This is an experimental LoRA that does one thing relatively well: PIV ???. You have to describe the scene precisely (see the prompts for example images) and sometimes you need to remind it that everyone is ?????. It doesn't really know the names of ??? positions (if you say cowgirl, you get a girl in a cowboy hat, for instance).

That being said, it's a LoRA that trains Qwen Image, which is otherwise completely ignorant of ???, to do pictures of sex.

It can also do female ??????, but despite the presence of ???? pics in the training data, it doesn't seem to understand ????? outside the context of being in vaginas. I think a full finetune will probably be required to do any better than this, so I wouldn't necessarily expect updates.