Google's new tool gives creators more control over AI videos
What's the story
Google has launched the latest version of its generative video tool, Gemini Omni 1.1. The update comes with a host of new features aimed at giving developers and creative professionals more control over AI-generated videos. These include tools for extending scenes, controlling transitions and camera movements, generating faster previews, and producing higher-resolution outputs.
Feature upgrades
Users can now extend existing videos
The Omni 1.1 update allows users to extend existing videos by generating new footage that seamlessly continues from where the original clip ends.
It can analyze up to 10 seconds of prior video context, improving visual consistency and narrative continuity.
The update also lets users specify starting and ending frames of a shot, with the model generating continuous video between two keyframes for smoother transitions.
Performance enhancements
Omni 1.1 generates previews up to 60% faster
Omni 1.1 can generate 360p previews up to 60% faster and at one-third the cost of standard 720p generation. This way, users can test and refine scenes before generating higher-quality versions.
The update also supports multimodal inputs, letting users provide additional references and details to guide video generation.
Now, Omni 1.1 can produce high-definition outputs (1080p and 4K) for professional production workflows as well.
Access details
Availability and pricing
Omni 1.1 is available to developers via Google AI Studio and the Gemini Enterprise Agent Platform. Documentation, a cookbook, and prompting guides are provided for integration.
The model is also accessible worldwide to Google AI Plus, Pro, and Ultra subscribers through Google Flow.
As for pricing, it charges $0.03 per second for 360p video generation with creative controls and $0.3 per second for 4K output in professional production workflows.