Google is pushing the boundaries of generative AI with the integration of its powerful Veo 2 video model into Gemini Advanced, the company’s flagship AI platform. The new feature, which is now rolling out globally to subscribers, allows users to effortlessly create short, high-quality video clips using only text prompts—right from their mobile device or web browser.
Veo 2 in Gemini: What’s new?
Veo 2, introduced in December 2023, is Google’s latest innovation in AI-driven video generation. Designed to produce visually rich and realistic content, the model boasts a sophisticated understanding of physics, facial expressions, human movement, and cinematic aesthetics.
Now embedded into the Gemini ecosystem, Veo 2 gives users the ability to generate 8-second video clips at 720p resolution, based on detailed text descriptions. These videos are delivered in MP4 format and a standard 16:9 landscape aspect ratio. The model is capable of interpreting nuanced commands, from fantasy and surreal settings to stylised, cinematic scenes.
Google has confirmed that users can specify genre types, visual tone, and even camera effects in their prompts, offering a wide degree of creative control. However, to manage computing demands, the company has introduced a monthly cap on the number of videos users can generate. A notification will be issued as users approach their usage limit.
How to generate videos using Gemini and Veo 2
To access this exciting new feature, users must have an active Gemini Advanced subscription. Once subscribed, here’s how you can start creating videos:
- Launch the Gemini app on your mobile device or visit Gemini on the web.
- From the model selection menu, choose “Veo 2.”
- In the prompt box, describe the scene or concept you want the video to portray.
- Gemini will process your request and generate a video clip based on your input.
- Once the video is created, you can refine it with additional instructions to enhance or adjust the content.
Whether you’re crafting a moody cinematic vignette or an animated sequence inspired by fantasy realms, Veo 2 interprets your words into compelling visual narratives.
A New era of AI-powered storytelling
This integration significantly strengthens Google’s position in the growing field of AI-generated multimedia content. With rival companies like OpenAI and Amazon entering the arena, tools like Veo 2 in Gemini aim to make high-quality video creation accessible to everyday users, not just professionals.
Importantly, Google has highlighted that Veo 2’s understanding of the physical world and character animation is more advanced than earlier models. This ensures a more fluid and natural output, particularly in scenes involving complex movements or emotional expressions.
More Read
Also new: Whisk animate on Google labs
Alongside the Gemini update, Google has also launched Whisk Animate, an experimental feature available via Google Labs. Building upon the original Whisk tool—which allowed users to generate still images from prompts—Whisk Animate now enables the transformation of those images into short eight-second video clips.
Powered by the same Veo 2 model, this feature is currently exclusive to Google One AI Premium subscribers. It offers a fun and imaginative way to animate static imagery into motion, opening up fresh avenues for creativity, especially in marketing, education, and digital storytelling.
In summary
With Veo 2 now integrated into Gemini Advanced, Google has opened the door to text-to-video generation in an intuitive, mobile-friendly package. While still limited in duration and resolution, the model’s rich feature set and realistic output make it a promising tool for creators, hobbyists, and storytellers alike. And with features like Whisk Animate also emerging, it’s clear that Google is betting big on AI-generated video content as the next frontier of digital expression.
