LTX-2 is an open-source AI video generation model developed by Lightricks. It is based on diffusion technology and can convert static images or text prompts into controllable high-fidelity video sequences. It supports synchronized audio and video generation, and is optimized for customization, speed, and creative flexibility, aiming to provide a convenient creation tool for studios, research teams, and independent developers. LTX-2 can efficiently run on consumer-grade GPUs, significantly reducing the cost of professional video production.