Open-Sora icon indicating copy to clipboard operation
Open-Sora copied to clipboard
verified publisher icon hpcaitech

Can this be used to train image to video models? Is there any guide on how to prepare dataset for that task?

Open alethea-deepak opened this issue 1 year ago • 1 comments

alethea-deepak avatar Mar 10 '24 16:03 alethea-deepak

This is just for text-to-video now. We may implement this feature in the future.

ver217 avatar Mar 11 '24 09:03 ver217

Now our code can train on both images and videos. Please see instructions to launch experiments.

zhengzangw avatar Mar 18 '24 05:03 zhengzangw