Closed DunyangNi closed 1 week ago
If I remember correctly, we train MLD on the original MLD repo and then directly load the pre-trained checkpoint to train MotionLCM. But there are some useless attributes in the pre-trained checkpoint as shown below. You only need to remain the 'state_dict'
.
The LAST step is to delete one useless parameter saved in 'denoiser', 'denoiser.mem_pos.pe'
. This param is not been used in denoiser but the author left it carelessly.
Finally, save the cleaned checkpoint which is a dict
with ONE key state_dict
.
If you encounter any issues in this process, feel free to inform me. hahaha
Feel free to open this issue
Is it possible to train MotionLCM on a checkpoint pretrained with the original MLD repo? If not, what are the configurations you use to pretrain the MLD?