metadata

license: creativeml-openrail-m
thumbnail: ./images/wd40-icon.png
tags:
  - stable-diffusion
  - text-to-image
  - safetensors
  - diffusers
inference: true
language:
  - en
widget:
  - text: >-
      1girl, solo, bangs, (pink hair, gradient hair, very long hair:1.1),
      (purple eyes:1.05), (cat ears, animal ear fluff:1.2), sidelocks, white
      shirt, collared shirt, buttons,  night, looking at viewer, table, pizza on
      table, pov, restaurant, medium breasts, smiling, (blush:0.7), colored
      inner hair, (symmetric), (masterpiece, exceptional, extremely
      detailed:1.1)
    example_title: example
library_name: diffusers

wdXL

a Stable Diffusion model for (mechanic) weebs

Overview

wdXL is a Stable Diffusion model trained on a dataset of anime-style images. It is based off Stable Diffusion XL Base, 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.

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

Recipe

Secret, for now ;)

> 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!