2023/2/15 update
Update dataset and model. Use offset noise to improve ability to generate lighter/darker images. Reduce the model file size to 1MB.
2023/2/8 update
Decrease the learning rate of text encoder to prevent overfitting.
Introduction
A LORA model of Taihou (azur lane) trained with 360 highres images, including nsfw and alternate costume, such as enraptured companion. The NAI's VAE is recommended. 0.6~0.8 weights are good.
Description
Update dataset and model. Use offset noise to improve ability to generate lighter/darker images. Reduce the model file size to 1MB.
FAQ
Details
Downloads
4,859
Platform
CivitAI
Platform Status
Deleted
Created
2/15/2023
Updated
7/29/2026
Deleted
7/5/2026
Trigger Words:
taihou \(azur lane\)
taihou \(enraptured companion\) \(azur lane\)
red eyes
twintails
hair between eyes
ahoge