2023/5/31 update

Retrain the model using new craft. Reduce learning rate to mitigate overfitting.

Introduction

A LoRA model trained with images illustrated by Kitsune-neko. The trigger tag is 'kitsune-neko'. The key features are 'shiny, shiny skin'. The 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) are recommended. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.6 version (original) YesMix.

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.