Concept LoRAs #
Concept LoRAs teach Stable Diffusion models to understand and generate specific objects, creatures, or abstract concepts that weren’t well-represented in the original training data. These adaptations modify the model’s understanding of semantic relationships and visual features associated with particular subjects. For example, a concept LoRA might help the model better generate specific architectural elements, unique creatures, or particular objects with consistent characteristics. Concept LoRAs typically require more diverse training data than style LoRAs (usually 50-100 images) to capture different angles, contexts, and variations of the subject matter. They work by adjusting both the model’s cross-attention and feed-forward layers to better recognize and reproduce the defining features of the target concept.
LoRAs #
- analbeads
- Oh my God! A sex toy! 🙀
- bdsm
- BDSM is an acronym standing for Bondage, Discipline, Sadism, and Masochism.
- blue_frost
- A bit of an experiment trying to make generating kitsch winter scenes easier.
- cervine_penis
- Anatomically correct penises for antlered friends!
- hev_suit
- The HEV suit from Half-Life is an iconic armor Gordon Freeman wears throughout the series. This LoRA is trained on a bunch of fan art and screenshots featuring it.
- small_dom_big_sub
- When a smaller character being the dominant partner in a sexual relationship with a larger character.
- space
- Space is a vast and mysterious expanse explored by the Hubble and James Webb Spaces Space Telescopes.
- surrounded_by_penis
- This LoRA aims to help generating images where one or more characters are surrounded by penises from multiple sides.