Google Gemini gets Veo 2 integration: How to generate videos on mobile app

Google is expanding the abilities of Gemini AI with the addition of its advanced video generation model, Veo 2. The feature, being introduced globally to Gemini Advanced subscribers, enables users to generate short video clips from text prompts, directly within the Gemini interface on mobile and web.

 

Veo 2 in Gemini

 

Veo 2, first introduced in December 2023, is Google’s next-generation video model designed to generate high-quality visuals with better realism. The company said that it has a better understanding of physics, human movement, and expressions, and supports commands for various genres, cinematic styles, and lens effects.

 

With the latest update, Gemini Advanced subscribers can now access Veo 2 via the Gemini app or on the web. To create a video, users simply need to describe a scene with a text prompt — whether it’s a short story, a stylised shot, or a fantasy setting. Prompts can include instructions for specific visual styles, like realistic or animated fantasy. 

  Using the Veo 2 model, Gemini can generate an eight-second video clip at 720p resolution, delivered as an MP4 file in a 16:9 landscape format. Google also said that there is a monthly limit on how many videos a user can create, and the company will notify them as they approach that limit.

 

How to generate videos in Gemini

• Ensure you have an active Gemini Advanced subscription.
• Open the Gemini app on mobile or visit Gemini on the web.
• From the model drop-down menu, select “Veo 2.”
• Enter a text prompt describing the video you'd like to create.
• Once the video is created, you can give further instructions to improve or edit it.

ALSO READ | Nova Reel AI by Amazon now generates 2-min videos using text, image inputs 

Whisk Animate

 

Alongside the Gemini update, Google has also introduced a new “Whisk Animate” feature to its Google Labs experiment platform. Powered by Veo 2, the tool allows users to animate images into eight-second video clips.

 

This feature builds on the existing Whisk tool, which previously allowed image generation using text and image prompts. Whisk Animate is now live for Google One AI Premium subscribers.