You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I found an interesting implementation in your codes: In Line 644-674 of MotionDirector_train.py, the spatial_lora is added for each video, it will lead to a result that the Linear layer of the LoraInjectedLayer will be recursively transformed into a LoraInjectedLayer. It will lead to a process like (if two videos are used for training):
I found an interesting implementation in your codes: In Line 644-674 of MotionDirector_train.py, the spatial_lora is added for each video, it will lead to a result that the Linear layer of the LoraInjectedLayer will be recursively transformed into a LoraInjectedLayer. It will lead to a process like (if two videos are used for training):
What is the motivation? Can I only inject only one time? If the number of videos are 100, 1000, ..., won't it cause some problems?
Thanks.
The text was updated successfully, but these errors were encountered: