# LTX-2

- Date: 2025-10-23
- Type: model
- Credit: Lightricks
- URL: https://aifilmhistory.org/entry/ltx-2

Nine days after Veo 3.1, Lightricks shipped the first open model that generates picture and sound together in a single pass: 19B parameters split 14B video and 5B audio, native 4K on a consumer GPU with 12 GB of VRAM. Native audio had been the closed models' moat since Veo 3; LTX-2 was the first time you could have it on your own hardware.

The honest asterisk is that on launch day you couldn't. Lightricks announced it as open source with weights "later this fall" and shipped only a paid API; the weights actually landed on January 6, 2026, free for companies under $10M ARR. It became the highest-ranked open model by early 2026 and the base [LTX-2.5](https://aifilmhistory.org/entry/ltx-2-5/) was built on.

Links:
- Lightricks — LTX-2 announcement: https://www.prnewswire.com/news-releases/lightricks-releases-ltx-2-the-first-complete-open-source-ai-video-foundation-model-302593012.html
- LTX-2 open weights release: https://ltx.io/newsroom/ltx-2-is-now-open-source-full-model-weights-released
- LTX-2 on Hugging Face: https://huggingface.co/Lightricks/LTX-2
- LTX-2 paper (arXiv): https://arxiv.org/abs/2601.03233
- LTX-2 on GitHub: https://github.com/Lightricks/LTX-2

---
Source: https://aifilmhistory.org/entry/ltx-2
Era: 2025 · The Studio Era
Last updated: 2026-10-02