2026-04-20 CometAPI Adds Doubao Seedance 2.0 Video Generation Models!

[tensornull]

CometAPI Update

• Call test to see the page (models)

doubao-seedance-2-0 / doubao-seedance-2-0-fast

• doubao-seedance-2-0: ByteDance's latest high-quality video generation model, supporting both text-to-video & image-to-video.

• doubao-seedance-2-0-fast: The accelerated version of Seedance 2.0 — faster generation, same powerful quality.

Important Notice

The legacy Seedance-series official API format is deprecated. All Seedance models (including doubao-seedance-1-5-pro and doubao-seedance-1-0-pro) should now use the unified v1/videos endpoint going forward.

Note: doubao-seedance-1-5-pro and doubao-seedance-1-0-pro do not support image-to-video (input_reference is not available for these models).

Parameters

Parameter

Description

Duration (seconds)

4–15 seconds, default 5

Aspect Ratio (size)

21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16, default 16:9

Resolution (resolution)

480p / 720p / 1080p*, default 720p

*1080p only available for doubao-seedance-1-5-pro and doubao-seedance-1-0-pro

Usage Example

curl --location --request POST 'https://api.cometapi.com/v1/videos' \
--header "Authorization: $COMETAPI_KEY" \
--header 'Content-Type: multipart/form-data' \
--form 'prompt="a cat running on the beach"' \
--form 'model="doubao-seedance-2-0"' \
--form 'seconds="5"' \
--form 'size="16:9"' \
--form 'resolution="720p"' \
--form 'input_reference=@"your_image.png"'

input_reference is optional — include a reference image forimage-to-video, or omit it fortext-to-video. Only supported by doubao-seedance-2-0 and doubao-seedance-2-0-fast.

Documentation

For full API details, please refer to: https://apidoc.cometapi.com/api/video/seedance/create