Google Brings Veo 2 Text-to-Video Generation to Gemini Application

Article by Jade Bryan from NextPit | Read the full article in English

Google is taking its AI video generation capabilities to the next level with the introduction of Veo 2, a new feature integrated into the Gemini AI platform. This innovative tool allows users to create short videos simply by typing in text descriptions. Unlike previous video generation technologies, Veo 2 promises more realistic and detailed video outputs, capturing nuanced movements and complex scenes with greater accuracy.

The new video generation feature is currently available to Gemini Advanced users who have a Google One AI Premium subscription. Users can create 8-second videos in 720p resolution, with the ability to specify different styles and film genres. The more detailed the text prompt, the more precise and tailored the generated video will become. Google has also implemented digital watermarks to help identify AI-generated content, adding a layer of transparency to the technology.

Interestingly, Google is not stopping at just video generation within Gemini. They are also expanding the technology to Whisk, an experimental image generation application. This means users can now animate images they create, further blurring the lines between static and moving visual content. While the current video length is limited to 8 seconds, the technology represents a significant step forward in AI-powered creative tools, making video creation more accessible to people without advanced editing skills.

Read More (translated)