Depending on the model, you can provide various modifiers to get different results. The modifiers work best with the base SD 1.5 model. Photorealistic models will require you to adjust the weights to around 0.5. Other models may "override" how some words behave.Version 1.0 was trained on 512x768 (portrait) images, so those will result in the best. Version 1.1 was trained on 768x768 images.You can generate 768x512 (landscape), but you may encounter missing limbs, extra arms, and so on.Example prompts<ul><li>legspread a photo of a naked woman spreading her legs and showing off her pussy 👈 this is always a good starting point</li><li>legspread a photo of a naked woman spreading her legs and showing off her pussy (with labia)</li><li>legspread a photo of a (caucasian|black|whatever else) naked woman spreading her legs and showing off her pussy</li><li>legspread a photo of a naked woman spreading her legs and showing off her (shaved|trimmed|bushy) pussy</li><li>legspread a photo of a naked woman with (small|medium|large) breasts spreading her legs and showing off her pussy</li><li>legspread a photo of a (petite|curvy|thick) naked woman spreading her legs and showing off her pussy</li><li>legspread a photo of a naked woman with (fair|tan|olive|brown|chocolate) skin spreading her legs and showing off her pussy</li><li>legspread a photo of a naked woman spreading her legs and showing off her pussy (and asshole)</li><li>legspread a photo of a naked woman (propping herself up) spreading her legs and showing off her pussy 👈 I didn't have a lot of images for this one, but in the next version there will be</li><li>legspread a photo of a naked woman (with tan lines) spreading her legs and showing off her pussy</li></ul>You can mix and match these modifiers how you see fit. You can put the other options in the negative to get a better result. No guarantees they'll always work!

Legspread

Used <a target="_blank" rel="ugc" href="https://github.com/bmaltais/kohya_ss">bmaltais's implementation of kohya_ss LoRA training scripts</a>.This version is resumed from 1.0 with 768x768 images. It will handle usual 512x768 (portrait) generations well, similar to 1.0, 768x512 (landscape) images may result in missing limbs or other weirdness. 768x768 generations are decent.It is a little overtrained, so for the base SD 1.5 model, I recommend setting the strength around 0.8, and other models, between 0.3 - 0.7.Demo images for 1.1 were generated with <a rel="ugc" href="https://civitai.com/models/4201/realistic-vision-v12">Realistic Vision 2.0</a>!Total Images: 116 total images, about half high resolutionRegularization Images: 300 total "sexy woman" regularization images from <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/ProGamerGov/StableDiffusion-v1-5-Regularization-Images/tree/main">ProGamerGov's dataset at huggingface</a>.Trigger word: legspread a photo of a woman spreading her legs and showing off her pussyTraining Steps: ~10000 in 1.1, ~17000 total including 1.0Unet Training Rate: 5.0e-05 (0.00005)Text Encoder Training Rate: 5.0e-05 (0.00005)

Files with SHA256: d28507abce859be25c663911b391b6b9ed19fcda2f5cbc251f207c35dc878917