Logo
LoginGet Started
Profile

google / veo-3.1-extend-video

Extend existing Veo-generated videos by seamlessly adding 7 seconds of high-fidelity footage and synchronized audio using text prompts.

0.4 per second of output video

Model Input

Input

The text description for the video extension.

The URL of the Veo-generated video to extend. Must be a 720p video with 16:9 or 9:16 aspect ratio.

Text describing what not to include in the video.

The aspect ratio of the video.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

Fill in the input form and click submit to see the output
Logs (1 lines)

Model Details

Model Details

# Extend Your Vision with Veo 3.1

This model effectively lengthens video content by extending previously generated Veo clips. It analyzes the final frames of an input video to generate an additional 7 seconds of footage, maintaining seamless continuity in visual style, lighting, and motion. This capability transforms short clips into longer, cohesive narratives, complete with natively generated audio that synchronizes perfectly with the new visual action.

Designed for iterative storytelling, the model outputs a single unified video file combining the original input with the new extension. You can use the output of one run as the input for the next, supporting up to approximately 20 sequential extensions for a total duration of nearly 2.5 minutes. This allows for complex scene evolution, such as tracking a subject across different environments or developing a longer sequence of events.

### Key Features

* **Seamless Continuity:** Ensures smooth transitions by preserving the context, characters, and aesthetics of the source video. * **Prompt-Driven Direction:** Use text prompts to guide the extension, allowing you to introduce new actions, change camera angles, or shift the narrative focus. * **Native Audio Extension:** Automatically generates coherent audio for the new segment, matching the ambience and events of the original clip.

### Usage Guidelines

To achieve the best results via the UI, ensure your input meets the specific requirements of the underlying engine:

* **Source Material:** The `video_url` must point to a video originally generated by Veo. * **Technical Specs:** Input videos must be 720p resolution and have an aspect ratio of either 16:9 or 9:16. * **Duration Limit:** The input clip must be 141 seconds or less.

### Example Usage

To run via ModelRunner javascript client, use the following code:

```javascript import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe('google/veo-3.1-extend-video', { input: { "prompt": "Track the butterfly into the garden as it lands on an orange origami flower. A fluffy white puppy runs up and gently pats the flower.", "video_url": "https://storage.googleapis.com/generativeai-downloads/images/Butterfly_original.mp4", "negative_prompt": "blurry, low quality, distorted, watermark", "aspect_ratio": "16:9" } }); ```