News for hackers. Stuff that matters.
Re:Stable Diffusion with Core ML on Apple Silicon by jwitthuhn on Thursday December 01, 2022 @05:35PM (#33823953)
Even with the slower pytorch implementation my M1 Pro MBP, which tops out at consuming ~100W of power, can generate a decent image in 30 seconds.

I'm not sure exactly what that costs me in terms of power, but it is assuredly less than any of these services charge for a single image generation.

There are no comments on this comment yet.