AnimateDiff icon indicating copy to clipboard operation
AnimateDiff copied to clipboard

Published 20 hours ago • verified publisher icon guoyww

difference between finetuning the unet's image layers and training motion modules

Open song-wensong opened this issue 9 months ago • 0 comments

What is the difference between finetuning the unet's image layers and training motion modules? Suppose I want to train animatediff on a small new dataset (about 72 minutes of video clips in total), should I use finetune?

song-wensong avatar May 06 '24 15:05 song-wensong