<ul><li>This is a DORA file. It may not be compatible with your inference software.</li><li>This DORA was trained directly on GurilaMash-v2. It is designed to work best with that model. It will likely not work well on other checkpoints.</li></ul><h1 id="undergarments-for-gurilamash-v2-x6elhdrjo">Undergarments for GurilaMash-v2</h1>Trained on nearly 500 high resolution images of women wearing a broad selection of lingerie and undergarments. This DORA is complex. Hit and miss. If you're looking for something specific, you may have to dig for it. It works best when you just let it rip and see what pops out. I'll include caption data to give some ideas on how to get the most out of it. The training material was primarily NSFW, but without nudity, however, the model it's trained on is heavily nsfw, this ain't you're dad's sears catalogue, it's more like victoria's secret on steroids. Using multiple variations of the trigger words is encouraged and creativity (withing the confines of tag-based prompting) is often rewarded.The design and motivation behind this DORA is to produce the highest quality photorealistic images possible with SDXL.score_7_up, photo \(medium\), photorealistic, realistic, panties,That will get you where you want to go.I'm happy to provide help in the comments, but don't complain about it's poor compatibility with other checkpoints. I've tested it on other models, it's somewhat usable on other models merged with BigAsp, but you won't achieve the quality it's capable of with the model I trained it on.

Undergarments SDXL for GurilaMash V2

444 images, 6 epochs, ~3k steps, adamw, linear

Files with SHA256: 70606f3ea1106b8934bdadafcbc4e1b189beaed85fecf267c6e54056238efddc