YN35/minisora

A minimal & Scalable PyTorch re-implementation of the OpenAI Sora training

24
/ 100
Experimental

This project offers a clear and scalable way for AI researchers and machine learning engineers to train sophisticated video generation models. It takes large datasets of videos and uses them to train a model that can then create new, short video clips or extend existing ones. This is designed for those exploring advanced video synthesis techniques and seeking to reproduce or build upon state-of-the-art methods.

Use this if you are an AI researcher or machine learning engineer looking to train your own large-scale video generation models with high efficiency and a straightforward codebase.

Not ideal if you are looking for an off-the-shelf application to generate videos without engaging in model training or understanding the underlying architecture.

video-synthesis AI-research machine-learning-engineering generative-AI deep-learning-training
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

MIT

Last pushed

Dec 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YN35/minisora"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.