Sudachis goal are easy to archive high quality flat 2d anime images. Model is trained/finetuned on KojiV2.1. My Discord for everything related to anime models and art. You can support me on my patreon and if you are interested, we also have a collaboration of multiple AI artists named Sinful Sketch Society that you can support!
Check deathspikes loras out, they are working nice with sudachi!
Supporters:
Thanks to my supporters Riyu, SETI, Jelly, lawrencium_Lr103, Alessandro and Kodokuna on my patreon!
You can support me on my patreon, where you can get other models of me and early access to model versions.
_____________________________________________________
Using the model:
Use mostly danbooru tags. No extra vae needed.
Use clip skip 2 with sampler DPM++ 2M Karras or DDIM.
Use "R-ESRGAN 4x+ Anime6B" as upscaler, if you want to remain on a flat style.
Don't use face restore and underscores _, type red eyes and not red_eyes.
_____________________________________________________
Black result fix (vae bug in web ui): Use --no-half-vae in your command line arguments
Trained/finetuned on koji.Detail: Koji trained with arround 300 images, koji merged with the outer layers of the trained model. Sudachi behaves like koji with a flat stlye look.