Google has improved its AI filmmaking tool, Flow, making AI-generated videos more realistic and less distinguishable from real footage. The recent update, Veo 3.1, introduces enhanced editing capabilities such as adjusting shadows and lighting within AI videos. Flow also now supports audio generation with three new features: ‘Ingredients to Video,’ which creates videos with audio from three reference images; ‘Frames to Video,’ which generates a video with audio transitioning between a start and end image; and ‘Scene Extension,’ which extends the final second of a clip up to a minute with additional generated video and audio.
Veo 3.1 is available as a paid preview via the Gemini API for developers and is enabled in the Gemini app, costing the same as Veo 3. Additionally, Flow users will soon be able to remove objects from videos seamlessly, with the background and scene automatically restructured to appear as if the object was never present.
