Kohaku XL

An anime SDXL model trained on 100kπ images.

Introduction

This model is trained from sdxl-1.0-base and merged with some other anime models to get optimal result.
I’m planing more training on more images (around 1.6M imgs) and some style lycoris models. so now it is just alpha version.

Usage Details

This model is very flexible on resolution, you can use the resolution you used in sd1.x/2.x to get normal result(like 512×768), you can also use the resolution that is more native for sdxl(like 896*1280) or even bigger (1024×1536 also ok for t2i).
negative_XL neg embedding is recommended.

Acknowledgements

Datasets

• 280k imgs from Mynefactory

• 30k imgs from cybermeow

Models

• AIO-FantasticAnimeXXXL

• CounterfeitXL