> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cdn-fly.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Kling 1.6 Multi-Image-to-Video

> Kuaishou Kling 1.6 multi-image-to-video model. Generate videos from up to 4 reference images.

Kling 1.6 Multi-Image-to-Video is a multi-image-to-video model in Kuaishou's Kling series, available through the Starrise AI API. Upload up to 4 reference images and combine them with a text prompt to generate a coherent video featuring all referenced subjects.

## Key Capabilities

* **Multi-image input** — Use up to 4 reference images as character/scene sources
* **Text guidance** — Combine images and text prompts to control video narrative
* **Flexible duration** — Generate 5-second or 10-second videos
* **Aspect ratio** — Supports 16:9, 9:16, and 1:1 output formats
* **Standard & Pro modes** — Choose standard mode or high-quality pro mode

## Quick Example

```bash cURL theme={null}
curl https://dayu.cdn-fly.com/kling/v1/videos/multi-image2video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-v1-6",
    "image_list": [
      {"image": "https://example.com/person1.jpg"},
      {"image": "https://example.com/person2.jpg"}
    ],
    "prompt": "Two people shake hands and smile at each other",
    "duration": "5",
    "mode": "std",
    "aspect_ratio": "16:9"
  }'
```

```python Python theme={null}
import requests

response = requests.post(
    "https://dayu.cdn-fly.com/kling/v1/videos/multi-image2video",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model_name": "kling-v1-6",
        "image_list": [
            {"image": "https://example.com/person1.jpg"},
            {"image": "https://example.com/person2.jpg"}
        ],
        "prompt": "Two people shake hands and smile at each other",
        "duration": "5",
        "mode": "std",
        "aspect_ratio": "16:9"
    }
)

task = response.json()
print(f"Task ID: {task['task_id']}")
```

## Parameters

| Parameter | Type | Required | Description |
| - | - | - | - |
| `model_name` | string | No | Must be `kling-v1-6` |
| `image_list` | array | Yes | Reference images (1–4), each item format: `{"image": "url_or_base64"}` |
| `prompt` | string | Yes | Text prompt (up to 2500 characters) |
| `negative_prompt` | string | No | Negative prompt (up to 2500 characters) |
| `mode` | string | No | `std` or `pro`, default `std` |
| `duration` | string | No | `5` or `10` seconds, default `5` |
| `aspect_ratio` | string | No | `16:9`, `9:16`, or `1:1`, default `16:9` |
| `callback_url` | string | No | Task status callback URL |

> **[API Reference](/en/api-reference/model-api/kuaishou/kling-v1-6-mi2v)**
>
> View the interactive API Playground for Kling 1.6 Multi-Image-to-Video.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.