Google Introduces An AI Filmmaking Platform For Veo 3

Flow is built to work specifically with Google DeepMind's most advanced models. That includes Veo for video, Imagen for images, and Gemini for language and orchestration.

Google made some of the biggest AI announcements yesterday during Google I/O 2025. They unveiled a brand-new image model called Imagen 4. They also released an upgraded video generator, Veo 3, an upgraded Gemini Pro model, and a bunch of other impressive updates.

But the one that ties all of these generative media tools together is something they’re calling Flow.

What is Flow?

Flow is the evolution of VideoFX, a Google Labs experiment that launched last year. It helps you create cinematic clips, seamlessly transition them into scenes, and have enough consistency to tell a story.

Flow is built to work specifically with Google DeepMind’s most advanced models. That includes Veo for video, Imagen for images, and Gemini for language and orchestration.

You can generate video clips inside Flow in three different ways:

• Text to Video: Generate using a text prompt

• Frames to Video: Upload or generate images to use as starting and/or ending frames

• Ingredients to Video: Upload or generate images to use as subject or style references