Google has developed the Imagen Video neural network, which creates a video based on a text description.

You've probably heard a lot about neural networks that can create images based on descriptions. American

Google not only decided to keep up with trends, but went further.

What is known

Google has announced a neural network that cancreate not photos, but entire videos according to a text description. The American company's system is called Imagen Video. It can create videos with a resolution of 1280 x 768 pixels. Although the duration can hardly be called long - up to 5 seconds.

Imagen Video mimics the styles of artists and cancreate three-dimensional shapes that retain their shape during rotation. To train the neural network, Google developers used several tens of millions of images, videos and text descriptions.

The results of the work are available on the website of the Imagen Video project. Google refuses to share the source code, citing a desire to prevent inappropriate content from appearing.