Ino_mahe / Inomahe / イのマヘ💡 Artist Style LoRA (Noob Vpred)

No more trigger word needed! Just plug and play.

Larger dataset

Pre-downscaled images before training using a new better custom image downscaling script

• sd-scripts does this already, but I wanted to achieve a higher downscale quality (I can upload it later)

Introduced tag-drop at rates of 17% w. protected tags enabled during training, for training the uncond of the model. This is to make the lora's style work better on things it is not trained on (like 1girl stuff).

Higher batch size/grad acc to generalize better during training (corresponds to batch size of 4).