Hacker News new | ask | show | jobs
by ttflee 1363 days ago
On intel MacBookPro 2020, CPU-only, the original one[1] using pytorch utilized one core only. A tensorflow implementation[2] with oneDNN support which utilized most of the cores ran at ~11sec/iteration. Another OpenVINO based implementation[3] ran at ~6.0sec/iteration.

[1] https://github.com/CompVis/stable-diffusion/

[2] https://github.com/divamgupta/stable-diffusion-tensorflow/

[3] https://github.com/bes-dev/stable_diffusion.openvino/
1 comments
gpderetta 1363 days ago
Yes, I use [3] and I get 2.4s/iter on my 10 core machine. I was wondering if keras would give additional help here. I'll have to try I guess.
link