← All projects
Images & video

LTX-2

An open AI model that generates video with matching sound from text or images.

Research-backedNew this week

What it does

LTX-2 is an AI model from Lightricks that creates video together with synchronised audio, from a text description or a starting image.

It offers different modes that trade speed for quality, and it can produce high-resolution results. The code and model files are published openly to download and run.

Running it means downloading large model files and using a powerful graphics card.

Who it's for

Developers and researchers who want to generate video with sound on their own powerful hardware.

Can I use it without coding?

Developers only. You download large model files and run it from the command line, with a strong graphics card. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Windows, Mac
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • No standard license listed. Check the GitHub page before using it for business.
  • More on staying safe

Where people are talking about it

  • LTX-2Research paper · Jan 2026