With a simple command, Google’s latest AI technology enables users to generate videos from text.
Google is making big moves in the AI arena, the latest being the ability to create videos with simple commands. The new AI model for this feature is called Lumiere, which uses a diffusion model called Space-Time-U-Net that looks at the intricate details of the video and makes the changes.
Google’s AI model can actually create a few-second clip with prompts similar to other AI models that have come across in recent months.
An interesting element that sets Lumiere apart from other platforms is that you can create and edit content as well. The magic of Google’s AI technology is that the content feels like real life where you can feel the object moving in the water just like in reality. Google’s biggest game changer is STUNet, which focuses on timing-based movement.
Lumiere is far from reaching the public, as tests are still being done internally to ensure that the AI does not spoil the promising product. In Google’s case, what also helps with the AI template is that you can also use it to create from image to video, where you can animate some of the content or give it a stylized touch. Basically, the world is your canvas, in this case thanks to Lumiere.
The main reason Google isn’t bringing Lumiere to everyone is because the company is concerned about its misuse to produce fake content, which has become a global problem, as Microsoft’s Satya Nadella and others have highlighted. Google is aware of its responsibility to preserve the sanctity of the content produced by these AI models, but only time will tell how it plans to combat the threat of fake content on the Internet.
