Ebiblue Style [PonyXL]

Ebiblue focuses on monochrome, manga-like images that feature girls with a "gesugao" expression. If that sounds good to you, then this LoRA is for you.

The LoRA is biased towards features typical for Ebiblue (gesugao, monochrome, spot color, etc.) but is not limited to them. It can even do fully colored images (to an extent)!

If you have read this far, you may also like my Gesugao LoRA. And if you like the LoRA, please leave a reaction, review and/or tip. Enjoy!

Usage

• No activation/trigger needed. Simply include the LoRA in the prompt.

• Recommended tags for typical ebiblue style (monochrome):
  monochrome, spot color, <color1> aura, <color2> eyes, glowing eyes, black background

• Recommended negative tags for colored: monochrome, greyscale

• Recommended tags for gesugao: evil grin, smug

• Recommended to use at strength 0.8 - 1.0

• Use Clip skip=1 or Clip skip=2 (other values may also work, use at own risk).

• Works best at 1024x1024. Struggles to get the style right at lower resolutions.

• VAE may be needed for colored images.

Example

See preview images (generated with pruned version).

Unpruned vs. Pruned vs. Lite

I offer three variations of the model, which only differ in the file size and quality. Pick the one that best suits your preferences. If you cannot decide, simply pick the "pruned" version. Note that the quality is relative, even the lite version usually produces images which closely resemble the intended art style.

• unpruned: The originally trained model. Largest file size, best quality. Pick if you want the best possible quality, at the cost of disk space.

• pruned: Downsized model. Almost same quality as the unpruned version, with noticably smaller file size.

• lite: Drastically downsized model. Smallest file size. Still has good quality, but noticeably worse than unpruned and pruned.

Notes

Since I basically already had most of the data needed for this LoRA from my gesugao LoRA, I decided to just make a dedicated ebiblue LoRA as well. I reverted to some older training settings for this one, since it did not work very well with my news ones. I guess the new ones are better for concepts while the old ones are better for styles.

Using training data

Feel free to contact me if you want access to the training data.The training data has been sourced from publicly available image boards.

Disclaimer

This LoRA is not affiliated with the artist it is based on. If you like the art style, please support the original artist:

• https://twitter.com/ebiblue

• https://www.pixiv.net/en/users/379606