-
Hi, thanks for your project.
When I download the pretrained checkpoints that you provide on the Obama video clip and test by
> python main.py data/obama/ --workspace trial_obama/ -O --test --ckp…
-
本项目中loss_u和loss_static_uncertainty使用了与er-nerf不同的权重，请教下具体原因是什么？
-
你好，我想问一下，对于预处理中的颈部的填充是如何填的呢，我借鉴于ER-NeRF的代码来进行修改
我根据论文的思想，取出对应图片的颈部的RGB颜色，然后填充，但是好像效果不一样，就请问一下，大概如何实现的
![image](https://github.com/ZiqiaoPeng/SyncTalk/assets/61195303/92a87aab-d0a3-406a-8830-21011c…
-
I used ave audio encoder to replace ernerf's audio encoder, and unfortunately I got a worse result.
-
1. 我在用hubert来重新训练May数据，得到的人物嘴巴抖动很快，使用Hubert来训练需要更改其他的设置吗？
2. 为什么hubert的self.audio_in_dim = 27，在er-nerf中是1024？
if 'esperanto' in self.opt.asr_model:
self.audio_in_dim = 44
elif …
-
-
i tried to preprocess my own video data, the bs.npy is generated from EmoTalk project.
-
-
EDIT: This approach is legally not solid. Therefore see #1349 where its about getting explicit agreements for the shipped plugins. However a general agreement is still useful for the case when we resu…
-
### Your GTNH Discord Username
chochem
### Your Pack Version
2.6.1
### Overview
The monthly ticket for quest changes. Well, maybe it is the _quarterly_ ticket for quest changes. A ticke…