Google Deepmind has unveiled its next-generation AI tools, Veo 2 and Imagen 3, along with a playful new experiment, Whisk, aimed at remixing visuals in creative ways. Veo 2 is the newest version of the company's flagship video-generation tool,

Google claims Veo 2 has a "better understanding of real-world physics"—an issue that often trips up such tools.

Google’s artificial intelligence (AI) research lab DeepMind has revealed a video-generating AI model, which aims to rival OpenAI’s Sora. Yesterday (16 December), DeepMind announced Veo 2, the successor to its Veo model, which powers a growing number of the tech giant’s products.