DiSReg: New LoRA Training Method Uses Self-Regulation to Eliminate Tag Pollution

bdsqlsz · x · 2026-09-06

hakomikan introduced DiSReg (Differential Self-Regulation), a new LoRA training technique shipped in TrainTrain that targets tag pollution: when training a character LoRA, tags like 1girl or solo absorb learning too, so the character activates without the trigger word.

How it works

The post includes the loss formulas for both the character-training and self-regulation steps, and the feature is already implemented in TrainTrain — useful for anyone training character/style LoRAs needing precise trigger control.

Original post →

More from Multimodal

Multimodal channel →