Gemini Omni 1.1 Flash release notes / what's new

Google DeepMind has introduced Gemini Omni 1.1 Flash, a suite of generative video capabilities and creative controls designed to make generative video production-ready for professional use. Available via the Gemini API in Google AI Studio, the update focuses on increasing controllability, iteration speed, and output quality for developers building media editing software and creative tools.

Enhanced Scene Extension for Narrative Consistency

Gemini Omni 1.1 Flash allows users to extend existing video footage seamlessly. The model can now analyze up to 10 seconds of prior context—a significant increase from previous models that only referenced the final second—to improve visual consistency and narrative adherence.

Videos can be extended in 10-second increments, reaching a total cumulative length of up to 40 seconds.

Precise Motion Control via Frame Interpolation

Omni 1.1 enables the specification of both starting and ending frames for a shot. The model generates continuous video between these two keyframes, which facilitates the creation of complex camera orbits, zoom transitions, and seamless looping clips without jump cuts.

Optimized Prototyping with 360p Drafting

To accelerate the iteration process, Omni 1.1 supports generating lightweight previews in 360p resolution. These drafts are generated up to 60% faster and cost one-third as much as the standard 720p resolution, making them suitable for rapid prototyping and storyboard iteration.

Professional Resolution and Upscaling

Omni 1.1 supports high-resolution outputs ready for professional production, with the ability to upscale video to 1080p or 4K resolution.

Multimodal Video Referencing

Developers can now include up to three seconds of video as part of the multimodal input. This allows the model to maintain character consistency and visual context by referencing specific movements or scenes from uploaded video files when generating new content.

Availability and Integration

Gemini Omni 1.1 Flash is available through several Google platforms:

  • Google AI Studio: Direct access for building and testing.
  • Gemini Enterprise Agent Platform: Deployment options for enterprise developers.
  • Google Flow: Available to Google AI Plus, Pro, and Ultra subscribers.
  • Gemini App: Scene extension capabilities are available to Google AI Plus, Pro, and Ultra subscribers globally.

Sources

Related

  • Dispatch
    Gemini Omni 1.1 Flash release notes / what's new

    Google has released Gemini Omni 1.1 Flash, introducing advanced creative controls for generative video, including scene extension, keyframe interpolation, and 4K upscaling.

  • Dispatch
    Gemini Omni Flash Release

    Google DeepMind has introduced Gemini Omni Flash, a natively multimodal model capable of generating and editing high-quality videos from combinations of text, image, audio, and video inputs.

  • Dispatch
    Gemini 3.1 Flash Live release notes / what's new

    Google DeepMind has released Gemini 3.1 Flash Live, a high-quality audio and voice model designed for natural, real-time dialogue with improved precision, lower latency, and expanded global availability.

  • Dispatch
    Gemini Omni: Google DeepMind's Leap into Conversational Video Creation

    Google DeepMind introduces Gemini Omni, a multimodal AI system capable of creating and editing high-fidelity video through natural language conversation and diverse reference inputs.

  • Dispatch
    Nano Banana 2 Lite and Gemini Omni Flash Release

    Google DeepMind has released Nano Banana 2 Lite for high-speed, cost-efficient image generation and Gemini Omni Flash for high-quality video generation and conversational editing.