Minimax H3 Image To Video

Minimax H3 Image To Video

Playground

MiniMax H3 Image to Video animates a first-frame image into a coherent 2K video, with natural-language motion instructions and optional last-frame control for consistent motion, scene continuity, and cinematic video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax H3 Image-to-Video generates high-resolution videos from a first-frame image and a text prompt. Upload an image, describe the desired motion and scene, optionally provide a last-frame image, and generate a 2k video output from 5 to 15 seconds.

Why Choose This?

• Image-to-video generation
  Animate a first-frame image into a video guided by your prompt.

• First-frame control
  Use the input image to define the starting visual state, subject, composition, and style.

• Optional last-frame guidance
  Provide last_image when you want to guide the ending frame or final visual direction.

• 2K video output
  Generate high-resolution video outputs with the fixed 2k resolution tier.

• Selectable duration
  Generate videos from 5 to 15 seconds.

• Simple generation workflow
  Provide an image and prompt, optionally add a last image, then generate the final video.

Parameters

How to Use

1. Upload first-frame image — Provide the image that should guide the opening frame, subject, style, and composition.
2. Write your prompt — Describe the desired motion, camera movement, scene development, lighting, and mood.
3. Add last image optional — Use last_image when you want to guide the final frame or ending direction.
4. Set duration — Choose a video length from 5 to 15 seconds.
5. Submit — Generate the video and retrieve the output URL.

Pricing

Pricing is $0.13 per second of generated 2K video.

Best Use Cases

• Image animation — Turn a still image into a high-resolution motion clip.
• Start-and-end-frame video generation — Use image and last_image to guide the beginning and ending of the video.
• Cinematic scene creation — Generate short videos with camera movement, atmosphere, and visual continuity.
• Character and product motion — Animate a subject, product, or scene from a reference image.
• Story and scene prototyping — Turn image concepts into short 2K video previews.
• Creative visual development — Explore motion, lighting, mood, and composition from a single starting frame.

Pro Tips

• Use a clear first-frame image with the main subject visible.
• Describe visible motion, camera behavior, lighting, mood, and scene progression in the prompt.
• Use last_image when the ending frame or final visual direction matters.
• Keep the first and last images visually compatible when using both.
• Use shorter durations for quick prompt testing and longer durations when the scene needs more time to develop.
• Make sure the input image matches the desired composition and aspect ratio.

Related Models

• MiniMax H3 Text-to-Video — Generate high-resolution video directly from text prompts.
• MiniMax H3 Reference-to-Video — Generate high-resolution video from reference media and prompt guidance.

## 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.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: `created`, `processing`, `completed`, or `failed` |
| 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 |