Skip to content

A Question About Training SPM #27

Description

@NHeLv1

In
https://github.com/RockeyCoss/SPO/blob/main/step_aware_preference_model/trainer/tasks/spm_task.py #L370-L421
Why do we need to do a denoise step using UNET when we try to get a noisy version of the image?

Isn't
image -> vae encode -> add noise -> vae decode
better than
image -> vae encode -> add noise ->unet denoise -> vae decode ?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions