> ## 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 2.0 API

> Generate videos from text, images, and multimodal references with ByteDance Seedance 2.0.

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

Seedance 2.0 generates videos from a text prompt, first and last frames, or a combination of image, video, and audio references.

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

**Default endpoint:** `POST https://api.higgsfield.ai/bytedance/seedance-2.0/text-to-video`

**Endpoint ID:** `bytedance/seedance-2.0/text-to-video`

<a className="model-playground-card" href="https://console.higgsfield.ai/models/bytedance%2Fseedance-2.0%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 2.0</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/text-to-video)           | `POST /bytedance/seedance-2.0/text-to-video`      | A non-empty `prompt`; no media inputs.                                              |
| [Image to video](/docs/models/seedance-2/image-to-video)         | `POST /bytedance/seedance-2.0/image-to-video`     | Required `image_url` and optional `end_image_url`.                                  |
| [Reference to video](/docs/models/seedance-2/reference-to-video) | `POST /bytedance/seedance-2.0/reference-to-video` | At least one image or video in `image_urls` or `video_urls`; optional `audio_urls`. |

## Quick Start

```bash cURL theme={"dark"}
curl --request POST \
  --url https://api.higgsfield.ai/bytedance/seedance-2.0/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.

## Working with references

* 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.
* Keep first/last-frame inputs separate from the reference arrays.
* Set an explicit output duration; automatic duration (`-1`) is not supported.


## Related topics

- [Seedance 2.0 Image To Video API](/docs/models/seedance-2/image-to-video.md)
- [Seedance 2.0 Reference To Video API](/docs/models/seedance-2/reference-to-video.md)
- [Seedance 2.0 Text To Video API](/docs/models/seedance-2/text-to-video.md)
- [Grok Image 2.0 API](/docs/models/grok-image-2.md)
- [Grok Image 2.0 Generate and Edit API](/docs/models/grok-image-2/generate-and-edit.md)