Sign In

Joan Cornellà Art Style

1.1k

Updated: Nov 21, 2025

style

Download

1 variant available

SafeTensor

217.87 MB

Verified:

Type

LoRA

Stats

102

172

88

Reviews

Published

Nov 21, 2025

Base Model

Illustrious

Hash

AutoV2
748AFCE3B5

Trigger Words

xjoanx

This is just as a joke, but it does have a certain charm to it, not to mention the original art have some funny captions. With the first version I released I didn't really know how to get it to work, now it's not a problem.

-finally got it right this time, even the eyes-

Trained on 194 images.

Artist's page: https://joancornella.net/en/

Recommended style tags:

digital drawing \(artwork\), minimalist, simplistic, flat colors, solid circle eyes
  • recommended to use characters at 0.6 str with this style

  • try to minimize expressions, makeup and eye color - eye color sometimes work with lower weights ex: (blue eyes:0.8)

I train everything on IL XL 0.1 so it's compatible with any IL model, but the problem with most checkpoint is that they are leaning towards anime too much and cause the chin and eyes to deform regardless how hard I train it. Legends say it should be allright with NoobAI aswell, I dunno', never tried that, it's an anime wasteland I was told...