This model does the opposite of my kontext foreskin model. I primarily use it to generate control images (before images) for my kontext foreskin dataset. It is not detailed enough, but it does a good job of making the head shape, highlights, and shadows. I sometimes just go in and add the pee hole in GIMP.*the new version 1.0 is much more consistent, but still generally fails if looking at the underside of the penis. Specifically it does not render the frenulum properly. Still, it is consistent enough to make it an official version 1. <a target="_blank" rel="ugc" href="https://civarchive.com/models/1821037/kontext-foreskin-prototype">https://civarchive.com/models/1821037/kontext-foreskin-prototype</a> This lora is meant to peel foreskin on a penis that already exists in an image. It is not trained to add penises to an image. Kontext is cool but not as robust as regular Flux. This model may not make the most realistic images, but may be helpful for creating new images for datasets.<ul><li>It does not always work on every image, for some reason it may not find the penis when the body is sitting at some angles. Even though it is trained primarily on close-ups, it sometimes doesn't work on close up images.</li><li>It is not 100% consistent. Some images work better than others and some don't work well at all. You may have to generate images multiple times and sometimes it will never work.</li><li>It is intended to work on both anime AND photos, but it may not be as high quality as desired. Test it out.</li><li>It is still not very good at making subtle details like the urethra, frenulum, and folds in the skin. This is probably due to a blurry dataset and difficulty training at higher training resolutions due to GPU limitations.</li><li>It was more difficult than expected to create a good dataset. If anybody wants to donate images to help grow the dataset, please DM me</li></ul>

Files with SHA256: deca7176735079a9920b9f8a1b253a05ac815dfd20fca838585cfa9c6cb7ab7d