seedance-2
seedance-2 Video Generation
Generate videos with seedance-2, seedance-2-fast, and seedance-2-mini
POST
- Supports
seedance-2,seedance-2-fast, andseedance-2-mini - Supports text-to-video, first-frame / first-last-frame image-to-video, and multimodal reference-to-video;
seedance-2-minialso supports frame roles and the audio generation switch - Supports combined image, video, and audio references;
seedance-2-miniallows up to9images,3videos, and3audios - Async task workflow: the submit API returns
generation.task, and the completed result is fetched from the task status API
Authorizations
string
required
Body
string
default:"seedance-2"
required
Video generation model name.Available models:
seedance-2- Standard version for higher quality output and the broader Seedance 2 workflowseedance-2-fast- Faster version for previews and lower-latency iterationseedance-2-mini- Lightweight version for lower-cost drafts and multimodal reference workflows, currently fixed to1result per request
string
Video content description.Supports Chinese and English input. We recommend clearly describing the scene, camera motion, subject action, style, and audio mood.Recommendations:
- Keep Chinese prompts within
500characters - Keep English prompts within
1,000words - When referring to reference materials, use “image 1 / video 1 / audio 1” to identify them
string
Your business-side ID, such as an order number or internal job ID. Once submitted, it is stored with the task and can be used later for status lookup:
GET /v1/videos/generations/{client_business_id}.metadata.client_business_id is also accepted, but the top-level field is recommended.integer
default:0
Video duration in seconds.Rules:
seedance-2:4-15seedance-2-fast:4-15seedance-2-mini:4-150: auto duration (seedance-2/seedance-2-fastonly)-1: auto duration (seedance-2/seedance-2-fastonly)
string
Video aspect ratio.Options:
21:916:94:31:13:49:16adaptive
adaptive lets the upstream choose an appropriate ratio from the input media.string[]
Compatibility image URL array.We recommend using
image_with_roles instead so you can explicitly mark first_frame, last_frame, or reference_image.array
Image list with explicit roles.Supported patterns:
seedance-2/seedance-2-fast/seedance-2-minifirst_framefor first-frame image-to-videofirst_frame+last_framefor first-last-frame video generationreference_imagefor multimodal reference generation
array
Video list with roles.Only
reference_video is currently supported in multimodal reference mode.Limits:seedance-2-mini: up to3reference videos
array
Audio list with roles.Only
reference_audio is currently supported in multimodal reference mode.Limits:seedance-2-mini: up to3reference audios
string
default:"720p"
Video resolution.Options:
seedance-2:480p,720p,1080p,4kseedance-2-fast:480p,720pseedance-2-mini:480p,720p
boolean
default:true
Whether to generate synced audio.
seedance-2-mini also supports this field.boolean
default:false
Whether to return the generated video’s last-frame image.When set to
true, the completed task response includes the image URL at result.data[0].last_frame_url.array
Tools the model may call. The Seedance 2 series currently supports web search:The model decides whether a search is needed from the prompt. The actual number of searches is returned at
usage.tool_usage.web_search; 0 means no search was performed.integer
Random seed for generation control.
string
ToAPIs standardized completion callback. Configure the Token URL and signing secret first; request-level URLs must be same-origin. See Task Webhooks.
string
Your tracking field. It does not depend on Webhook configuration.
Use Uploaded Assets
If you already uploaded private assets and obtained a usableasset_id, you do not need to send the original media URL again. Use:
asset://<ASSET_ID>
- Images:
first_frame,last_frame,reference_image - Videos:
reference_video - Audios:
reference_audio
active status.
Related guides:
Input Combinations
Typical supported combinations:- Text only: text-to-video
- Text + first frame: first-frame image-to-video
- Text + first frame + last frame: first-last-frame generation
- Text + reference images: multimodal reference generation
- Text + reference video: video-reference generation
- Text + reference images + reference audio: multimodal reference generation
- Text + reference images + reference video + reference audio: multimodal reference generation
Capabilities
seedance-2-mini is currently fixed to 1 output per request and does not expose count / n. Express frame control through image_with_roles using first_frame / last_frame.Response
string
Task ID for status queries.
string
Your business-side ID. Returned only when
client_business_id was provided in the request.string
Object type, always
generation.task.string
Model name used for this request.
string
Task status:
queued, in_progress, completed, or failed.integer
Task progress percentage (
0-100).integer
Task creation timestamp.
The submit API returns the base task object. After completion, use Get Video Task Status to fetch
completed_at, expires_at, and result.type = "video" with result.data[].url and result.data[].format. With return_last_frame, the last-frame URL is at result.data[0].last_frame_url; with web_search, the search count is at usage.tool_usage.web_search.