Google’s Veo 3.1 is best at producing movies from photos

Google has released a brand new replace to its Veo AI video technology mannequin that ought to make it do a greater job of sticking to prompts and changing photos into movies. Veo 3.1 is out there to attempt in the present day by means of Google’s Gemini API and is now additionally powering the corporate’s Flow video editor.

Veo 3.1 builds on the brand new capabilities Google launched with launch of Veo 3 at Google I/O 2025. The brand new mannequin affords higher “immediate adherence,” in keeping with Google, and will have a better time creating movies based mostly on the picture “elements” you add alongside your written immediate. Veo 3.1 additionally makes it attainable to transform photos to video and generate audio on the identical time, a functionality that wasn’t out there with Veo 3.

In Move, Veo 3.1 helps at the least a brand new characteristic that provides you finer management over the movies you generate. With what Google calls “Body to Video,” Move permits you to add a primary and final body, after which generates the video in-between. Adobe Firefly, which is powered by Veo 3, affords a similar feature, however Move will be capable of pull it off and create audio on the identical time. These added audio expertise will even apply to the video editor’s capacity to increase clips and insert objects into current footage, too.

Primarily based on the samples Google’s shared, movies generated with Veo 3.1 nonetheless have an uncanny high quality that appears to fluctuate vastly relying on the immediate and topic. Even when it is lacking a few of the realism of OpenAI’s Sora 2, although, the corporate’s choice to attempt to make Veo extra helpful to individuals who truly work with video reasonably than a supply of social media spam is a welcome transfer.