Description:

A calm, matte modern-anime look. Colours go muted and slightly cool, shading turns soft and flat, and the lighting becomes quiet and cinematic, like a still from a modern TV anime.

Known quirk: it pulls hair and clothes toward darker, desaturated colours, so bright character colours can come out darker (in the previews, silver hair turned black). Name the colours in your prompt if you need them kept.

This isn't a trained LoRA. No images were used to make it. It comes from steering neurons inside the base model:

• I mapped the UNet's feed-forward neurons into groups. This file is three groups of about 1,000 neurons each, across three layers (one in the middle of the UNet, two style layers), mixed by a random combination search.

• The LoRA stores that push as a bias change, which is why the file is only about 17 KB.

How to use

• No trigger word. Just load the LoRA; it acts on the model only, not the text encoder.

• Strength 1 is the look in the previews. The effect scales linearly with strength: lower it for a lighter touch; negative values push the other way.

• It stacks with other LoRAs.

• Preview settings: 768×1024, 20 steps, CFG 4.5, DPM++ 2M Karras.

Compatibility

• Made and tested in ComfyUI (Load LoRA / LoraLoaderModelOnly) on prefectIllustriousXL v4.0.

• Other UIs: the file holds only bias changes, which some UIs (A1111 / Forge) may not load. If nothing changes, that's why.

• Other Illustrious checkpoints: untested, but they share the base, so it may carry over.