Skip to content

Is it possible to use a Lora or a finetuned model for SDXL Turbo method? #182

@timosenko1

Description

@timosenko1

As far as I can see, the loading of a LoRA model is not possible for the SDXL Turbo model?

It is only done if model is not SDXL turbo: relevant line.

I attempted to merge the lora into the SDXL Turbo and extract the unet and text encoder to use with StreamDiffusion, but I could not get it to work.

Is there an easier way to achieve this? I would be very grateful for any help!

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