Seedance 2.0 Fast video generation model (with or without audio). A lightweight, faster variant of Seedance 2.0 with identical capabilities and parameters.
Pass Authorization: Bearer <YOUR_API_KEY> in the request header. Go to the API Keys management page to create and manage API Keys.
Fixed value doubao/seedance-2.0-fast.
The prompt. Supports Chinese, English, Japanese, Indonesian, Spanish, and Portuguese.
We recommend ≤ 500 Chinese characters or ≤ 1000 English words; overly long prompts may cause the model to ignore some details.
"A slow pan across a misty mountain valley at sunrise, cinematic"
Output resolution. Defaults to 720P.
480P, 720P Output aspect ratio. Defaults to adaptive (auto-adapted by the model based on the input assets or prompt).
16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive Video duration in seconds. Defaults to 5; integer in the range 4 ~ 15.
4 <= x <= 15Whether to generate audio in sync with the video. Defaults to true. Generated audio is mono.
Reference image list. Up to 9 images. The input mode is determined by the reference_type combination:
first_framefirst_frame + 1 last_frameasset; may be combined with reference_videos / reference_audiosImage requirements: formats
jpeg/png/webp/bmp/tiff/gif; ≤ 30 MB per image; total request body ≤ 64 MB (avoid base64 for large files); width/height 300–6000 px; aspect ratio between 1:2.5 and 2.5:1.
9Reference video list. Up to 3 clips; total duration across all videos ≤ 15 seconds; public URL only.
Video requirements: formats
mp4/mov; resolution 480P / 720P; 2–15 seconds per clip, ≤ 50 MB each; width/height 300–6000 px; aspect ratio between 1:2.5 and 2.5:1; pixel-product range [640×640, 834×1112]; FPS 24–60.
3Reference audio list. Up to 3 clips; total duration across all audios ≤ 15 seconds. Cannot be used alone — must be accompanied by at least one reference_image or reference_video.
Audio requirements: formats
wav/mp3; 2–15 seconds per clip, ≤ 15 MB each; total request body ≤ 64 MB (avoid base64 for large files).
3Supports Seedance's official extension parameters. All optional:
seed — integer in [-1, 2^32-1]. -1 or omitted uses a random seed; the same seed yields similar (but not guaranteed identical) outputs.watermark — boolean, defaults to false. Whether to add a watermark to the generated video.return_last_frame — boolean, defaults to false. When enabled, you can retrieve the generated video's last-frame image (PNG, no watermark, same dimensions as the video) via the query endpoint, useful for chaining multiple continuous video segments.Submitted successfully (asynchronous mode)
Unique task ID, used for subsequent polling
"task_2044275355061448704"
The model ID used for this task
"doubao/seedance-2.0-fast"
Task creation time (ISO 8601)
"2026-04-15T04:43:20.233Z"
Unique request ID
"67e2e394-cf6f-4998-b293-ebf20d14dc26"