Google Flow initially launched as a filmmaking playground built around Veo. Early versions of the tool provided creators with basic controls for camera movement and the ability to extend existing shots. Over time, Google evolved Flow into a broader AI creative studio. This transition integrated image generation and editing directly into the workspace.

The platform took another leap forward with the introduction of the Gemini Omni video model. This allowed users to combine text, images, audio, and video to create and edit footage. Now, Google is giving the video creation experience another significant upgrade with Gemini Omni 1.1 Flash.

The new model introduces several controls designed to make AI-generated video easier to shape into a finished production. Gemini Omni 1.1 Flash gives Google Flow more precise control over AI-generated videos, including first- and last-frame interpolation.

Scene Extension and Keyframe Interpolation

For Flow users, scene extension can now continue an existing clip seamlessly. Google says Omni 1.1 can now analyze up to 10 seconds of an existing video when extending a scene. This is a major shift from earlier versions, which relied on just the final second of footage. This broader analysis provides the model with more context to maintain visual consistency and narrative continuity as the footage progresses.

These scene extensions can be generated in 10-second increments. By chaining these increments together, video sequences can reach up to 40 seconds cumulatively.

Creators can also specify the exact first and last frames of a shot. After setting these points, Omni 1.1 will generate the video directly between those keyframes. This keyframe interpolation gives creators much more control over camera movements, transitions, and clip looping, rather than leaving the entire sequence up to the model.

Additionally, creators working from existing footage have a new tool to ensure stability. You can also give Omni 1.1 up to three seconds of a separate video as a reference when creating a scene. These video references help the model maintain accurate visual context and character consistency based on the provided reference footage.

Workflow Efficiency: From Drafts to 4K Output

Google is also making experimentation cheaper and faster. Creators can now draft videos in 360p faster and with fewer credits before moving to higher-quality renders.

These 360p drafts generate up to 60% faster than previous outputs. They are also available at one-third the cost of standard 720p generation. This streamlined workflow makes it easier to test ideas before committing resources to a higher-resolution render.

Once a concept is ready for final production, the platform can deliver a high-quality finish. Omni 1.1 has been updated to produce polished 1080p or 4K output.

Global Availability and Developer Access

The Gemini Omni 1.1 Flash update is available globally in Flow. It is accessible for Google AI Plus, Pro, and Ultra subscribers. Furthermore, the new scene extension capabilities are available to those same subscribers directly in the Gemini app.

Developers have their own pathways to integrate these features. Developers can access Omni 1.1 through Google AI Studio and the Gemini Enterprise Agent Platform. This expanded access brings the exact same controls to standalone apps and broader creative workflows.