Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于生成视频抖动 #184

Open
sixone-Jiang opened this issue Jul 5, 2024 · 0 comments
Open

关于生成视频抖动 #184

sixone-Jiang opened this issue Jul 5, 2024 · 0 comments

Comments

@sixone-Jiang
Copy link

感谢您们出色的工作,但我注意到一些小小的问题,我想是否能在以下几个角度和您进行讨论:1. 我注意到您们相当于使用显式关键点作为条件,在类似FOMM / LivePortrait / follow your emjio这类的工作中,都采用了一个小网络来将关键点进行隐式表示,这样是否可以降低由于drive视频检测到的关键点本身抖动带来的偏差(生成视频很抖动);2. 在Cross Attn层加入Clip特征是否有助于人脸细节的生成,或许也能降低一些推理时降噪步数;3. 先前的模型会时不时有奇怪的手生成出来,能否通过将VFHQ / Vecelvhq清洗一下进行微调来修复这个问题呢?4. 现在的模型推理时实在是太慢了,诚然,也许LCM之类的技术或许能进一步大幅降低推理时间;但出于一些别的考虑,这个模型本身是否能做的更小一些呢?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant