Take me to Valhalla!
Update: Fixed my training captions and uploaded a new version that works a bit better. The INOUT2 LoRA block weight referenced in the generation data is 1,1,1,1,1,0,0,0,0,0,0,1,1,1,1,1,1.
Description
I accidentally left underscores in my caption tags when I trained the first one. It works better without them, so I redid it.