Moe Fussion Anima
Moe Fussion focuses on providing wide spectrum of models suitable for different purposes. You are free to use these models however you want to what Anima License allows. Please read a rest to know how to use these models.

General Info:
This is a whole new generation of models based on Anima, better prompt adherance, composition, knowledge, details than SDXL based models like Illustrious. The ecosystem is new so you may not find Controlnets and some LoRAs yet. This model was made to improve backgrounds and be easier to use, it also comes with strong base style, prompting artists still work but their style will be altered by the base style. Before you use this model make sure you have fully updated ComfyUI or SwarmUI, I do not guarantee it will works somewhere else.
There are 3 variants, 0 is base A and B goes opposite directions from 0.

Cfg: around 4 maybe closer to 3
Steps: 30+
Sampler: er_sde
Scheduler: Simple

Negative prompt: lowres, worst quality, low quality, old, early, bad anatomy, bad hands, 4koma, comic, greyscale, censored, jpeg artifacts, blurry, simple background

Prompting style: use danbooru tags with combination of natural language, longer prompts may perform better, it is as well possible to use just tags or just natural language it will work just fine. For artists use @artist also prompting is case sensitive in this model.

These are not absolute rules how to use the model, feel free to experiment, for some specific scenarios different configuration may be better.