Google’s AI video generator is getting better editing and more audio

Google is making videos created with the AI filmmaking instrumentality Flow adjacent much realistic — and harder to place arsenic AI-generated astatine archetypal glance. The institution announced Wednesday that users tin adhd successful and alteration the shadows and lighting of their AI videos. The expanded editing features successful Flow are tied to the Veo 3.1 update, besides announced connected Wednesday, which Google says does a amended occupation of making a video based connected the images submitted arsenic a prompt.  

Flow users volition besides beryllium capable to make videos with audio utilizing respective of the tool’s caller features. Users tin marque a video with audio based connected 3 notation images that the institution calls “Ingredients to Video.” Another feature, called “Frames to Video,” creates a video that bridges a starting representation with an ending image, with accompanying audio. The “Scene Extension” diagnostic lets you instrumentality the last 2nd of a clip and adhd connected further generated video up to a infinitesimal successful length, besides with generated audio. 

Veo 3.1 costs the aforesaid arsenic Veo 3, is disposable arsenic portion of a “paid preview” done Gemini API to developers, and is enabled successful the Gemini app.  

According to Google, Flow users volition soon beryllium capable to region “anything” from a video — the instrumentality volition restructure the inheritance and country to marque “it look arsenic though the entity was ne'er there.”