Google has launched its AI video generation model, Gemini Omni 1.2 Flash, which natively supports generating videos up to 15 seconds long and introduces a new multi-turn conversational editing feature. Compared with the previous generation, the maximum video duration has been extended from 10 seconds to 15 seconds—a 50% increase. Users can set the generation duration between 3 and 15 seconds in 1-second increments. According to Google, the new model has improved its ability to follow reference content and can better maintain consistency of characters, objects, props, scenes, and environments across multiple shots, reducing visual drift or morphological changes during motion and shot transitions. This capability also applies to interpolation between the first and last keyframes, as well as to extending videos based on existing clips.