Model Information





Description
This is an illustrious anime model, focused on consistency and detailed backgrounds with a painting-like artstyle. It’s very easy to control and will yield good results without many quality tags. Works best for generation of the scenes requiring a high level of small details.
Short usage guide
Use DPM++ 2M SDE, with CFG 3, 20-40 steps.
General usage is pretty good around CFG 2 to 4, lower CFGs are much less saturated and allow to generate consistently good backgrounds, while CFG 4 makes the image more colorful. Hires fix is not required, but ADetailer is probably preferable.
Prompts
I use three sets of prompts with similar frequency, every one of them has decent outputs, it's more a matter of style.
First one allows to achieve the best lighting, but not every image really needs it:
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 just decent, it's probably the most consistent:
masterpiece, best quality,detailed faceNegative
lowres, bad quality, bad anatomy, sketch, jpeg artifacts, signature, watermark,simple backgroundThird one is simple, almost pure model output to achieve more painterly feel:
masterpieceNegative
worst qualityAlso you can add this in negative as you see fit because I had problems with characters having longer than usual fangs or random sweating:
fangs,sweat,sharp teeth
Base models used in this merge:
NoobIEater by jyrrata https://civitai.com/models/879640?modelVersionId=1034051
NTR MIX by tkio https://civitai.com/models/926443?modelVersionId=1061268
VentusMix
v1.0
Model Details
- Type
- AI Model
- Task
- text-to-image
- Subtype
- Safetensors / Checkpoint AI Model
- Created
- Updated
- June 6, 2026