Re:Optical Transformers
by grishka on Thursday February 23, 2023 @02:12AM
(#34907739)
Stable Diffusion on the M1 runs on the GPU, not the ANE
[ Parent
| on HN ]
You can run it on either now (for example, MochiDiffusion allows you to pick https://github.com/godly-devotion/MochiDiffusion#compute-uni...). Anecdotally, the GPU seems to be faster for an M1 Max or up GPU, the ANE is a touch faster on anything smaller, and more power efficient in general.
I think https://machinelearning.apple.com/research/stable-diffusion-... describes running it on the Neural Engine.