Google is rolling out a new feature for its paid Gemini AI assistant users, enabling them to transform still photos into short video clips. Subscribers to Google AI Ultra and Pro plans in select regions can access the feature via the web version of Gemini, with a rollout to the Gemini mobile app expected throughout the week.
How Google Gemini ’s photo-to-video feature works
The new functionality allows users to generate 8-second video clips with sound from a single photo, enhanced by any text description provided in the prompt. These videos will be produced as MP4 files at 720p resolution in a 16:9 landscape format, according to Bloomberg.
Google's photo-to-video capability is powered by Veo 3 , the company's latest video generation model, which was unveiled in May at its annual developer conference. Veo 3 has also been available through Flow, a standalone paid filmmaking tool.
Google states it has implemented "significant steps behind the scenes to make sure video generation is an appropriate experience." This includes prohibiting video creation from images of publicly identifiable figures like celebrities or political leaders, and banning outputs that promote dangerous activities or incite violence or bullying.
A Google spokesperson acknowledged that while there's no explicit instruction for the AI model to change a person's appearance, photo-to-video generation and face animation are still new technologies that might produce outputs not fully representative of the original image.
The spokesperson added that the model is currently better at animating everyday objects, drawings, paintings, and nature photos, and that improvements, including for face animation, are planned for future updates.
Google CEO Sundar Pichai says Gemini users have created over 40 million videos since MayGoogle CEO Sundar Pichai made the announcement in a post on X, saying, “Since I/O in May, you've created 40M+ videos with Veo 3!”
“Now our new photo to video feature in the @Geminiapp lets you create clips inspired by the world around you. Here’s how I imagine our resident dino Stan roams the Google campus when we’re not looking:) Ultra/Pro subscribers can try it now at http://gemini.google.com,” he added.
By integrating this feature into Gemini's chat interface, Google is better positioned to compete with rivals like OpenAI and Runway AI Inc., a startup specialising in AI-generated video. The company also faces strong global competition, with players like China's Alibaba Group Holding AI startup Manus, and Kuaishou Technology recently launching or updating their own video tools.
How Google Gemini ’s photo-to-video feature works
The new functionality allows users to generate 8-second video clips with sound from a single photo, enhanced by any text description provided in the prompt. These videos will be produced as MP4 files at 720p resolution in a 16:9 landscape format, according to Bloomberg.
Google's photo-to-video capability is powered by Veo 3 , the company's latest video generation model, which was unveiled in May at its annual developer conference. Veo 3 has also been available through Flow, a standalone paid filmmaking tool.
Google states it has implemented "significant steps behind the scenes to make sure video generation is an appropriate experience." This includes prohibiting video creation from images of publicly identifiable figures like celebrities or political leaders, and banning outputs that promote dangerous activities or incite violence or bullying.
A Google spokesperson acknowledged that while there's no explicit instruction for the AI model to change a person's appearance, photo-to-video generation and face animation are still new technologies that might produce outputs not fully representative of the original image.
The spokesperson added that the model is currently better at animating everyday objects, drawings, paintings, and nature photos, and that improvements, including for face animation, are planned for future updates.
Google CEO Sundar Pichai says Gemini users have created over 40 million videos since MayGoogle CEO Sundar Pichai made the announcement in a post on X, saying, “Since I/O in May, you've created 40M+ videos with Veo 3!”
“Now our new photo to video feature in the @Geminiapp lets you create clips inspired by the world around you. Here’s how I imagine our resident dino Stan roams the Google campus when we’re not looking:) Ultra/Pro subscribers can try it now at http://gemini.google.com,” he added.
By integrating this feature into Gemini's chat interface, Google is better positioned to compete with rivals like OpenAI and Runway AI Inc., a startup specialising in AI-generated video. The company also faces strong global competition, with players like China's Alibaba Group Holding AI startup Manus, and Kuaishou Technology recently launching or updating their own video tools.
You may also like
BBC's Charlie Stayt humiliates top Tory for trying to 'ridicule' Labour in brutal TV moment
GB News erupts into furious migrant row as boat set on fire: 'Are you serious?'
Calcutta HC seeks report from Union Home Ministry on charges of migrant workers from Bengal in Delhi being deported to Dhaka
Kapil Sharma Cafe Attacked: Promotion proved costly for comedian Kapil Sharma, is this the reason for the attack on Canada Cafe?
Maya Jama 'in talks' to host brand new show away from Love Island
