LTX-2.5 is an open-weight multimodal generative model from Lightricks for creating and transforming video and audio from text, images, and other media. It is intended for developers and creators running inference through local libraries, notebooks, or compatible applications.
LTX is a Video generation project. It focuses on generating and transforming synchronized video and audio from text, images, and existing media without relying on a closed hosted service. It is built as an open-source project for AI developers and generative media creators. The project is open source (Open Source). LTX is available on the web and the command line, and it can be self-hosted.
Lightricks builds and maintains LTX, and it first shipped in 2026. The project is developed in the open on GitHub with 9.1k stars and 16 commits in the last 90 days. Among its 7 catalogued features are text-to-video, image-to-video, and video-to-video.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do