Lightricks/LTX-2 — 7,712 Stars
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
Watch Episode
About This Repo#
Lightricks/LTX-2 — 7,712 ⭐
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model. - Lightricks/LTX-2
Narration#
AI just learned to generate video AND audio together. LTX-2 is the first open-source model creating fully synchronized audiovisual content from a single prompt. Ten pipelines: text-to-video, lip dubbing, HDR output, even retake specific moments. Twenty-two billion parameters, fully open, runs on your own GPU. The future of AI video is here. Link in bio.