Open foreverpiano opened 1 week ago
You can start to train a video generation model based on Sigma. Some of existing works are doing so.
Like Open-Sora by adding time dimension? the current version is still 1dverison,
Yes. what else do you plan to do except the 1d temporal dimension?
I don't really understand how to transform 1d to 2d easily. So is the major thing to add time embedding in fintuning?
@lawrence-cj