Skip to content

Support providing diffusion models and text encoders separately? #352

Closed
@stduhpf

Description

@stduhpf

With very large open models like SD3 medium and Flux.1 gaining popularity It's becoming comon to provide the diffusion model (unet/diffusion transformer) part of the model and the text encoders separately, since the text encoders can often be reused across different models, to save internet bandwidth and storage space.

I think it would be cool to support these split models here. It could also be a way to use different quantization for different parts of the model.
VAEs can already be provided separately, and this is the same kind of thing.

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