Files
InvokeAI/ldm/modules/attention.py
Mihai dd3fff1d3e ~7% speedup by switch to += in ldm.modules.attention. (#569)
Tested on 8GB eGPU nvidia setup so YMMV.
Re-land with .clone() fix, context #508
2022-09-14 18:10:33 -04:00

11 KiB