mirror of
https://github.com/invoke-ai/InvokeAI.git
synced 2025-01-08 11:57:36 +08:00
~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