midjourney_generate_video
Generate AI video clips from a reference image by describing the motion in a prompt. Get four variations with adjustable resolution, mode, and optional end frame.
Instructions
Generate a video from a reference image using Midjourney.
This creates an AI-generated video based on your description and a starting
frame image. Midjourney video generation is image-to-video only — a reference
image is always required. You can optionally specify an ending frame for more
control.
Use this when:
- You want to animate a still image
- You want to create short video clips from a reference image
- You need AI-generated video content
The generation process returns 4 video variations.
Returns:
Task ID and video information including cover image and video URLs.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| loop | No | If true, generate a looping video where the end seamlessly connects to the beginning. | |
| mode | No | Generation mode. 'fast' is recommended for most use cases. | fast |
| prompt | Yes | Description of the video to generate. Examples: 'A cat walking on a table', 'Ocean waves crashing on the shore', 'Timelapse of clouds moving' | |
| image_url | Yes | URL of the first-frame reference image when generating the video. Required for video generation (Midjourney video generation is image-to-video only and does not support pure text-to-video). | |
| resolution | No | Video resolution. '720p' or '480p'. | 720p |
| callback_url | No | Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the video is generated. | |
| end_image_url | No | Optional URL of the last frame reference image. Use this to control where the video ends. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |