Remember the golden age of eroge?

This LoRA brings back the look of mid-2010s Japanese visual novel CGs — crisp clean lineart, soft glossy shading, and those unmistakable 2015-era anime eyes.

Trigger word

nijigen2015

Put it at the very beginning of your prompt.

How to use

• Base model: Animagine XL3.1 — other SDXL anime models may work, but this is what it was trained on

• Weight: 0.8 – 1.0

• ⚠️Do NOT use year/quality tags like newest — they push the style back toward modern anime and fight the LoRA

Training details

• SDXL LoRA — dim 8 / alpha 1, 20 epochs

• 109 images, captioned with WD14 tagger

• Full training parameters are embedded in the file metadata — check the details panel on this page