"♪ In case you ain't heard, I'm the Devil!
I'm a real low-down, not on the level!"

These are the results of my first experiments with a Google Colab LoRA maker. Early versions were made with PixAI and later evolved into Google Colab, though the dataset mostly remained the same. Results will vary, but I managed to get some improvement over the iterations. Anime tags were used in the LoRA making process, I suggest anime-style and cartoon-style models, though semi-realistic ones seem to work okay as well.

Activator/trigger tag:

• the devil \(cuphead\)

Other tags to use in your prompts:

• red nose, demon, horns, claws, black fur, yellow sclera, red eyes, fewer digits, demon tail

Tags for use in the negative prompt:

• tongue out, missing horns, missing tail, extra horns, extra tail

This model is not for commercial use, generated images are not to be sold or presented fraudulently as anything other than AI generated material.