mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
We now require more free memory to avoid attention slicing. 17.5% free was not sufficient headroom, so now we require 25%.
We now require more free memory to avoid attention slicing. 17.5% free was not sufficient headroom, so now we require 25%.