Google DeepMind’s Veo enters the generative video fray

Google’s DeepMind division describes Veo as “our most capable video generation model to date”. It generates high-quality, 1080p resolution videos “that can go beyond a minute, in a wide range of cinematic and visual styles”.

“It accurately captures the nuance and tone of a prompt, and provides an unprecedented level of creative control — understanding prompts for all kinds of cinematic effects, like time lapses or aerial shots of a landscape.

Our video generation model will help create tools that make video production accessible to everyone. Whether you’re a seasoned filmmaker, aspiring creator, or educator looking to share knowledge, Veo unlocks new possibilities for storytelling, education and more.

From the Vet web page
The prompt that was used for the video shown above

A fast-tracking shot through a bustling dystopian sprawl with bright neon signs, flying cars and mist, night, lens flare, volumetric lighting.

A fast-tracking shot through a futuristic, dystopian sprawl with bright neons signs, starships in the sky, night, volumetric lighting.

A neon hologram of a car driving at op speed, speed of light, cinematic, incredible details, volumetric lighting.

The cars leave the tunnel, back into the real world city Hong Kong.

The Veo workflow

According to the Veo web page, where you will find out more about its current capabilities and see examples of video and the prompts used to generate them, “certain creators” are going to be able to experience Leo through VideoFX, a new experimental tool at YouTube Shorts will also be used to provide updates.

Anybody who is interested in learning more and giving it a try can join the waiting list now.