Moe Fussion/Loli Diffusion XL
Focuses on providing wide spectrum of models suitable for different purposes. You are free to use these models however you want to what SDXL License allows, however I will be happy if you credit me or at least give me a donate https://boosty.to/moefussion Please read a rest to know how to use these models. Older versions you will find on hugging face https://huggingface.co/LoliRimuru/moeFussion/tree/main
General Info:
The base model is NoobAI XL which so far is leading model. This models have better understanding of complex prompts, however you should stick to danbooru tags and e621 tags. There are 3 models, Z and DB225 and DBOM which both have a slightly different default style and went slightly different ways so I recommend you to try which suits you better. Versions with vz are zsnr + vpred models.
Example settings:
Cfg: around 4
Steps: around 40
Sampler: Euler a
Schedular: Normal
Negative prompt: worst quality, normal quality, old, early, jpeg artifacts, watermark, signature, username, logo, unfinished, simple background, multiple views, comic, 4koma, censored, mammal, anthro, furry, ambiguous form, feral, semi-anthro, monochrome (if you want furry and stuff than ofc remove it from negative)