练后脖子部分出现背景,请问哪个流程能优化改进
#227 opened by jukhang - 0
The list of test video on the paper
#231 opened by kingsj0405 - 0
About dataset preparation
#229 opened by nldhuyen0047 - 1
[extract flow] FileNotFoundError: [Errno 2] No such file or directory: 'data/xxx\\flow_result\\2_1.npy'
#224 opened by linhcentrio - 15
合成后人物脸部、下巴会有背景颜色
#200 opened by yeyuechen - 2
- 4
mouth clarity
#218 opened by varunjain99 - 1
hubert 中文配适模型有没直接开源可用的?
#222 opened by EYcab - 0
- 1
How to Calculate Sync and AUE ?
#187 opened by Neank - 3
安装PyMCubes失败
#189 opened by felixswang - 2
- 1
No keypoints in keypoints.txt why?
#216 opened by thatnerdyaigirl - 2
Windows 集成包,脸部丢失
#220 opened by xzw168 - 0
How to get commercial license ?
#219 opened by lordkrishna - 5
The mouth is terrible, and side view
#206 opened by I8Robot - 0
[Bug] SyncTalk Fails When Head Moves Significantly in the Training video
#217 opened by thatnerdyaigirl - 2
推理出来的视频,有时候嘴巴附近变得比较模糊,请问什么原因
#211 opened by wangyl218 - 3
为什么我训练出来的视频牙齿不清晰,嘴巴在快速抖动?
#213 opened by LeviArckman - 2
推理后,怎么把头部和身体再贴一块
#214 opened by qingshuiyuyu - 4
使用trial_may.zip中模型自己找数据测试一下,效果很差。请问这里的trial_may.zip 是通用的模型还是基于may专门优化的啊?
#186 opened by gobigrassland - 1
ValueError: zero-size array to reduction operation minimum which has no identity
#196 opened by XxsStrongest - 0
运行hubert.py发生错误
#212 opened by LeviArckman - 1
- 5
是否可以支持fps 30帧
#201 opened by lqql8790229 - 1
The results inferred using the model file with 'may' do not contain any faces in the video.
#203 opened by yyjjww - 1
Weird face all of a sudden while speaking
#207 opened by thatnerdyaigirl - 0
blurry teeth
#209 opened by varunjain99 - 2
Background appearing on output
#208 opened by thatnerdyaigirl - 0
audio_visual_encoder.pth应该如何训练?
#205 opened by caitongbo - 2
脸部丢失
#185 opened by XxsStrongest - 0
Export Facial Animation Mesh render
#202 opened by NikoBele1 - 2
- 0
Training (finetuning lip) is too slow.
#197 opened by Standchen - 1
An alternative project EchoMimic is open-sourced
#190 opened by lymhust - 0
请问Facial-Aware Masked-Attention部分在哪
#195 opened by Sprinkle0 - 3
- 2
Do training videos need to be synchronized?
#191 opened by xiaoqidaov2 - 1
唇同步定量评估的两个音频是否可以公开?
#188 opened by Neank