Re:Easy Stable Diffusion XL in your device, offline
by philote on Friday December 01, 2023 @12:41PM
(#38489589)
Another con is it only works on Silicon Macs.
[ Parent
| on HN ]
Re:Easy Stable Diffusion XL in your device, offline
by Vicinity9635 on Friday December 01, 2023 @03:04PM
(#38491549)
Apple Silicon* I presume?
This could honestly be the excuse I need (want) to order an absolute beast of a macbook pro to replace my 2013 model.
Re:Easy Stable Diffusion XL in your device, offline
by quitit on Friday December 01, 2023 @04:05PM
(#38492394)
If it's just for hobby/interest work, then just a heads-up that even the 1st generation Apple Silicon will turn over about one image a second with SDXL Turbo. The M3s of course are quite a bit faster.
The performance gains in recent models and PyTorch are currently outpacing hardware advances by a significant margin, and there are still large amounts of low-hanging fruit in this regard.
Re:Easy Stable Diffusion XL in your device, offline
by wayfinder on Friday December 01, 2023 @04:56PM
(#38493029)
If you want an absolute beast, especially for this stuff, you probably want Intel + Nvidia. Apple Silicon is a beast in power efficiency but a top of the line M3 does not come close to the top of the line Intel + Nvidia combo.
Re:Easy Stable Diffusion XL in your device, offline
by Vicinity9635 on Friday December 01, 2023 @05:04PM
(#38493137)
Well this would just be the excuse. I'm typing this on a Ryzen 5950X w/32 GB of RAM and a 4090. So I guess I already have the beast?
Re:Easy Stable Diffusion XL in your device, offline
by NorwegianDude on Friday December 01, 2023 @06:25PM
(#38494004)
I guess EPYC and a few H100s is the next big step, at a much higer price point...