VentusMix
About this model
This is an illustrious anime model, focused on consistent outputs and detailed backgrounds with a painting-like artstyle. It’s pretty easy to control and it will yield good results without many quality tags.
V2 should be a decent improvement across the board, it has better prompt adherence, colors and nicer faces. It needs a bit lower CFG than V1.
V2alt is just a small style adjustement with some lighting improvements.
Short usage guide
Use DPM++ 2M SDE, with CFG 2-2.5, 20-40 steps.
Hires fix is not required, but ADetailer is probably preferable.
Prompts
I use two sets of prompts with nearly the similar frequency.
First one allows to achieve the best lighting and detail, but not every image really needs it and excessive quality tag prompting can degrade the prompt adherence:
masterpiece, best quality, amazing quality, very aesthetic, absurdres,newest,detailed face,(volumetric lighting)Negative
lowres, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest,simple backgroundSecond one is simple, almost pure model output with two quality tags to fix small details:
masterpieceNegative
worst qualityFor better shadows just add this, maybe also add "solo" if you get shadowy figures, Illustrious does that sometimes:
volumetric lighting,shadowsAlso you can add this in negative as you see fit because I had problems with characters having longer than usual fangs or adetailer adding teeth over lips:
fangs,teeth,sharp teeth
Base models used in this merge:
NoobIEater by jyrrata MIX by tkio
Related Models
Similar AI models you may like
Juggernaut XL
Pony Diffusion V6 XL
CyberRealistic Pony
CyberRealistic
epiCRealism XL
Nova Anime XL
✨ Lazy Embeddings for ALL illustrious NoobAI Pony SDXL models LazyPositive LazyNegative (Positive and Negative plus more!)
