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

VAE training code #646

Open
cdfan0627 opened this issue Jan 8, 2025 · 5 comments
Open

VAE training code #646

cdfan0627 opened this issue Jan 8, 2025 · 5 comments
Assignees

Comments

@cdfan0627
Copy link

請問你們有計畫release 3D VAE 的 training code嗎? 或者可以直接用你們目前diffuser 版的training code 然後fix住 transformer,改成直接train VAE嗎?

@samueleruffino99
Copy link

+1, english please! I would be interested in the training code of the 3D Causal VAE :)

@zRzRzRzRzRzRzR zRzRzRzRzRzRzR self-assigned this Jan 9, 2025
@zRzRzRzRzRzRzR
Copy link
Member

We do not provide the code for training VAE separately. Thank you for your understanding.
If you are aiming to improve the generation effect of the model, VAE is responsible for the reconstruction part, which has less impact on the model's effect than transformers fine-tuning.

@cdfan0627
Copy link
Author

想問目前從VAE 的code 中看到好像8 * N張或8 * N + 1張好像都可以encode跟decode對嗎

@zRzRzRzRzRzRzR
Copy link
Member

@cdfan0627
Copy link
Author

想再請問一下,如果想要用pose、depth、optical flow等video當作condition,會建議多train一個vae 嗎,還是其實用pretrain vae 再finetune transformer 就好了。

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

3 participants