LTX-2.3 is an open-source multimodal AI model that enables text-to-video, audio-to-video, and other video generation tasks. It supports local inference and is designed for researchers and developers working on generative AI.
LTX sits in PulseGate's Text to video category. It focuses on generating videos from text, audio, or multimodal inputs using open-source AI models locally. It is built as an open-source project for AI researchers and developers. LTX is open source under the Open Source license. It ships for the command line, and it can be self-hosted.
It is developed by Lightricks, and it first shipped in 2026. The project is developed in the open on GitHub with 8k stars and 14 commits in the last 90 days. Among its 5 catalogued features are text-to-Video, audio-to-Video, and Multimodal Input.
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