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.

Sign up for GitHub

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

Jump to bottom

Please add support for cogvideox #3

Open
smktech9 opened this issue Mar 2, 2025 · 1 comment
Open

Please add support for cogvideox #3

smktech9 opened this issue Mar 2, 2025 · 1 comment
Labels
feature request New feature or request

Comments

@smktech9
Copy link

smktech9 commented Mar 2, 2025

How much vram will it require to finetune using lora?
@jbilcke-hf
Copy link
Owner

jbilcke-hf commented Mar 5, 2025 •
edited
Loading

Hello,

FYI I don't know when I will implement CogVideoX, as I will add support for Wan first (it's easier as it is close to HunyuanVideo and LTX Video, while CogVideoX is among the "legacy" training scripts in the Finetrainers projects, which is why I wasn't in a hurry to implement it in comparison to newer/better models like Wan)

But I can answer your question about full finetuning, for CogVideoX you would need around 64 Gb it seems, see this table:

https://github.com/a-r-r-o-w/finetrainers?tab=readme-ov-file#support-matrix

@jbilcke-hf jbilcke-hf added the feature request New feature or request label Mar 5, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
feature request New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@smktech9 @jbilcke-hf