gemini-omni-1.1-flash — Video Generation AI Model
This node was VEO 3.1. Google retires VEO 3.1 on 2026-10-22, so it now runs Gemini Omni 1.1 Flash behind the same ports - text, a still, a first and last frame, or references in; a clip with sound out at up to 4K. Runs on Google's side, against your API key.
What it does
This node was built on VEO 3.1. Google retires VEO 3.1 on 2026-10-22, so it now runs Gemini Omni 1.1 Flash behind the same ports and settings: text, one still, a first and a last frame, or up to three reference images in, a clip with synthesised sound out at 720p, 1080p or 4K.
Saved flows keep working, and the image mode still decides which image ports are read. Clip length is now chosen by the model rather than the seconds setting, and seed, person policy and reference types no longer apply.
When to use it
- Short cinematic clips with ambient sound generated alongside them
- Animating a single still while keeping its look in the first frame
- Interpolating motion between a first and a last frame you supply
- Keeping flows built on VEO running after Google retires VEO 3.1
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
Text prompt for video generation
- Image 1Inputimageoptional
Source image, first frame, or reference image 1
- Image 2Inputimageoptional
Last frame or reference image 2
- Image 3Inputimageoptional
Reference image 3 (Reference Image mode only)
- VideoOutputvideo
Generated video with native audio
Parameters
- modelstringdefault VEO 3.1options: VEO 3.1, VEO 3.1 Fast, VEO 3.1 Lite
Model variant
Kept for saved flows. Google retires VEO 3.1 on 2026-10-22, so 'VEO 3.1', 'VEO 3.1 Fast' and 'VEO 3.1 Lite' all run Gemini Omni 1.1 Flash and behave the same.
- image_modestringdefault Text to Videooptions: Text to Video, Image to Video, First & Last Frame, +1 more
Input-image mode
How the optional image inputs are used. 'Text to Video' (default) ignores images and generates from text only. 'Image to Video' animates Image 1. 'First & Last Frame' interpolates motion from Image 1 to Image 2. 'Reference Image' uses up to three images (Image 1-3) as subject or style references.
- aspect_ratiostringdefault 16:9options: 16:9, 9:16
Aspect ratio
Output video aspect ratio. '16:9' for landscape / cinema, '9:16' for vertical / mobile.
- resolutionstringdefault 720poptions: 720p, 1080p, 4k
Resolution (720p/1080p/4k)
Output resolution. '720p' (default) is the native generation size; '1080p' and '4k' are upscaled by the model.
Limitations
- The default image mode is text only and ignores images wired to the image ports - a clip that resembles nothing you supplied is usually this.
- Clip length is decided by the model (about ten seconds at most). The seconds, seed, person and reference-type settings stay in saved flows but are not used.
- VEO 3.1, Fast and Lite now call the same model, so the cheaper tiers no longer cost less or run faster.
- Runs on your own Google AI API key. Without one configured in the workspace the node cannot run.
Tags
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.
- Omni
Google Gemini Omni: text/image/video in, video out, with conversational editing. Which input ports apply depends on Task — Text to Video: Text only. Image to Video: + Image 1. Reference to Video: + Image 1–3. Edit / Extend: + Video (aspect ratio and resolution are ignored). Unused ports are dropped even if wired. Needs API key.
- Video Analysis
Gemini video analysis. Feed a video and get back timecoded highlight segments. Needs API key.