> ## 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.

# Seedance 1.0 Lite Text-to-Video

> ByteDance Seedance 1.0 Lite text-to-video model — supports video generation from text and images with flexible control over duration, aspect ratio, and resolution.

Seedance 1.0 Lite Text-to-Video is a video generation model from ByteDance's Seedance series, available through the Starrise AI API. It uses a multimodal content format to create videos from text prompts and reference images.

## Key Capabilities

* **Text-to-video** — Generate videos from text prompts
* **Flexible duration** — Generate 2–12 second videos
* **Multiple aspect ratios** — 16:9, 4:3, 1:1, 3:4, 9:16, 21:9
* **Multiple resolutions** — 480p, 720p, 1080p

## Quick Example

```bash cURL theme={null}
curl https://dayu.cdn-fly.com/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-1-0-lite-t2v-250428",
    "content": [
      {"type": "text", "text": "A cat walking through a sunflower field under a golden sunset"}
    ],
    "ratio": "16:9",
    "duration": 5,
    "resolution": "720p"
  }'
```

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

response = requests.post(
    "https://dayu.cdn-fly.com/v1/video/generations",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "doubao-seedance-1-0-lite-t2v-250428",
        "content": [
            {"type": "text", "text": "A cat walking through a sunflower field under a golden sunset"}
        ],
        "ratio": "16:9",
        "duration": 5,
        "resolution": "720p"
    }
)

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

## Parameters

| Parameter | Type | Required | Description |
| - | - | - | - |
| `model` | string | Yes | Must be `doubao-seedance-1-0-lite-t2v-250428` |
| `content` | array | Yes | Multimodal array: text (required) + image\_url (for image-to-video, with role) |
| `ratio` | string | No | `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `21:9`, `adaptive`, default `16:9` |
| `resolution` | string | No | `480p`, `720p`, `1080p`, default `720p` |
| `duration` | integer | No | 2–12 seconds, default `5` |
| `watermark` | boolean | No | Whether to add a watermark, default `false` |
| `seed` | integer | No | Random seed for reproducibility |
| `camera_fixed` | boolean | No | Whether to fix the camera, default `false` |

> **[API Reference](/en/api-reference/model-api/bytedance/doubao-seedance-1-0-lite-t2v-250428)**
>
> View the interactive API Playground for Seedance 1.0 Lite Text-to-Video.


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