Sudachis goal are easy to archive high quality flat 2d anime images. Model is trained/finetuned on KojiV2.1.
Check deathspikes loras out, they are working nice with sudachi!
My Discord for everything related to anime models and art.
If you'd like to support my work, you can do so at: SubscribeStar, every bit helps and is truly appreciated!
____________________________________________________________
Supporters:
Thanks to my supporters pttcot, SETI and Kodokuna
_____________________________________________________
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
Description
Sudachi inpainting version. SD 1.5 changed with SD 1.5 inpainting.
Use for img2img -> inpaint.
Because i rip SD 1.5 out and put SD 1.5 inpainting in, some parts of sudachi gets damaged with it. Use it in combination with the base model.
FAQ
Comments (11)
love all your models,great work!
Thanks!
can this model be used to train style?
You can train on any model you like
Wow this model is so good. I'm constantly getting great results even with prompts and loras other models don't pair so well
Even today it holds up, giving superb results with comparatively little effort. Don't sleep on this model, guys!
The only model that makes what I want when writing prompts.
Need SDXL version ;_;
I consider Kohaku_XL as the XL-Sudachi. It's very similar.
This is my favourite model from SD1.5! Will you happen to be planning to make it for Pony?
Hi, are you intending to make a SDXL or Pony version of this?
Same but for Pony AuraFlow or Flux