Try Pro FREE for 2 weeksGet Started
Start for free

gemini-omni-1.1-flash — Video Generation AI Model

Gemini Omni takes text, images or a clip and returns video, and edits conversationally: the node emits an Interaction ID, and feeding it into another Omni node refines the same clip rather than starting over.

Try in Studio

What it does

Omni takes text, images or an existing clip and returns video. The Task selector decides which input ports are read - text alone, a still to animate, up to three reference images, or a clip to edit or extend - and ports the Task does not use are dropped even when they are wired.

Its point is editing by conversation. The node emits an Interaction ID, and feeding that into the next Omni node's Previous Interaction ID port refines the same clip instead of generating a new one, so "now make it night" is a second node rather than a second attempt.

When to use it

  • Refining one generated clip over several steps instead of re-rolling
  • Animating a still image into a short clip from a written direction
  • Holding a subject or a style steady using up to three references
  • Editing a clip you already have by describing the change in words
  • Extending a clip by about ten seconds at a time, up to forty in all

Details

  • CategoryVideo Generation
  • Year2026
  • LicenseGoogle Cloud Terms

Compliance & Provenance

  • ProviderGoogle · GPAI
  • EU AI Act RiskLimited Risk
  • Art. 50 TransparencyRequired — AI-generated outputs are marked

Inputs & Outputs

TextInputstring

[all tasks] Prompt describing the video to generate, or the edit to apply.

Image 1Inputimageoptional

[Image to Video / Reference to Video / Edit] Source image, or reference image 1. Ignored by Text to Video.

Image 2Inputimageoptional

[Reference to Video / Edit] Reference image 2. Ignored by Text to Video and Image to Video.

Image 3Inputimageoptional

[Reference to Video / Edit] Reference image 3. Ignored by Text to Video and Image to Video.

VideoInputvideooptional

[Edit only] The existing clip to modify. Ignored — and not uploaded — by every other task.

Previous Interaction IDInputstringoptional

[any task] Interaction ID output by a previous Omni node. Continues editing that same video instead of generating a new one.

VideoOutputvideo

Generated or edited video.

Interaction IDOutputstring

Wire into another Omni node's Previous Interaction ID port to keep editing this video.

Parameters

modelstringdefault Omni Flashoptions: Omni Flash

Model variant

Which Omni tier to call. 'Omni Flash' (default) runs Gemini Omni 1.1 Flash, the only tier currently published.

taskstringdefault Text to Videooptions: Text to Video, Image to Video, Reference to Video, Edit, +1 more

Task (decides which input ports apply)

What Omni should do. 'Text to Video' (default) generates from the prompt alone and ignores any wired images. 'Image to Video' animates a supplied still. 'Reference to Video' uses up to three images as subject/style references. 'Edit' modifies an existing clip and 'Extend' continues one by about 10 seconds (up to 40 s total) — supply the clip on the Video port, or chain a Previous Interaction ID to work on the clip a prior Omni node produced.

aspect_ratiostringdefault 16:9options: 16:9, 9:16

Aspect ratio (not used by Edit/Extend)

Output video aspect ratio. '16:9' for landscape / cinema, '9:16' for vertical / mobile. IGNORED by Edit and Extend: they inherit the source clip's geometry, and the API rejects the field outright if it is sent, so it is dropped from the request for those tasks.

resolutionstringdefault 720poptions: 720p, 360p, 1080p, 4k

Resolution (not used by Edit/Extend)

Output resolution. '720p' (default) is the native generation size; '360p' is a cheaper preview; '1080p' and '4k' are upscaled by the model. Ignored by Edit and Extend, which keep the source clip's resolution.

Limitations

  • No duration, seed or negative-prompt controls here - put negative guidance in the prompt. Resolutions above 720p are upscaled.
  • Edit and Extend ignore aspect ratio and resolution: they inherit the geometry of the clip they started from.
  • Runs on your own Google AI API key. Without one configured in the workspace the node cannot run.

Tags

  • video-generation
  • video-editing
  • text-to-video
  • image-to-video
  • multimodal
  • conversational-editing

Alternatives in Image/Video Models

  • GPT Image

    OpenAI GPT-Image text-to-image / edit. Needs API key.

  • Nano Banana

    Google Gemini-based image gen/edit with multimodal reasoning. Needs API key.

  • VEO

    Text/image to video with native audio, now run by Gemini Omni 1.1 Flash (Google retires VEO 3.1 on 2026-10-22). Needs API key.

  • Video Analysis

    Gemini video analysis. Feed a video and get back timecoded highlight segments. Needs API key.

Resources

All AI models