LTX-2

by Lightricks · AI

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

New0 ratings9,366 starsActive
AIDeveloper ToolPythonCuda
Open project ↗↓ Download v1.3.0GitHub⚑ Report
LTX-2 preview

About this project

LTX-2 LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs, API access, and open access. 🚀 Quick Start Clone the repo Install the dependencies. The natten extra is the fastest backend for the diffusion video VAE below, and is Linux + CUDA only -- on Windows and macOS it is skipped automatically and decoding falls back to a Triton or eager implementation, so the same command works everywhere (see neighborhood attention backends) Download the models or use the Hugging Face CLI That…

Technologies

PythonC++CCudagenerative-ailtxltx-2

Project health

Actively maintained
Last updatelast week
Contributors4
Latest releasev1.3.0
Open issues & PRs38
LicenseOther
On GitHubsince 2026

GitHub

9,366
stars
1,483
forks
4
contributors
38
open issues & PRs
Python
language
last week
last commit
View on GitHub ↗All releases ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review LTX-2.

Built by

Lightricks
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain Lightricks/LTX-2? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like