Here's how to use AI to create videos with Gemini
Recently, millions of people have been captivated by artificial intelligence through customized images in a variety of formats, like Studio Ghibli. Now, Google may be bringing this craze to the video medium.
The new Veo 2 model from Gemini, the AI platform of the American company, lets users send a text message and get a brief video in return.
Google surpasses its primary rival, OpenAI's ChatGPT, which at the moment is unable to produce video directly within the chatbot, with this new feature.
According to the company, Veo 2 "represents a major leap forward in video generation" and is intended to produce high-resolution, cinematic videos.
The company has cautioned that, like any generative AI tool, Gemini may produce content that some people may find offensive. Gemini's results are based on user input.
Today, Gemini Advanced subscribers worldwide will have access to the web and mobile versions of this video creation feature, which will be finished in the upcoming weeks. The feature is accessible in Arabic as well as all other languages that the Gemini app supports.
How to use Google's AI to make videos
Only users of Gemini Advanced, the premium edition of Google's AI platform, can create videos with Veo 2.
First, choose Veo 2 from the drop-down menu after logging into Gemini. This feature produces a 720p, 8-second video in 16:9 horizontal MP4 format.
You are limited in how many videos you can make in a given month, but you will be alerted when you are almost at that limit.
Similar to image generators, you must describe the scene you wish to create in order to create these videos; the more specific the prompt, the better the outcome.