Midjourney Image To Video API Documentation

Midjourney Image To Video API Documentation

Playground

Midjourney Image to Video turns a single image into an artistically rich, high quality AI video with strong visual style and creative motion. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Midjourney Image-to-Video generates a video from a single input image. Upload an image, optionally describe the desired motion or scene, choose the output resolution, and select the motion strength for the generated video.

Why Choose This?

• Image-to-video generation
  Convert a single input image into a generated video.

• Optional motion guidance
  Add a prompt to describe the motion, camera movement, or scene direction.

• Resolution options
  Choose between 480p and 720p depending on your quality and cost requirements.

• Motion strength control
  Select low or high motion strength to control how much movement appears in the generated video.

• Simple workflow
  Only an input image is required. If no prompt is provided, a gentle cinematic camera movement is used.

Parameters

How to Use

1. Upload your image — Provide the input image to use as the first frame.
2. Add motion guidance (optional) — Describe the motion, camera movement, or scene direction you want.
3. Select resolution — Choose 480p or 720p. The default is 480p.
4. Choose motion strength — Select low or high. The default is low.
5. Submit — Generate the final video.

Output

Returns generated video URL(s) in the standard WaveSpeed prediction response.

Pricing

Billing Rules

• Pricing is charged per generation.
• 480p costs $0.35 per generation.
• 720p costs $1.10 per generation.
• The price depends on the selected resolution.

Best Use Cases

• Image animation — Turn a still image into a generated video.
• Cinematic camera movement — Add gentle camera motion to a static image.
• Motion exploration — Test different motion strengths from the same input image.
• Scene development — Use prompt guidance to describe how the image should move or evolve.
• Short visual content — Generate video assets from image references.

Pro Tips

• Use a clear input image with the main subject visible.
• Add a prompt when you want more control over the motion or scene direction.
• Leave prompt empty when you want the default gentle cinematic camera movement.
• Use low motion for more subtle movement.
• Use high motion when you want stronger movement.
• Use 480p for lower-cost testing and 720p for higher-resolution output.
• Ensure the image URL is publicly accessible.

Notes

• image is the only required field.
• prompt, resolution, and motion are optional.
• Default resolution is 480p.
• Default motion is low.
• If prompt is omitted, a gentle cinematic camera movement is used.
• Ensure uploaded image URLs are publicly accessible.

## Authentication

For authentication details, please refer to the [Authentication Guide](/api-authentication).

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} />

#### Response Parameters

<SubmitResponse />

#### Result Request Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| id | string | Yes | - | Task ID |

#### Result Response Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., "success") |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: `completed` is successful; `failed`, `cancelled`, `timeout`, and `deleted` are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |