---
license: openrail
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- minecraft
---
## Overview

This Stable Diffusion model was fine-tuned to generate a pre-version 1.8 Minecraft character skins, based on a text prompt.

The model was fine-tuned on the dataset for 13,000 steps using the 'train_text_to_image.py' script provided with the diffusers library.  A checkpoint has been included in the 'checkpoint' directory.

Some postprocessing is required to import and use the generated skins in Minecraft.

Example code to generate usable in-game Minecraft skins can be found in the [Monadical-SAS/minecraft_skin_generator](https://github.com/Monadical-SAS/minecraft_skin_generator) GitHub respository.

## Examples

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

* "Albert Einstein"
![Albert Einstein](examples/einstein.png)

* "Mahatma Ghandi"
![Mahatma Ghandi](examples/ghandi.png)

* "A man in a purple suit wearing a top hat."
![A man in a purple suit wearing a top hat.](examples/purplesuit.png)

## Contact Information

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

[![Monadical](logo.png)](https://monadical.com/)