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: woman, outer space, stars, ??????????????, from side, smile, long blonde hair, lips, green eyes, blue planet, looking at viewer, space uniform
Medium form captioning: woman, outer space, from side, space uniform, planet
Trigger word only: outer space
Put any details you don't want from the original into the negative prompt. The green eyes, long blonde hair, and space uniform are especially likely to override your prompts.
Initial Release, resized from rank 128 LoRA using sv_fro 0.9, max rank 128
1. Права на репостнутые модели принадлежат оригинальным создателям.
2. Для подтверждения авторства модели создателям следует обратиться к сотрудникам SeaArt AI через официальные каналы. Нажмите, чтобы подтвердить
