We’re rolling out significant updates to Veo that give people even more creative control.
Veo 3.1, Google’s latest AI video generation model, introduces several advanced creative capabilities designed to enhance content creation:
-
Extended Video Duration: Unlike its predecessor, which was limited to 8-second clips, Veo 3.1 supports videos up to 60 seconds long, allowing for more complex storytelling. (developers.googleblog.com)
-
High-Definition Output: The model generates videos in native 1080p resolution, ensuring professional-quality visuals suitable for various applications. (developers.googleblog.com)
-
Multi-Scene Storytelling: Veo 3.1 enables the creation of videos with multiple scenes, maintaining character consistency across shots and facilitating seamless transitions. (developers.googleblog.com)
-
Cinematic Presets: Users can apply built-in cinematic and lighting presets, such as drone shots, slow or fast pans, and zooms, to streamline the storytelling process without extensive prompting. (developers.googleblog.com)
-
Enhanced Audio Integration: The model offers synchronized audio generation, including natural conversations and sound effects, aligning lip movements and background sounds with the visual content. (developers.googleblog.com)
- Improved Character Consistency: Veo 3.1 ensures that characters maintain consistent appearance and behavior across scenes, reducing visual inconsistencies. (developers.googleblog.com)
These advancements position Veo 3.1 as a powerful tool for creators seeking to produce high-quality, dynamic videos with greater ease and flexibility.
Veo 3.1: Google’s Enhanced AI Video Generation Model:
- Veo 3.1 is coming soon, and Google’s clearly aiming it right at Sora 2 with longer video support, Published on Friday, October 10
Discover DeepMind, a world-leading AI research lab by Google. Learn how it’s advancing science, healthcare, and technology through cutting-edge artificial intelligence breakthroughs..
