Re:Easy Stable Diffusion XL in your device, offline
by calamari4065 on Friday December 01, 2023 @03:11PM
(#38491637)
Is this at all usable on a CPU-only system with a ton of RAM?
[ Parent
| on HN ]
Re:Easy Stable Diffusion XL in your device, offline
by brucethemoose2 on Friday December 01, 2023 @04:00PM
(#38492293)
Not really. There is a very fast LCM model preset now, but its still going to be painful.
SDXL in particular isn't one of those "compute light, bandwidth bound" models like llama (or Fooocus's own mini prompt expansion llm that in fact runs on the CPU).
There is a repo focused on CPU-only SD 1.5.
Re:Easy Stable Diffusion XL in your device, offline
by calamari4065 on Friday December 01, 2023 @08:19PM
(#38494829)
Yeah, llama runs acceptably on my server, but buying a GPU and setting it all up seems really unfun. Also much more expensive than my hobby budget
Re:Easy Stable Diffusion XL in your device, offline
by brucethemoose2 on Friday December 01, 2023 @09:06PM
(#38495155)
You don't need a big one, even an old 4GB GPU will massively accelerate the prompt ingestion.