Skip to content

question about the relationship of target_idx and vid_idx #26

Description

@renleidewenming


我理解CogVideoX1.5-5B-I2V的VAE是将4N+1视频帧编码为N+1个latent,其中首帧单独编码,后面每4个视频帧对应一个latent。那么在_prepare_ref_latent_i2v函数中,target_idx对应的应该是(vid_idx+3)// 4,而非target_idx = vid_idx // 4。我的理解是否正确?

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