It was trained with NF4 weights while respecting the original Turbo model steps (unlike other trainers). Used custom scripts, slightly overbaked compared to other loras.
Tested with Haoming's A1111 Forge Neo, in bfloat16 precision.
Description
Each downloadable file has a distinct character or style. I have decreased the lora multiplier in the training, and now it converges faster while maintaining stability compared to the first version of this series.
Use "loose brushstrokes" for a stronger effect.