Skip to content

MMDiT v/s Cross Attention #2

Description

@ando-shah

Congratulation on the CVPR acceptance! Your paper notes that you use MM-DiT, but for conditionals you "use standard cross-attention conditioning on the flattened patchified sequence each layer of the network".

Do you only have the noise input as a stream to MMDiT and have the conditionals cross attend to them after every self-attention block? If so, why bother with MMDiT (how is joint attention useful here?) and just use DiT / JiT instead? Or is it that you use the expanded / funneled fields as independent streams?

Happy to wait for the code drop, but could also do with a short response!

Thanks!

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions