In what has become a familiar refrain over the past year and change, AI technology is pushing forward at breakneck speeds. There have been countless improvements to generative AI video technologies over the past few months, perhaps none as noteworthy as Google’s introduction of the company’s new Veo 3 generative AI video model.On top of the Veo 3 announcement (that is also paired with a new Imagen 4 image model and other tools), Google is also rolling out Flow, the company’s new AI filmmaking tool. Let’s take a look at these new technologies and explore what they’re set to offer in the creative film and video space.Introducing Google Veo 3As a follow-up to Veo 2, which was quite noteworthy at its release, Veo 3 promises to be even more state-of-the-art and provide some of the most sophisticated generative AI videos known to mankind. Compared to Veo 2, Veo 3 is set to add more photorealism as well as the ability to better generate text and replicate real-world physics.Veo 3 also gets a notable boost by adding audio generation for the first time, as well as the ability to add appropriate background noise and even dialogue for scenes with characters speaking with each other.Veo 3 is available today for Google Ultra subscribers through the Gemini app as well as with Flow, which we’ll explore more about below.Google’s Flow AI Filmmaking ToolThe biggest news here, along with Darren Aronofsky’s announcement of his own generative AI storytelling venture, ‘Primordial Soup’, which is set...
Published By: NoFilmSchool - Yesterday