Trained on a smaller dataset of 150 fully rendered works by Raiou. https://twitter.com/raiounsfw
I recommend "realistic" as the negative prompt.
Unlike the SD1.5 version, it's mostly trained on his newer stuff, so expect clean linework. I might train a sketchy/soft lines model later, idk, let me know if that's something you want.
Description
Trained via Civitai on ~700 works by RaiouNSFW. https://twitter.com/raiounsfw
Use tags like "thick lips, big lips" to get that luscious bimbo look. It can handle a variety of lipstick colors, but red is unreliable for some reason.
FAQ
Comments (2)
I love this Lora. Can you do a version for SDXL?
I actually already have, just haven't gotten around to making sample images and posting it. I'll do it today! Or tonight. Probably.