JAKARTA - Some time ago, Google introduced Veo, Google's newest and most advanced video creation model, as well as Imagen 3, the high-qualitytext-to-image model of the tech giant.

Veo is Google's new Artificial Intelligence (AI) tool that can create 1080p resolution videos with a duration of more than one minute. This model gives much greater creative control, and understands cinematic terms such as timelapse or aerial shots of a landscape.

Veo also makes consistent and coherent videos so that humans, animals, and objects can be seen moving realistically throughout the scene.

Currently, Veo is available for selected creators in private preview mode on VideoFX by joining the waiting list. Later, Google will also bring a number of Veo capabilities to YouTube Shorts and other products.

The company says that this text-text-to-image model can produce incredible level of detail, create photosrealistic and live images, compared to previous models.

Being Google's best model to date, Imagen 3 can now create custom birthday messages, title them in presentations, and so on. Imagen 3 will launch on VertexAI soon.

"The creative potential of generative AI is huge and we can't wait to see how people around the world come up with their ideas with our new models and tools," said Eli Collins, VP, Product Management and Douglas Eck, Senior Research Director.


The English, Chinese, Japanese, Arabic, and French versions are automatically generated by the AI. So there may still be inaccuracies in translating, please always see Indonesian as our main language. (system supported by DigitalSiber.id)