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

New Feature Suggestion: Choose specific duration of the video to affect - for example only 3-6 seconds of a 10 second video. #374

Open
simplyexperimental opened this issue Sep 7, 2024 · 0 comments

Comments

@simplyexperimental
Copy link

simplyexperimental commented Sep 7, 2024

A good idea came up to me - say your target video is 10 seconds and the driving video is 10 seconds - by default live portrait will apply to the entire video duration of the target.

I would like to suggest to affect a custom duration of the video for example if i ask for 5 seconds then live portrait will only apply the modification of the driving video to the target starting at the duration I entered which is 5 seconds and leaves th first 5 seconds of the target video untouched.

In advanced implementation live portrait could even try to interpolate the last second with the original to make the blend of live portrait and the target video at that 5-6 second mark flow more naturally.

Example:
I have a video that is 10 seconds long and only at the last 3 seconds the person laughs in the video that's it the rest of the first 7 seconds the person doesn't do much or perhaps they talk about something then go into the laugh at the last 3 seconds.

I would like to be able to specifiy to live portrait that I want to affect seconds 1-6 - leaving the last 4 seconds of the video untouched.

Implementation:
I don't need to worry about any special editing of the driving video - live portrait gives a option to specifiy for the target video what duration from and to that I want modified and the same occurs for the driving video where I can specificy what part of the video from and to - to be appled to the target video.

If that is done correctly I can make the person say what I want them to say - a leadup for a joke for example then make them laught as they originally did from seconds 7-10.

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

1 participant