← Back to context Comment by GaggiX 2 days ago Very nice being able to read an actual paper on a powerful text-to-video model. 1 comment GaggiX Reply liuliu 2 days ago Yeah. It is great. So apparently separating spatial / temporal attention works if you are careful and train with large enough dataset too!
liuliu 2 days ago Yeah. It is great. So apparently separating spatial / temporal attention works if you are careful and train with large enough dataset too!
Yeah. It is great. So apparently separating spatial / temporal attention works if you are careful and train with large enough dataset too!