Google DeepMind has unveiled Veo 2, its latest artificial intelligence model for video generation. This new tool is presented as a significantly improved version of its predecessor, Veo, capable of creating videos longer than two minutes in 4K resolution. In comparison, its competitor Sora from OpenAI is limited to 20-second clips in 1080p.
However, these capabilities remain theoretical for now. The VideoFX tool, where Veo 2 is currently being tested, restricts the creation to 8-second videos in 720p. Google promises that access to this tool will expand in the coming days and that Veo 2 will also be integrated into other products like its Vertex AI platform as the technology becomes ready for widespread use.
Despite impressive figures, Veo 2 stands out for its technical capabilities. DeepMind claims that the model better understands the principles of physics, camera movements, and light properties, resulting in sharper textures and more realistic handling of shadows and reflections.
