2023/4/15 update

Upload lycoris version. The preview images of the new model are generated using 'hires fix' and upscaled with 'sd upscale'.

Introduction

A LoRA model trained with ~180 images by Dishwasher1910. The 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) are recommended. 0.6 ~ 0.8 weights are good. The preview images are generated using latest version of YesMix and EasyNegative embedding. It's also recommended to use this and any Azur Lane LoRA (e.g. Musashi, Taihou, Shinano) to generate high-quality masterpiece.