minimax/hailuo/02-fast/image-to-video
Hailuo 02 Fast is MiniMax's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runminimax/hailuo/02-fast/image-to-videoInput Schema
4 parameters · 2 required · 2 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | — |
prompt | string | Required | Max length: 2000 |
duration | integer | Optional | The duration of the video in seconds. 10 seconds videos are not supported for 1080p resolution. · Options: 6, 10 · Default: 6 610 |
prompt_optimizer | boolean | Optional | Whether to use the model's prompt optimizer · Default: true |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "minimax/hailuo/02-fast/image-to-video",
"image": "https://static.sandbase.ai/examples/minimax/hailuo/02-fast/image-to-video/input_image_0.webp",
"prompt": "Extremely realistic movement An old samurai is breaking a stone in half",
"duration": 6,
"prompt_optimizer": true
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
MiniMax Hailuo 02 Fast (Image to Video)
MiniMax Hailuo 02 Fast Image-to-Video animates a supplied still image into a short video while using the prompt to define subject movement, camera behavior, and scene evolution. It is the speed-oriented Hailuo 02 route for teams that already have a key visual and need motion rather than a scene invented entirely from text.
The route offers six- and ten-second generation with prompt optimization enabled by default, helping concise direction expand into more production-ready motion language. Its image-led workflow is useful for social creative, product shots, character beats, and storyboard frames that must retain the source image as their visual anchor.
Highlights
Image-anchored animation. Preserves the supplied still as the visual starting point while the prompt directs movement and camera action.
Fast Hailuo 02 workflow. Prioritizes turnaround for short-form image-to-video iterations and rapid creative review.
Six- or ten-second clips. Supports two practical short-form durations for quick beats and more developed motion.
Prompt optimization. Can automatically expand concise direction into richer motion instructions, while allowing direct prompt handling when disabled.
Pricing
| Duration | Price |
|---|---|
| 6 seconds | $0.102 |
| 10 seconds | $0.170 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| A still image should anchor the video's subject and composition | The whole scene should be invented from text alone |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For image-conditioned generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{
"duration": 6,
"image": "https://static.sandbase.ai/examples/minimax/hailuo/02-fast/image-to-video/input_image_0.webp",
"prompt": "Extremely realistic movement An old samurai is breaking a stone in half"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | minimax/hailuo/02-fast/image-to-video |
| Inputs | duration, image, prompt, prompt_optimizer |
| Required inputs | prompt, image |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |
| Duration | 6 / 10 |
Related Models
minimax/hailuo/02/pro/image-to-video— Compare a nearby route in the same local model family.minimax/hailuo/02/pro/text-to-video— Compare a nearby route in the same local model family.minimax/hailuo/02/standard/image-to-video— Compare a nearby route in the same local model family.