Google unveils Veo, a high-definition AI video generator that may rival Sora

Google Veo generated images

Google introduced Veo, an AI video generator, at Google I/O 2024, capable of creating HD videos from text prompts like OpenAI’s Sora. Veo can edit videos from written instructions and generate cinematic effects, but it’s not widely available yet. Google plans to integrate Veo’s features into YouTube Shorts and other products, emphasizing responsible content creation with watermarking and safety filters.

Google says that Veo builds upon the company’s previous video-generation models, including Generative Query Network (GQN), DVD-GAN, Imagen-VideoPhenaki, WALT, VideoPoet, and Lumiere. To enhance quality and efficiency, Veo’s training data includes more detailed video captions, and it utilizes compressed “latent” video representations. To improve Veo’s video-generation quality, Google included more detailed captions for the videos used to train Veo, allowing the AI to interpret prompts more accurately.

Veo also seems notable in that it supports filmmaking commands: “When given both an input video and editing command, like adding kayaks to an aerial shot of a coastline, Veo can apply this command to the initial video and create a new, edited video,” the company says.


Thanks for taking the time to read this post. If you’ve enjoyed the insights and stories, consider showing your support by subscribing to my weekly newsletter. It’s a great way to stay updated and dive deeper into my content. Alternatively, if you love audiobooks or want to try them, click here to start your free trial with Audible. Your support in any form means the world to me and helps keep this blog thriving. Looking forward to connecting with you more!