Google Launches Veo: The Brand New Video Generation Model

| Updated on May 21, 2024

Around three months ago OpenAI launched Sora, an AI model that can generate lifelike videos. Now, Google is trying to do the same with their latest video generation model named, Veo

Google announced the new tool at its I/O developer conference. Google says its latest generative AI video model can generate high-quality 1080p resolution videos over a minute in length. It can also offer a wide range of visual and cinematic styles. 

In the above example, you can see the type of videos Veo can generate through simple text prompts. Check out the official Veo webpage from Google where they shared many more such clips that are AI-generated. 

According to a Google Press Release, Veo has “an advanced understanding of natural language,” enabling it to understand concepts like time lapse or aerial shots of a landscape. 

To use it, users can simply use text, image, or video-based prompts and Veo will do the rest. Google says the generated videos are more consistent and coherent, depicting more realistic movement for people, animals, and objects in the clips. 

Google DeepMind CEO Demis Hassabis said in a press preview that these clips can be refined even further with additional prompts. He also says that Google is exploring additional features to enable Veo to produce storyboards and longer scenes. 

For now, Veo is not available to the general public. Google says it is inviting select filmmakers and creators to experiment with it. It will help them determine how it can best support creatives and will build on those collaborations. 

Meanwhile, OpenAI is pitching Sora to top Hollywood creators and planning it to release at the end of this year. Google also wants to do the same with Veo which is why they are giving previews to creators and Hollywood filmmakers. 

Himanshu Kumar

Tech and Software Writer