Google Project Phenaki - Text to Video Frequencies (2 minutes)
But it gets even crazier! With the Phenaki project, entire sequences can be created with tracking shots.
And here too, the input is just (long) text. Similar to Imagen, the transitions are not very clean, but it still makes sense and the camera movements are impressive.
Source and more videos
On the corresponding project page you can find initial examples as well as the linked paper on the project: https://phenaki.video/index.html
The result
Google AI creates videos from texts 3
The text input
Lots of traffic in futuristic city. An alien spaceship kazakhstan number dataset arrives at the futuristic city. The camera gets inside the alien spaceship. The camera moves forward until showing an astronaut in the blue room. The astronaut is typing in the keyboard. The camera moves away from the astronaut. The astronaut leaves the keyboard and walks to the left. The astronaut leaves the keyboard and walks away. The camera moves beyond the astronaut and looks at the screen. The screen behind the astronaut displays fish swimming in the sea. Crash zoom into the blue fish. We follow the blue fish as it swims in the dark ocean. The camera points up to the sky through the water. The ocean and the coastline of a futuristic city. Crash zoom towards a futuristic skyscraper. The camera zooms into one of the many windows. We are in an office room with empty desks. A lion runs on top of the office desks. The camera zooms into the lion's face, inside the office. Zoom out to the lion wearing a dark suit in an office room. The lion wearing looks at the camera and smiles. The camera slowly zooms out to the skyscraper exterior. Timelapse of sunset in the modern city
Not yet accessible to the public
Unfortunately (or fortunately), both systems are still under lock and key and not accessible to the public.
Although the videos are not perfect, it certainly won't be long before you can no longer tell the difference between videos at first glance.
Generate texts, images and videos with AI
Meanwhile, tools and artificial intelligence are getting better and better and are helping not only to generate videos, but also texts and images. There are now several AI text generators and tools for generating AI images are also increasingly being published.