Home Projects FastVideo
FastVideo
Python

FastVideo

A unified inference and post-training framework for accelerated video generation.

by hao-ai-lab · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
diffusersdiffusion-modelsdistillationApache-2.0Python
View on GitHub
In plain words

Generate videos quickly using a framework that speeds up video creation and processing.

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 →
FastVideo — GitHub preview card
📈 Star history
3.85k3.80k
2026-07-072026-08-31
📈 Track FastVideo

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

A unified inference and post-training framework for accelerated video generation.

FastVideo has 3.8k stars on GitHub. It has been forked 383 times. FastVideo is written mainly in Python. It has been in active development since 2024. FastVideo is available under the Apache-2.0 license. Its main topics are diffusers, diffusion-models, distillation, inference.

Frequently asked questions

What is FastVideo?

A unified inference and post-training framework for accelerated video generation.

Is FastVideo open source?

FastVideo is an open-source project. It is released under the Apache-2.0 license.

Is FastVideo free?

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

What license does FastVideo use?

FastVideo is available under the Apache-2.0 license.

What language is FastVideo written in?

FastVideo is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — FastVideo

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

[![olud.ai](https://olud.ai/badge.php?tool=hao-ai-lab-fastvideo)](https://olud.ai/project/hao-ai-lab-fastvideo.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.