Skip to main content
The video() method generates videos from text descriptions using AI models like Runway, Kling, and Luma.

Basic Video Generation

Video Sizes

Control video dimensions and aspect ratio:

Supported Sizes

Use 720x1280 for social media vertical videos (TikTok, Instagram Reels, YouTube Shorts).

Video Duration

Set how long the video should be:
Supported durations vary by model. Most support 5-10 seconds. Check your gate’s model capabilities.

Image-to-Video

Generate video from a starting image:

Base64 Images

Reference Images

Guide video generation with reference images:

Reference Types

Advanced Parameters

FPS (Frames Per Second)

Negative Prompts

Specify what to avoid:

Multiple Videos

Generate variations:

Deterministic Generation

Use seeds for reproducible results:

Parameters

Request Parameters

Response

Best Practices

1. Write Motion-Focused Prompts

2. Be Specific About Camera Movement

3. Use Appropriate Dimensions

4. Always Handle Errors

5. Monitor Costs

Video generation is more expensive than images:

Examples

Social Media Content

Marketing Video

Animation from Image

Nature Scene

Style-Consistent Video

Advanced Usage

Batch Generation

Generate multiple videos:

Override Model

Use a specific video model:

Custom Metadata

Track video generation:

Next Steps

Images

Generate static images

Audio

Add voiceover with text-to-speech

Gates & Routing

How Verlon routes video requests

Cost Tracking

Monitor video generation costs