LususNaturae/Moss Medieval Illuminations

A style LoRA for Moss Image CFT trained on 200 images from the ByvanckB dataset for 1800 steps. I'm impressed by how well the model has learned the style to be honest. The model works even without it, but for best result, remember to prompt the fact that you want a medieval illumination.

<iframe src="https://silytics.si/embed/item/fea41d5f-9939-4d48-830c-6c6c8524af5a" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 25 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.