Artificial intelligence (AI) is a hot topic globally, with Google leading this technological race.
In its latest innovation, Google has introduced a new Large Language Model (LLM) named ‘Video Poet’, designed to convert text into videos.
This AI-powered tool, ‘Video Poet’, can generate videos based on the input text provided by the user. Additionally, it allows users to incorporate their preferred audio clips, adding a personalised touch to the videos.
This breakthrough offers users an easy and convenient way to create custom videos.
With the release of Video Poet, Google has added a statement in a blog, “A recent wave of video generation models has burst onto the scene, in many cases showcasing stunning picturesque quality. One of the current bottlenecks in video generation is in the ability to produce coherent large motions. In many cases, even the current leading models either generate small motion or, when producing larger motions, exhibit noticeable artifacts.”
To showcase the capabilities of Video Poet, Google has released a demonstration video.
Google describes Video Poet as a straightforward modelling approach capable of producing high-quality videos using LLM.
The process begins with the Video Poet creating individual video clips for each piece of text. These clips are then combined to form a cohesive video.
This innovative tool is set to revolutionise how we create and consume video content.