mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
~7% speedup (1.57 to 1.69it/s) from switch to += in ldm.modules.attention. (#482)
Tested on 8GB eGPU nvidia setup so YMMV. 512x512 output, max VRAM stays same.
This commit is contained in:
parent
aba94b85e8
commit
49a96b90d8