anime style merge stable diffusion

Ritium is a universal anime model. The goals of working on it were as follows:

The settings will also be universal:

Set clip skip 1-2, ENSD: 31337, use samplers: DPM++ 2M Karass, Eular A, DDIM, CFG Scale 6-10 on average, but values above or below may also give good results.

My negative prompt:

(deformed, distorted, disfigured:1.3), EasyNegative, (bad_prompt:0.8), (bad_prompt_version2:0.8), poorly draw, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4) badhandv4

The Embeddings I use in `negative prompt':

badhandv4

easynegative

bad_prompt


license: openrail