<h1 id="heading-8">ABXL</h1><h3 id="heading-9">All Purpose ABDL LoRA</h3>I am building this for the entire community and need help building and improving the dataset. If you can help gather or caption images, please contact me. The more people we get involved, the better this will become. Share with your friends!Goals:<ul><li>Diaper Types: White, Printed, Pullups,...</li><li>Diaper Sizes: Small, Medium, Large, Huge,...</li><li>Any Art Style</li><li>Custom Diaper Designs</li><li>Alternative Models for Specific Use Cases</li></ul>Tips:Seems to work really well with Pandora's Box(see resources). I usually run Pandora's Box as the main model and use Better Than Words(see resources) as the refiner for extra detail. Double it with img2img and finally double it again with your favorite 4x upscaler.v0.1 info:<ul><li>~380 mostly autotaged image dataset</li><li>White Female Bias</li><li>Biases to specific poses: butt shots and legs spread specifically</li><li>No distinction between types or size</li><li>More difficult to work with than I would like</li></ul>

ABXL

Completely rebuilt dataset by hand. ~130 painstakingly hand captioned images. Using short phrase captions.

Files with SHA256: 18c1020098787e34059fcddbcbd9e026d4bd56d6561ba568eb423e35a5d174b8