Google Flow gains finer AI video control with Gemini Omni 1.1 Flash

With the new model, Flow's scene extension can analyze up to 10 seconds of an existing video instead of only the final second before continuing a clip. Google says this gives the system more context to maintain visual consistency and narrative continuity. Extensions can be generated in 10-second increments, up to 40 seconds cumulatively.

Creators can now draft videos in 360p more quickly and with fewer credits before committing to higher-quality renders. The update also adds 1080p and 4K output, while video references can help maintain visual context and character consistency.

Google Flow originally began as a filmmaking playground built around Veo, with controls for camera movement and a way to extend existing shots. Google later expanded it into a broader AI creative studio, bringing image generation and editing into the same workspace. Gemini Omni then allowed users to combine text, images, audio, and video to create and edit footage, and the latest Flash model pushes that experience further.