Creates the humanoid race of Daedra featured prominently in Oblivion: the Dremora.

The model was trained on both male and female members of the race across a diverse set of places that featured them.

The primary trigger for them is the word "Dremora," but you are likely to have better results by using "Dremora man" or "Dremora woman" when prompting, since each source image was tagged as such.

The secondary trigger for them to determine what skin type they have is either "blue skin" or "ashen skin," and their face tattoos can be brought out or suppressed with the trigger "facepaint."

You can control the length of their horns by using

• no horns

• short horns

• medium horns

• long horns

Additionally, if you want to ensure or prevent a secondary set of horns, a dual set of horns can be prompted with "four horns."

This model is not specifically trained to create Daedric armor, but it was contained in the source data, and thus may be brought out with the right prompting.

• Skyrim-style armor was consistently tagged as "black daedric armor"

• Oblivion-style armor was tagged as "red daedric armor."

If prompting for armor, the following triggers may aid your generation prompts, since they were used frequently in the dataset:

• shoulder armor

• gauntlets

• pauldrons

• breastplate

• chainmail

• armored boots

California AB 2013 Training Data Disclosure

• This LoRA was fine-tuned using visual data consisting of still images of video games, fanart, and Legends card art. The training data includes copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution.

• The dataset consists of 30 images collected from publicly accessible sources online. Image data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images were included as part of the training dataset. Dataset was assembled in 2025.

• This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.