Concept model based on 20 images (mix of drawn and photo) of Mehndi body art, a traditional form of non-permanent body 'tattooing' using paste from the henna plant. Popular in South Asia, especially the Indian subcontinent, it is often worn by women for wedding ceremonies.
Usage
Works well at a strength of 1.0. May require increasing to 1.2 with photorealistic checkpoints.
Base trigger is mehndi followed by [body part] markings
hand, arm, leg and foot markings are pretty consistent, but otherwise, the lower the tag count, the less likely it is to trigger successfully:
14 tags:
hand markings11 tags:
arm markings4 tags:
leg markings,foot markings2 tags:
belly markings,sternum markings1 tags:
back markings,face markings,forehead markings,head markings,neck markings,pubic markings
Extra
In the interest of openness and community-helping, I have uploaded the dataset along with the model, this includes: images, captions, and the training json (for kohya_ss).