A early test model for a hogtie/barefoot Lora trained on Realistic Vision. It takes quite a bit of fiddling to get a decent image in it's current state. Uploaded just to show progress.
Edit:
I'd suggest trying to start with one word, i.e. hogtied, prone, kneeling, etc, and then add a word or two to try and add what you want, to see what works.
Description
A early test model for a hogtie/barefoot Lora trained on Realistic Vision 4.0. It takes quite a bit of fiddling to get a decent image in it's current state. Uploaded just to show progress. Hogtied, on stomach, barefoot, rope, front view, side view, rear view, kneeling, prone, are the main tags (check uploaded images for used tags). it's kinda rigid and the quality can drop quite a bit by changing one or two tags. I'll have to expand my image set to try and add more flexibility. Usually used strength 0.6-0.7, usually used 512x512, but sometimes it was necessary to increase one dimension a little to keep it from squishing, and denoising strength of 0.5 with nearest for upscaling.