Google has announced that users can now use text-based prompts and images to create videos using Gemini Advanced and Whisk Animate. These features will use its recently launched AI video model, Veo 2.
In its latest update, Gemini Advanced can now be used to convert text-based prompts into eight-second long videos in 720p resolution. This will be delivered in an MP4 file in 16:9 landscape format. According to Google, there is a monthly limit, which Neowin claims could have been placed to avoid overuse, similar to ChatGPT’s image generation feature. The image counterpart of the feature is Whisk Animate, using Veo 2, which will also be eight seconds long.
Generated videos can be shared to platforms such as Youtube Shorts and TikTok. In an effort to ensure safety, all videos generated with Veo 2 will have a SynthID embedded in each frame, which is a digital watermark to indicate that it is AI-generated.
The company states that the feature will be rolled out globally to Gemini Advanced users on both web and mobile. This, along with Whisk Animate, is accessible under the Google One AI Premium subscription. The video generation ability was launched today, and will continue to roll out in the upcoming weeks.
(Sources: Google Blog, Neowin)
Manisha Dharmendra contributed to this article.
