Video: Edit & Effects

seedance-2.5-omni-reference (balanced)

Generate video guided by multiple reference images, videos, and audio with Seedance 2.5. Input: prompt (required) + optional images_list (up to 20), videos_list (up to 6), audios_list (up to 6), resolution (480p/720p/1080p/4k, default 720p), duration (4-30s), aspect_ratio, seed. Output: video at the selected resolution. Use for: style-consistent multi-reference video, camera-motion transfer, audio-guided mood.

post/api/v1/seedance-2.5-omni-reference

Request

  • Base URL: https://api.muapi.ai
  • URL: https://api.muapi.ai/api/v1/seedance-2.5-omni-reference
  • Auth: one of:
    • API key in header x-api-key
    • OAuth 2 (client credentials, token URL https://api.muapi.ai/oauth/token)

Query parameters

webhookstring
team_idinteger nullable

Headers

x-api-keystring
x-embed-codestring nullable
x-agent-embed-codestring nullable
x-whitelabel-studiostring nullable
authorizationstring nullable

Request body

webhook_urlstring uri nullable
durationinteger

Video duration in seconds, from 4 to 30.

aspect_ratio'adaptive' | '16:9' | '9:16' | '1:1' | '4:3' | '3:4' | '21:9' | '9:21'
seedinteger nullable

Random seed for reproducible generation. Use -1 for random.

high_bitrateboolean
promptstring nullable

Text prompt describing the desired video, referencing the provided images, video clips, and audio as environment, motion, and mood cues. Required unless draft_request_id is set.

images_liststring[] nullable

Reference image URLs. Up to 30 images.

videos_liststring[] nullable

Reference video URLs. Up to 10 clips.

audios_liststring[] nullable

Reference audio URLs. Up to 10 files.

omni_reference_task_type'auto' | 'reference' | 'edit' | 'extend'

Hint for the omni-reference subtask type (reference-to-video, video editing, or video extension), so mismatches with ratio/duration are caught at submission time instead of failing asynchronously. The provider still re-derives the actual type from the prompt during processing, so a mismatch can still surface as an async error.

resolution'480p' | '720p' | '1080p' | '4k'

Output resolution. Price scales with resolution — see the model's pricing table.

draftboolean

Generate a cheap 480p draft (resolution must be 480p or omitted when true — any other value is rejected). Finalize the draft you keep at 1080p by calling this same endpoint again with draft_request_id set to this request's request_id.

draft_request_idstring nullable

Finalize an earlier draft (submitted with draft=true) into a full 1080p render. Set to that draft's request_id; prompt/references/duration/seed are ignored and reused from the draft instead. resolution must be 1080p or omitted and draft must not be true (rejected otherwise); the draft must be completed and at most 7 days old.

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 2 revisions of this API.