Today, we’re announcing a major breakthrough in our latest generative media model. These models create breathtaking images, videos, and music, allowing artists to realize their creative visions. It also provides great tools for everyone to express themselves.
Our latest video and image generation models, Veo 3 and Imagen 4, push the frontiers of media generation with groundbreaking new features. It also expands access to Lyria 2, giving musicians more tools to create music. Finally, we invite visual storytellers to try out Flow, our new AI filmmaking tool. Using Google DeepMind’s most advanced models, Flow gives you more control over characters, scenes, and style to bring your stories to life with cinematic weave.
We’ve been working closely with the creative industry, including filmmakers, musicians, artists, and YouTube creators, to help bring these models and products to life responsibly, giving creators new tools to realize the potential of AI in the arts.
