search

YuanxunLu / LiveSpeechPortraits

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)
MIT License
1.2k stars 209 forks source link

会提供训练代码？ #58

Closed foocker closed 2 years ago

YuanxunLu commented 2 years ago

Please check issue #33.

foocker commented 2 years ago

Please check issue #33.

谢谢，还没仔细看论文，这个是一个人物，一套模型？ 如果不是，能讲解下数据制作？

YuanxunLu commented 2 years ago

Yes, the proposed method is person-specific. For data processing, please check the paper.

foocker commented 2 years ago

Yes, the proposed method is person-specific. For data processing, please check the paper.

谢谢，总结了下，还是有很多细节。有点好奇，看了下历史issue，既然这么多人复现了，怎么没有一个pr的？

foocker commented 2 years ago

@YuanxunLu 训练数据的目录结构方便发一下吗？h5里面的数据是？change_paras中的scale, xc, yc咋计算的？

YuanxunLu commented 2 years ago

Releasing the training data & structure is not in the scope of this repo for copyright reasons, check issue #33.

The released code, including training settings, dataset files, etc will help you to train your own model.

foocker commented 2 years ago

Releasing the training data & structure is not in the scope of this repo for copyright reasons, check issue #33.

The released code, including training settings, dataset files, etc will help you to train your own model.

ok,我重新开了一个问题，希望您可以选择性的回答一些疑问。

ak01user commented 1 year ago

我训练出来了，比LiveSpeechPortrait的画面更稳定，演示效果 https://space.bilibili.com/3494353091693235

YashVadi commented 8 months ago

@ak01user I am facing difficulty in implementing this. can you please share some of your training code?