Oatd Style (Illustrious)

This is a fairly general purpose pinup (single woman subject) LoRA. It produces a hybrid between western cartoon and anime styles. The initial version was trained on Illustrious v1.0.

If you want the full story, it's in the description of the original Pony model, which also has some more technical details about the dataset. I'm starting over with a new model card for Illustrious because I need to improve (mostly properly upscaling) the dataset to get the best results with Illustrious v1.0+, but I also don't want to just sit on my early model, so I'm starting over from version 0.1 and releasing it now.

There's no specific trigger word, but certain prompts are rich prompts and thus they should generally be included for best results.

woman - All of the training data has this caption, so it's recommended to include it for best results

from front/from side/from behind - Pick one of these options to ensure you get the right angle, it broadly prefers "from front" by default

indoors/outdoors/simple background - Pick one of the options to get the right overall setting, it prefers "simple background" by default, you can alternatively just be more specific about your setting and it should start to pick up what you mean.

The low captioning style also includes basic information about attire, body positioning, and body shape, so those captions are recommended as well. You can leave out any of these captions and it should perform fine.

On the other end of the spectrum, it's also well trained on keeping colors separated in the high captioning style so it does well at keeping colors of clothing/hair/eyes/etc. specific to that thing.

One last notable caption is face focus which will give a close up of the character's face. Useful for inpainting!

The model itself is very general purpose and should be able to make SFW or NSFW depending on how you prompt it. Some of the included training data is somewhat NSFW, including nudity and absurd female proportions, but it doesn't contain sex. By default it ranges from SFW to mildly risque.

The training data is at 1024x1024 and 1024x1536, which is why I want to get better data. It seems to work just fine at native 1536x1536 though.