wd40

a Stable Diffusion model for (mechanic) weebs

Overview

wd40 is a Stable Diffusion model trained on a dataset of anime-style images. It is based off Stable Diffusion XL Base Kakigori v3, and is designed to generate high-quality images of anime-style characters. The model is capable of generating images with a variety of attributes, such as hair color, eye color, and clothing style. As long as they're that exact one same catgirl and she's holding a can of WD-40.

If you're a big fan of spray lubricants and workshops, this is the model for you.

Recipe

Hold right way up and shake before use. Turn the nozzle to be in line with the blue mark on the top of the can. Spray upright, at an angle, or even upside down.

In case you hadn't worked it out, no, this is not the real SDXL-based WD model, it's a meme joke april fools' model. XL is 40 in roman numerals, and WD-40 is, well, WD-40. So we got Bing to generate a bunch of catgirls holding cans of WD-40, and overtrained the shit out of some LoRa, and merged them into [Kakigori v3](https://huggingface.co/nubby/Kakigori) (thanks nubby!) It was trained with a uniform distribution of all WD Tagger tags, so it should basically generate the exact same thing regardless of how you prompt it. Is it good? Not really! but it sure is funny, and Derrian did an amazing job on the LoRAs.

Credits

A big thankyou to Derrian, nubby, ao, yoinked, and many others!

What?

This was our April Fool's Day joke for 2024 😉