Hello, thanks for your work! This isn't really an issue, but more of an enhancement.
I've just released training code for MotinLoRAs that are compatible with this repository. It uses the recently released MotionDirector method as it decouples the spatial information from the temporal, allowing you to focus more on motion modelling. You can try out the code here:
Here's an example from a recent run (at default settings from my repository) that took about 13.5GB of VRAM and trained in about 300 steps in 10 minutes on a 3090.
Edit: Added update for 500 steps in 16 minutes of training
I saw in the README that training MotionLoRAs are in the works, so this may introduce some useful synergy between these two repositories :+1: .
Hello, thanks for your work! This isn't really an issue, but more of an
enhancement
.I've just released training code for MotinLoRAs that are compatible with this repository. It uses the recently released MotionDirector method as it decouples the spatial information from the temporal, allowing you to focus more on motion modelling. You can try out the code here:
https://github.com/ExponentialML/AnimateDiff-MotionDirector
Here's an example from a recent run (at default settings from my repository) that took about 13.5GB of VRAM and trained in about 300 steps in 10 minutes on a 3090.
Edit: Added update for 500 steps in 16 minutes of training
I saw in the README that training MotionLoRAs are in the works, so this may introduce some useful synergy between these two repositories :+1: .