Google is making videos created with its AI Flow video creator even more realistic and, at first glance, harder to identify as AI-generated. Business announced on Wednesday that users can add and change the shadows and lighting of their AI videos. The enhanced editing features in Flow are related to I see update 3.1also announced Wednesday, which Google says is better at creating videos from photos submitted as incentives.
Flow users will also be able to generate videos with audio using several fresh features in the tool. Users can create a video with audio based on three reference images, which the company calls “Video Ingredients.” Another feature called “Video Frames” allows you to create a video that combines the starting image with the ending image and accompanying audio. The “Scene Extension” feature allows you to select the last second of a clip and add an additional generated video up to a minute long, also with generated audio.
Veo 3.1 costs the same as Veo 3, is available to developers in a “paid preview” via the Gemini API, and is enabled in the Gemini app.
According to Google, Flow users will soon be able to remove “anything” from a video – the tool will restructure the background and scene to “look as if the object was never there.”