# Hailuo Live | Image to Video

Convert images to video with near zero latency (real time) for live streams and interactive applications using hailuo i2v live.

## API Information

- **Model Slug:** hailuo-i2v-live
- **Branded URL:** https://www.eachlabs.ai/minimax/i2v/hailuo-i2v-live
- **Provider:** MiniMax
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.50 per video generation
- **Estimated Processing Time:** 424 seconds
- **Last Updated:** 2026-04-09
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/hailuo-i2v-live

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.5000
- **Pricing Details:** $0.50 per video generation

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | $0.50 per video generation |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Enter your prompt to generate video |
| prompt_optimizer | boolean | No | true | - | The model will automatically optimize prompts to improve generation quality. To maintain stricter adherence to instructions, set this parameter to False. For best results, provide more detailed prompts. |
| first_frame_image | string | Yes | - | png, jpeg, jpg | First frame image for video generation. The output video will have the same aspect ratio as this image. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "hailuo-i2v-live",
  "input": {
    "first_frame_image": "https://storage.googleapis.com/magicpoint/inputs/hailuo-i2v-live-input.jpeg",
    "prompt": "let this person slowly hug the person on the left"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**hailuo-i2v-live — Image-to-Video AI Model**

hailuo-i2v-live from Minimax transforms static images into dynamic videos with near-zero latency, enabling real-time applications like live streams and interactive experiences that demand instant image-to-video AI model generation.

Part of the i2v family, this model stands out by delivering **live, real-time video synthesis** from images, a capability tailored for developers seeking **Minimax image-to-video** solutions where traditional models lag due to processing delays.

Ideal for **hailuo-i2v-live API** integrations, it supports high-quality outputs up to 1080p, making it perfect for creators and apps needing seamless animation of product shots or user uploads without waiting.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.