KayWaii / README.md
kayfahaarukku's picture
Update README.md
5dfcf9a verified
metadata
license: creativeml-openrail-m

HF page is not maintained anymore. Please move to Civitai

This model will always be updated on Civitai first, then it will be uploaded here if I don't forget.

Welcome to KayWaii, a "young-aged" anime oriented model. This model is very capable of generating "young girls".

The model uses similar merging methods used to merge AingDiffusion, a powerful anime model, also merged by me.

Guide to generate good images with this model

  • Use the VAE I included with the model. To setup VAE, you can refer to this guide.

  • Use EasyNegative for negative prompts (highly recommended), you can add other embeddings and negative prompts alongside it as well.

  • Hi-res fix is a must if you want to generate high-quality and high-resolution images. For the upscaler, I highly recommend SwinIR 4x or 4x-AnimeSharp.

    Important: I spotted an issue that in a rare case, the VAE broke the upscaled output. You can set the VAE to "None" if the issue occurs.

  • Set Clip skip to 2, ENSD (eta noise seed delta) to 31337 and eta (noise multiplier) for ancestral samplers to 0.667.

===

Special thanks to kawAICE