Skip to content

Using EDM for end-to-end training of latent diffusion models #28

Description

@pandekan

It would be great if I could please get some guidance on how to adapt this framework for end-to-end training of the parameters of VAE and diffusion models on the VAE's latent space as in this LSGM paper by Vahdat et al. https://github.com/NVlabs/LSGM.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions