This is wild. Lightricks just open-sourced LTX-2, the first truly open audio-video generation model, complete with open weights and full training code. Even better: it’s optimized for NVIDIA RTX GPUs, making high-quality local video generation finally practical on consumer and workstation hardware. Here’s everything you need to know 👇

1. Open Source LTX-2 is a complete open-source release for audio-video generation, featuring open weights, full training code, benchmarks, and customization tools. No hosted API is required to use, modify, or extend the model.

2. Runs Locally (not cloud only) LTX-2 is designed to run on-device, enabling private workflows, fast iteration, and full control. Distilled and quantized variants reduce memory and compute requirements.

3. 20 sec Clip Extend creative range with long-form generation. Produce up to 20 seconds of high-fidelity video with complete control and consistent style.

4. 50 FPS Performance Optimized for speed without sacrificing quality. Generate synchronized 4K video and audio in seconds with the fastest production-grade AI model available today.

5. Native 4K 50 FPS Generate cinematic-grade video with synchronized audio at true 4K / 50 fps. Built for professional workflows, ready for studio, developer, or enterprise production.

6. Audio & Video Create synchronized visuals and sound in one coherent process: motion, dialogue, ambience, and music, generated together with natural timing