Seedance 2.0 API - Higgsfield API Docs

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

Text to video Image to video Reference to video

Default endpoint: POST https://api.higgsfield.ai/bytedance/seedance-2.0/text-to-video Endpoint ID: bytedance/seedance-2.0/text-to-video ▶Try Seedance 2.0Open this endpoint in the Higgsfield API Playground.↗

Available endpoints

Workflow	Endpoint	Inputs
Text to video	`POST /bytedance/seedance-2.0/text-to-video`	A non-empty `prompt`; no media inputs.
Image to video	`POST /bytedance/seedance-2.0/image-to-video`	Required `image_url` and optional `end_image_url`.
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

cURL

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 or configure 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.