Description:
A warm, cosy painted look. Scenes get soft lamplight and dusky shadows, rendering turns gently painterly with a little texture, and interiors feel lived-in and quiet, like a storybook or a slice-of-life key frame at dusk.
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 five groups of about 1,000 neurons each, across five layers (two early in the UNet, one in the middle block, two style layers), one pushed up and four pushed down, mixed by a random combination search.
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.


