Works best on simpler prompts. Has been trained on 57 high quality images. First Lora I've made where I actually try to give the images good tags, so it has relativly good prompt coherence. Not all results are perfect though. Highly recommended to be use with ADetailer to get good faces. Tested with <a target="_blank" rel="ugc" href="https://civarchive.com/models/1003674/purerealism-mix-xl">PureRealism</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/573152/lustify-sdxl-nsfw-and-sfw-checkpoint"> </a>but probably works fine with other models. Inspired by <a target="_blank" rel="ugc" href="https://civarchive.com/models/854522/dressed-to-naked-or-female-only-or-flux">Pooors Lora</a>Trigger words "Dressed undressed". Use "phone, mirror" to get a mirror styled selfie.Hope you enjoy!

Files with SHA256: 2fe9dfc2fd477dd1ffdd706a68e87724185479ddf5dab61486d14db2351a3c9d