I Didn’t Know AI Could Do THIS

Google's Gemini Omni model can generate video from visual inputs like maps and sketches. Demonstrated use cases include creating a first-person taxi cab driving video from a Google Maps screenshot with a drawn route, and generating drone POV footage from a hand-sketched camera path. The generated videos accurately follow the specified paths, including flying under bridges and past specific buildings. This opens up practical applications for filmmakers needing establishing shots without physical drone equipment.