←back to thread

Z-Image: Powerful and highly efficient image generation model with 6B parameters

(github.com)
396 points doener | 5 comments | 30 Nov 25 11:36 UTC | HN request time: 0.392s | source
1. idontwantthis ◴[06 Dec 25 18:43 UTC] No.46175575[source]▶
Does it run on apple silicon?
replies(2): >>46175677 #>>46175681 #
2. iamflimflam1 ◴[06 Dec 25 18:55 UTC] No.46175677[source]▶
It's working for me - it does max out my 64GB though.
replies(1): >>46175745 #
3. sheepscreek ◴[06 Dec 25 18:55 UTC] No.46175681[source]▶
Apparently - https://github.com/ivanfioravanti/z-image-mps

Supports MPS (Metal Performance Shaders). Using something that skips Python entirely along with a mlx or gguf converted model file (if one exists) will likely be even faster.

replies(1): >>46177478 #
4. sheepscreek ◴[06 Dec 25 19:04 UTC] No.46175745[source]▶
Wow. I always forget how unlike autoregressive models, diffusion models are heavier on resources (for the same number of parameters).
5. opensandwich ◴[06 Dec 25 23:13 UTC] No.46177478[source]▶
(Not tested) though apparently it already exists: https://github.com/leejet/stable-diffusion.cpp/wiki/How-to-U...