Overview

This Stable Diffusion model was fine-tuned on the Minecraft Character Dataset to generate a Minecraft-style characters, based on a text prompt.

The model was fine-tuned on the dataset for 15,000 steps using the 'train_text_to_image.py' script provided with the diffusers library.

I've written up the training process in more detail on the Monadical blog.

Examples

Here are some example text prompts and the images they generate:

• "Albert Einstein"

• "Mahatma Ghandi"

• "A man in a purple suit wearing a top hat."

Contact Information

You can contact me at: Cory Spencer <cory@monadical.com>