Description:

A light, clean linework look. Outlines go thin and confident, colours turn soft and flat with very little shading, and backgrounds fade to plain warm paper. It feels like a tidy character sheet or a clean sketch that has been neatly coloured.

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

• An automated evolutionary search mixed and mutated groups of the UNet's feed-forward neurons; this look came out of round 2 as #261.

• This file is five groups of about 1,000 neurons each, across five layers (two early in the UNet, one in the middle block, two style layers).

• The LoRA stores that push as a bias change, which is why the file is only about 28 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.