2023/12/26 update

Update dataset. Retrain the model using the latest technology to make generated images more similar to the dataset.

2023/7/19 update

Update dataset and training strategy.

Introduction

A LoRA model of Hindenburg from Azur Lane. The trigger tag is hindenburg \(azur lane\). The key features are red hair, demon girl, demon horns, ahoge, underboob, elbow gloves, pointy ears. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.6 version, 2.0 version Yesmix and MeinaMix to verify the compatibility of this LoRA model on different base models.

This model still requires more images to improve its generalization ability.

Cautions (Must Read)

For anime model,

pls disable 'face restoration' during generating.

pls disable 'face restoration' during generating.

pls disable 'face restoration' during generating.

• Some preview images are generated using 'Hires Fix' and upscaled using 'SD Upscale'. Thus, if you wanna generate the preview images, pls download the original preview images and analyze them using 'PNG INFO' in webui to get all generating information.

BTW, make sure set this option in 'Stable Diffusion' settings to 'CPU' to successfully regenerate the preview images with the same seed.

• The training resolution of this model is 1024x1024, so generating resolution must not exceed this range. Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.

• For 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) users, make sure add '--no-half-vae' in command line of webui to prevent generating black images. See voldy's log for the details of edit method. For high-performance GPU, make sure 'medvram' and 'lowvram' mode are disabled.