Introducing Our Latest Generative Media Models

We are excited to announce the launch of our latest generative media models, which represent a significant leap forward. These innovative models enable the creation of stunning images, videos, and music, giving artists the power to turn their creative vision into reality. Additionally, they drive remarkable tools that allow everyone to express themselves in new and exciting ways.

Our newest models, Veo 3 and Imagen 4, are pushing the boundaries of video and image generation with their cutting-edge capabilities. We are also expanding access to Lyria 2, providing musicians with more tools to create music. Furthermore, we are inviting visual storytellers to experience Flow, our new AI filmmaking tool. Powered by Google DeepMind’s most advanced models, Flow allows you to craft cinematic films with greater control over characters, scenes, and styles, bringing your story to life.

We have collaborated closely with the creative industries — including filmmakers, musicians, artists, and YouTube creators — to help shape these models and products in a responsible manner. Our goal is to provide creators with new tools to unlock the full potential of AI in their art.