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

# Seedance 2.5 API

> Generate, edit, and extend videos with ByteDance Seedance 2.5.

<div className="models-color-scope" aria-hidden="true" />

Seedance 2.5 supports text-to-video, frame-based animation, multimodal references, video editing, and video extension. Generate at 480p or 720p through dedicated workflow endpoints.

<div className="model-workflow-tabs" aria-label="Seedance endpoints">
  <a className="model-workflow-tab" href="/docs/models/seedance-2-5/text-to-video">Text to video</a>
  <a className="model-workflow-tab" href="/docs/models/seedance-2-5/image-to-video">Image to video</a>
  <a className="model-workflow-tab" href="/docs/models/seedance-2-5/reference-to-video">Reference to video</a>
  <a className="model-workflow-tab" href="/docs/models/seedance-2-5/video-edit">Video edit</a>
  <a className="model-workflow-tab" href="/docs/models/seedance-2-5/video-extend">Video extend</a>
</div>

**Default endpoint:** `POST https://api.higgsfield.ai/bytedance/seedance-2.5/text-to-video`

**Endpoint ID:** `bytedance/seedance-2.5/text-to-video`

<a className="model-playground-card" href="https://console.higgsfield.ai/models/bytedance%2Fseedance-2.5%2Ftext-to-video/playground" target="_blank" rel="noreferrer">
  <span className="model-playground-icon">▶</span>
  <span className="model-playground-copy"><span className="model-playground-title">Try Seedance 2.5</span><span>Open this endpoint in the Higgsfield API Playground.</span></span>
  <span className="model-card-arrow">↗</span>
</a>

## Available endpoints

| Workflow                                                      | Endpoint                                          | Inputs                                                                 |
| ------------------------------------------------------------- | ------------------------------------------------- | ---------------------------------------------------------------------- |
| [Text to video](/docs/models/seedance-2-5/text-to-video)           | `POST /bytedance/seedance-2.5/text-to-video`      | A non-empty `prompt`; no media inputs.                                 |
| [Image to video](/docs/models/seedance-2-5/image-to-video)         | `POST /bytedance/seedance-2.5/image-to-video`     | Required `image_url` and optional `end_image_url`.                     |
| [Reference to video](/docs/models/seedance-2-5/reference-to-video) | `POST /bytedance/seedance-2.5/reference-to-video` | At least one reference in `image_urls`, `video_urls`, or `audio_urls`. |
| [Video edit](/docs/models/seedance-2-5/video-edit)                 | `POST /bytedance/seedance-2.5/video-edit`         | Required `prompt` and `video_url` for the source footage.              |
| [Video extend](/docs/models/seedance-2-5/video-extend)             | `POST /bytedance/seedance-2.5/video-extend`       | Required `prompt` and `video_url` for the source footage.              |

## Quick Start

```bash cURL theme={"dark"}
curl --request POST \
  --url https://api.higgsfield.ai/bytedance/seedance-2.5/text-to-video \
  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "A cinematic tracking shot of a cyclist along a sunlit coastal road",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'
```

The request returns a `request_id` and `status_url`. [Poll the status URL](/docs/concepts/polling) or configure [webhooks](/docs/how-to/webhooks) to retrieve the completed video.

## Workflow parameters

* Use `480p` or `720p` resolution.
* Use public media URLs; `asset://` references are not supported by these endpoints.
* Set an explicit `aspect_ratio`, such as `16:9`, for reference-to-video requests.
* Image-to-video uses the input image's framing. Video editing and extension use the source video's framing.
* Omit `duration` for video editing; the source clip determines its length. Set an explicit duration for generation and extension.
* The endpoint selects the workflow; a separate `mode` parameter is not needed.


## Related topics

- [Seedance 2.5 Image To Video API](/docs/models/seedance-2-5/image-to-video.md)
- [Seedance 2.5 Reference To Video API](/docs/models/seedance-2-5/reference-to-video.md)
- [Seedance 2.5 Text To Video API](/docs/models/seedance-2-5/text-to-video.md)
- [Seedance 2.5 Video Edit API](/docs/models/seedance-2-5/video-edit.md)
- [Seedance 2.5 Video Extend API](/docs/models/seedance-2-5/video-extend.md)