mirror of
https://github.com/invoke-ai/InvokeAI
synced 2025-07-25 21:05:37 +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%.