Hey, thanks for doing this. I am looking around your git repo.

I wrote a Swift book with a couple of CoreML examples. Apple did a fine job supporting deep learning models incorporated in macOS, iOS, and iPadOS apps.

any idea if CoreML Stable Diffusion is appreciably faster or slower than regular-SD-on-Python?

( sorry if this is somehow well known, ive been trying to pay attention but havent seen anyone comment on what effect the implementation difference has had on the system performance)

It’s supposed to be roughly twice as fast:

https://arstechnica.com/information-technology/2022/12/apple...

They mention that in the M1 Ultra, it gets within a fraction of a second of the performance of an RTX 3060, which is very impressive!

Sure, an M1 Ultra computer costs 3.6K€ higher than an RTX 3060 computer nowadays, but still, it gets close to the best performance on the market.

This is neat!

Would you consider changing the license from GPLv3 to the ISC license?

https://choosealicense.com/licenses/isc/

Generally I use a libre license like GPLv3 for end-user apps to prevent others from quickly flipping them for profit, and open source license like MIT for libraries.

If you need to release a closed-source fork I’m happy to sell you a custom license.

Understandable. Thank you :)