Google introduces Veo 2, a cutting-edge video generation model creating realistic clips from text or images. 🎥 Alongside, Imagen 3, an enhanced text-to-image model, is now live on ImageFX, offering stunning visuals with improved quality
Veo 2 is able to:
▪️ Create videos at resolutions up to 4k
▪️ Understand camera controls in prompts, such as wide shot, POV and drone shots
▪️ Better recreate real-world physics and realistic human expression
In head-to-head comparisons of outputs by human raters, it was preferred over other top video generation models. → https://goo.gle/veo-2
google, your crushing openai, but please announce + release. People forget and are starting to hate this previews and wait lists. Regardless, it's way better than sora.
I wonder when this level reaches games. Imagine playing a game with this kind of optics. Maybe with RTX 9090 in 2030 😸
Veo 2 is well-versed in the language of filmmaking. Users can request specific styles, define shots, and suggest cinematic effects, and Veo 2 will deliver with extended video lengths of up to several minutes in stunning 4K resolution.
marvelous!everyone be an AI Director！
google, your crushing openai, but please announce + release. People forget and are starting to hate this previews and wait lists. Regardless, it's way better than sora.
