Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Google DeepMind Unveils a New Video Model To Rival Sora - Slashdot

Dec 17, 2024 - slashdot.org
Google DeepMind has introduced Veo 2, a next-generation AI tool designed to generate video clips that can exceed two minutes in length and reach resolutions of up to 4K. Currently, Veo 2 is exclusively available in Google's experimental video creation tool, VideoFX, where videos are limited to 720p resolution and eight seconds in duration. This contrasts with OpenAI's Sora, which can produce clips up to 1080p and 20 seconds long. Access to VideoFX is currently restricted by a waitlist, but Google plans to expand user access soon.

Eli Collins, VP of product at DeepMind, mentioned that Veo 2 will eventually be available through Google's Vertex AI developer platform as it becomes ready for broader use. Google intends to refine Veo 2 based on user feedback and aims to integrate its capabilities across various applications within the Google ecosystem. Further updates on Veo 2's development and integration are expected to be shared next year.

Key takeaways:

  • Google DeepMind has announced a new video-generating AI tool called Veo 2, designed to compete with OpenAI's Sora.
  • Veo 2 can generate video clips longer than two minutes with resolutions up to 4K, but is currently limited to 720p and eight-second clips in Google's VideoFX tool.
  • VideoFX, where Veo 2 is available, is behind a waitlist, but Google plans to expand access soon.
  • Google intends to make Veo 2 available via its Vertex AI developer platform as it becomes ready for large-scale use, with further updates expected next year.
View Full Article

Comments (0)

Be the first to comment!