https://github.com/randomgamingdev/mcbuildsgen
An AI Minecraft build generator based on a hybrid diffusion and autoregression architecture and trained off of grabcraft builds
https://github.com/randomgamingdev/mcbuildsgen
Last synced: 3 months ago
JSON representation
An AI Minecraft build generator based on a hybrid diffusion and autoregression architecture and trained off of grabcraft builds
- Host: GitHub
- URL: https://github.com/randomgamingdev/mcbuildsgen
- Owner: RandomGamingDev
- Created: 2024-06-14T19:00:55.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-06T16:02:47.000Z (4 months ago)
- Last Synced: 2025-03-06T16:38:07.880Z (4 months ago)
- Language: Jupyter Notebook
- Size: 30.4 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🚧 Work-in-Progress 🚧
### This contains an older stable version of the core training script (the one originally used). However, do note that there are external scripts not included including the post-processor for the AI's generated result.
Some of the uploading didn't work due to technical issues, meaning that I wasn't able to upload everything so
### Check out some of my other projects in this short 2m video! https://www.youtube.com/watch?v=yTmrJB4P9w0
In order for the diffusion model to understand colors I'm currently using the average color of a block's texture, with the textures being sourced from this custom asset extractor:
https://github.com/RandomGamingDev/minecraft-asset-extractor