Image credit to the talented @Myrmicus

I've decided to lean into being the single image dataset LoRA guy and make some fun single image LoRAs. Training data is included.

This LoRA will make something really similar to the original image, but this is intentional. Use lower strengths (0.6 and below) to break out of the original and make something inspired by it, or higher strengths to stick close to the original (0.8 and above).

The LoRA was regularized and will respond to the regularization dataset captions as well, most notably "galena" but also (much more weakly) "oatd". Repeating these style words will make their respective effects stronger. You can use higher strengths with these alternate styles.

Long form captioning: yd woman, 1girl, elf, pointed ears, black eyes, black sclera, black hair, braided hair, long hair, tall, slender, large breasts, dancing outfit, revealing outfit, black and yellow clothes, transparent clothes, gold jewelry, gold lipstick, full body, holding spear, dancing pose, white background, simple background

Short captioning: yd woman, 1girl, holding spear, dancing pose, full body

Also white background, simple background is a very strong caption and is recommended if you want a simple white background. These and the short captioning got most of the training, so that's what you should use.

yd woman has captured the original style very strongly.

This LoRA has a tendency to feminize men even with male-ified versions of trigger words like yd man

Training data included. It's a single image and the above captioning.