Home Projects pixelgpt-24x24
pixelgpt-24x24
JavaScript

pixelgpt-24x24

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

by unstonio · GitHub
Stars
Forks
Created
Last commit
Language
Likely
Self-hostable
autoregressive-modelfastapigenerative-aiJavaScriptSelf-hostable
View on GitHub
In plain words

Type a prompt to generate a 24x24 pixel art sprite locally, using a limited color palette.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
pixelgpt-24x24 — GitHub preview card
📈 Star history
8544
2026-08-022026-08-31
📈 Track pixelgpt-24x24

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

pixelgpt-24x24 has 85 stars on GitHub. It has been forked 8 times. pixelgpt-24x24 is written mainly in JavaScript. It has been in active development since 2026. Its main topics are autoregressive-model, fastapi, generative-ai, local-ai.

Frequently asked questions

What is pixelgpt-24x24?

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

Is pixelgpt-24x24 open source?

pixelgpt-24x24 is an open-source project.

Is pixelgpt-24x24 free?

Yes. pixelgpt-24x24 is free and open source — you can use, modify and self-host it.

What language is pixelgpt-24x24 written in?

pixelgpt-24x24 is written mainly in JavaScript.

🏅 Maintainer of this project?
olud.ai badge — pixelgpt-24x24

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=unstonio-pixelgpt-24x24)](https://olud.ai/project/unstonio-pixelgpt-24x24.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.