On August 27, 2026, Google added three new features to its AI video tool, Flow: keyframe control for start and end frames, video exports in 1080p and 4K, and more affordable test renders in 360p. All three features are based on the new Gemini Omni 1.1 Flash model and are now available worldwide to paying Flow subscribers.
For those who aren’t yet familiar with Flow: The tool is Google’s AI creative studio for images and videos, which was unveiled at the I/O conference in May 2025 and brings together models like Veo, Nano Banana, and Gemini under a single interface. Anyone who has already worked with Flow knows how tedious it used to be to guide a clip precisely to a specific final shot. That’s exactly where the new update comes in.
An overview of the three new features
| Feature | What it does |
|---|---|
| Start and End Frame Control | You specify the start and end frames of a clip, and Flow generates the motion in between |
| 4K Video Export | Export in 1080p or 4K instead of the previously lower standard resolution |
| Affordable 360p Drafts | Render and test drafts in 360p, then finalize them in full resolution |
Start and End Frames: Finally, Predictable Transitions
Until now, Flow was rather short-sighted when extending clips: The model only looked at the last second of a video to decide how to proceed. This often resulted in minor breaks in motion, lighting, or camera angle whenever multiple scenes were strung together.
With Gemini Omni 1.1, Flow now analyzes up to ten seconds of existing footage before continuing its calculations. Users can also specify an exact start frame and end frame, according to Android Authority, in increments of ten seconds up to a total of 40 seconds at a time. In practice, this means: You design a scene that begins with a character at the door and ends inside the room, and Flow fills in the movement in between. Additionally, up to three seconds of separate video footage can be imported as a reference to ensure that characters and the environment remain consistent across multiple clips. For commercials, short films, or social media content featuring recurring characters, this is a significant improvement over the old one-second logic, where you could never be entirely sure if the character would still be wearing the same jacket in the next clip.
4K Export and Faster, Cheaper Drafts
The second feature concerns output quality. Finished clips can now be exported directly in 1080p or 4K, making Flow suitable for the first time for broadcast and professional social media workflows that require fixed resolution specifications.
The third feature is aimed at saving money: If you just want to test whether a prompt works at all, you can render a 360p preview. According to Google, these drafts are generated up to 60 percent faster and cost only about one-third of a regular 720p rendering. Only once the result is satisfactory is it upscaled to full resolution. This saves a noticeable amount of time and credits, especially for concepts that require multiple prompt variations.
The technology behind it: Gemini Omni 1.1 Flash
All three features run on Gemini Omni 1.1 Flash, a faster version of Google’s multimodal Omni model, which was first introduced in May 2026. Omni models process text, images, audio, and video within a single system, which, in the context of Flow, means the model can understand longer video segments simultaneously and maintain movement, lighting, and perspective more consistently across multiple frames than the previous version.
As with the Flow relaunch in March 2026, when Google integrated the image generators Whisk and ImageFX directly into the interface, the approach remains the same: multiple specialized AI models under a single user interface, rather than opening a separate tool for each step.
Availability and Pricing
The update is now live worldwide, both in Flow itself and in the Gemini app. Access is available to subscribers of the Google AI Plus, Pro, and Ultra tiers. Developers can also access the features via Google AI Studio and the Gemini Enterprise Agent Platform. As of now, users without a paid subscription remain limited to the basic features of Flow.google.
Anyone who wants to try out the new creative tools can find them directly at labs.google/fx/tools/flow.
Context: More Control, Less Randomness
At first glance, the three features seem unspectacular, but they address a common pain point with AI video tools in general: Anyone working with Sora, Veo, or similar generators today is familiar with the problem that each new prompt run turns out slightly different. Start and end frame control removes precisely this uncertainty from the process, because the beginning and end are fixed, and only the path in between is generated. Combined with more affordable test renders, this shifts Flow a step further away from being a gimmick and toward a tool that actually enables planned production.
It’s important to note the labeling requirement: Anyone publishing clips created with Flow should keep an eye on the current guidelines for labeling AI-generated content, especially for commercial use in Germany.
Conclusion
With the new Creative Controls, Google Flow closes one of the biggest gaps in traditional video editing workflows: predictable transitions instead of random generation, plus 4K export and more affordable preview renderings. Anyone who works with AI video professionally or just wants to give it a try should check out the update—it costs nothing extra besides an active Google AI subscription.
