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

gradio UI for finetuning T2V AND I2V - CogVideoX 5B #386

Closed
GeeveGeorge opened this issue Oct 2, 2024 · 2 comments
Closed

gradio UI for finetuning T2V AND I2V - CogVideoX 5B #386

GeeveGeorge opened this issue Oct 2, 2024 · 2 comments
Assignees

Comments

@GeeveGeorge
Copy link

Feature request / 功能建议

gradio UI for finetuning T2V AND I2V - CogVideoX 5B @zRzRzRzRzRzRzR @LittleNyima , with multi gpu and single gpu options.
also script for captioning videos the users have.

Motivation / 动机

a gradio UI will be easy to use. for videos, include a path url textbox where the user can specify the path to their video dataset.

Your contribution / 您的贡献

if there is a good well tested fine-tuning script, then i could help contribute to the developement of the gradio UI.

@GeeveGeorge
Copy link
Author

@zRzRzRzRzRzRzR @LittleNyima fine-tuning the 5B model still seems like a very confusing process. any updates on simplifying the same?

@zRzRzRzRzRzRzR zRzRzRzRzRzRzR self-assigned this Oct 3, 2024
@zRzRzRzRzRzRzR
Copy link
Member

We are still testing the relevant code together with the Huggingface team, such as
huggingface/diffusers#9482
Currently, the fine-tuned videos include both normal and faulty ones, and we are verifying the faulty videos

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

2 participants