[Feature Request]: Refiner models for SDXL

[MLTQ]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

Support the use of refiner models, allowing better content from SDXL style model sets

Proposed workflow

1. Load base model as normal
2. Have a drop down for selecting refiner model
3. Select at what step along generation the model switches from base to refiner model
4. On generate, models switch like in base A1111 for SDXL

Additional information

No response

Are you going to help adding it?

I may get around to this, but I don't have the time for another project unfortunately...