During its Google I/O 2025 developer event earlier this week, Google introduced Flow—an AI-driven video creation tool aimed at filmmakers. The platform is built on a combination of three advanced AI models: Veo for generating video content, Imagen for producing visuals, and Gemini for handling text input and prompt generation.
Flow, powered by the latest Veo 3 model, enables creators to craft cinematic scenes and short clips using straightforward text descriptions. According to Google, the tool delivers highly realistic visuals with strong adherence to prompts, offering film-quality results that excel in physics accuracy and visual storytelling.
“Flow is inspired by what it feels like when time slows down and creation is effortless, iterative and full of possibility. It’s custom-designed for Veo, Google’s state-of-the-art generative video model, with exceptional prompt adherence and stunning cinematic outputs that excel at physics and realism. Behind the scenes, Gemini models make prompting intuitive, so you can describe your vision in everyday language. You can bring your own assets to create characters, or use Flow to make your own ingredients with Imagen’s text-to-image capabilities,” the search engine ginat said in a statement.
Flow is equipped with a variety of features designed for both seasoned professionals and beginners:
Camera Controls: Gain precise command over your shots by adjusting camera movements, angles, and viewpoints.
SceneBuilder: Effortlessly modify and expand your existing footage—uncover more of a scene or smoothly transition into the next moment, all while maintaining fluid motion and character consistency.
Asset Management: Organize and handle all your media elements and text prompts with ease.
Google also unveiled Flow TV, a curated hub of video clips, channels, and content produced using Veo. This platform allows users to view the exact prompts and creative approaches behind each clip, offering an educational resource to discover and experiment with different storytelling techniques.
Flow builds on the foundation of VideoFX, an experimental project from Google Labs introduced last year. The upgraded tool is now accessible to users in the U.S. through Google’s AI Pro and AI Ultra subscription tiers.
The AI Pro plan includes essential Flow tools and supports up to 100 generations per month, while AI Ultra offers expanded generation limits and early access to Veo 3, featuring native audio capabilities that incorporate ambient sounds and character dialogue directly into the videos.