29
you are viewing a single comment's thread
view the rest of the comments
[-] Zarxrax@lemmy.world 5 points 9 months ago

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.

[-] Even_Adder@lemmy.dbzer0.com 4 points 9 months ago

It's based on Würstchen which has real savings on training, but the VRAM requirement is through the roof.

[-] wewbull@iusearchlinux.fyi 2 points 9 months ago

Sdxl was 3 models too. Base, refiner and vae.

Cascade is 3. Lores, hires, vae.

this post was submitted on 13 Feb 2024
29 points (100.0% liked)

Stable Diffusion

4309 readers
1 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 1 year ago
MODERATORS