LTX-2.5 is an open-weight diffusion model for generating and transforming synchronized video and audio. It supports text, image, video, and audio inputs and can be used locally through compatible pipelines and ComfyUI workflows.
LTX is a Video generation project. It focuses on generating synchronized video and audio from text, images, and existing media. LTX is an open-source project aimed at AI developers, researchers, and creators building local generative media workflows. LTX is open source under the Open Source license. LTX is available on the web, the command line, and API, and it can be self-hosted.
It is developed by comfyicu, and it first shipped in 2026. The project is developed in the open on GitHub with 9.4k stars and 13 commits in the last 90 days. Key capabilities include 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