V2 version has larger dataset.

Main prompt: legbinder, opened legbinder, laces, buckles, belts, locks, zipper

Optional prompt:

• opened legbinder [when you can see legs inside it],

• latex legbinder [50/50 chance of switching material from leather to latex]

Locks may not be generated properly because the dataset contains only around 3–4 images with them.

Belts, laces and legbinder can be different color, see examples for prompt.

Negative (optionally): straitjacket, gag [never happened to me but be aware]

Do not forget to use Adetailer and Hires fix!

Parameters may vary. Experiment by yourself.

The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images.