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

Normalization of image or video input. #27

Open
LuPaoPao opened this issue Jan 19, 2025 · 1 comment
Open

Normalization of image or video input. #27

LuPaoPao opened this issue Jan 19, 2025 · 1 comment

Comments

@LuPaoPao
Copy link

LuPaoPao commented Jan 19, 2025 •
edited
Loading

Thank you for your outstanding contributions. I noticed that your input was normalized mean=0.5, std=0.5. However, CogVideo does not have such operation, may I ask why? Or can CogVideo generalize to this range?
@flymin
Copy link
Owner

flymin commented Jan 20, 2025

This operation is equivalent to normalizing a [0,1] image to [-1, 1], which should fit for almost all generative models. I think CogVideo are doing the same. Could you check again?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@flymin @LuPaoPao