- cross-posted to:
- technology@lemmy.world
- cross-posted to:
- technology@lemmy.world
You must log in or register to comment.
Looks interesting, but also somewhat complicated. Now generation has to run through 3 models? I thought it was bad enough having a separate refiner model for sdxl.
It’s based on Würstchen which has real savings on training, but the VRAM requirement is through the roof.
Sdxl was 3 models too. Base, refiner and vae.
Cascade is 3. Lores, hires, vae.
Oh wow, I was just looking for updates on this yesterday and suddenly this pops up! Very exciting!
deleted by creator