Download
1 variant available
720 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
5.4K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
1.7K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
(10)
Oct 25, 2025
Trained with entirely 1024x1024 images with more curation to bake facial features into the model. Hair color still iffy.

23.7K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
4980 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
5.7K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

Created on Civitai
License:
Illustrious LicenseRefined model for my two OCs with better training data. Still haven't gotten it to fully associate the hair color with the trigger words, but now has somewhat works as a style LoRA for the facial structure.
Theoretically "lunaviltaria" should produce blue hair, "solaviltaria" should produce red hair, both with similar facial features and blue eyes. In practice the LoRA has picked up more on the image styling and less on the distinctive character attributes.
