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

Finetune / lora / training - any chance for those? #101

Open
ChieVFX opened this issue Feb 18, 2025 · 3 comments
Open

Finetune / lora / training - any chance for those? #101

ChieVFX opened this issue Feb 18, 2025 · 3 comments

Comments

@ChieVFX
Copy link

ChieVFX commented Feb 18, 2025

It'd be great if we could finetune / train loras for this, so we can adapt it to our uses.
As you probably have noticed from Hunyuan Video model, releasing training code makes the model much more popular and the tool much more diverse. I see nothing related to training or finetuning in plans, so I really hope you add it there(or at least consider it).

One of the comepting models, Trellis is expected to release training code sometime this spring, I believe.
I'd prefer to work with Hunyuan, as you have proven that you do a great job at this.

Whatever you decide, thank you for releasing this gem.

@Zeqiang-Lai
Copy link
Collaborator

Thanks @ChieVFX, we acknowledge the benefits of releasing the finetuning code, but we are still discussing the timeline for it.

@Yidada
Copy link

Yidada commented Feb 20, 2025

Really looking forward to it! A truly great project—huge thanks to the team!

@usual0
Copy link

usual0 commented Feb 26, 2025

同蹲

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

4 participants