Meta unveils a tool to create videos from phrases
With Make-A-Video it is possible to get short video clips using an English phrase.
After DALL-E, a software from the firm OpenAi allowing to generate images from a few words, Meta in turn unveils Make-A-Video, which offers the same functionality, but for video content.
< p class="e-p">With this tool, it is possible to write a sentence, like a cat watching television with a controller in hand, in order to obtain a short video sequence generated by the algorithms of the algorithm. technology company. This system is also able to create a video from an image.
Start of the widget. Skip widget? End of widget . Back to the beginning of the widget?
To pull off this little magic trick, Meta used artificial intelligence and machine learning, feeding its software an astronomical number of images associated with text descriptive. This one was also exposed to a large amount of videos, so that he could learn the concept of movement, according to what the company explained in a press release.
For the tech giant, it's the logical sequel to Make-A-Scene, a tool it unveiled this summer that lets you create images from text.
It is much more difficult to generate a video than a photo, because in addition to correctly generating each pixel, the system must also predict how it will evolve over time, the boss of Meta wrote on Thursday , Mark Zuckerberg, on Facebook.
Internet users who wish to try Make-A-Video should apply to Meta. The company has not specified how many people have access to it at this time.