Wan 2.7 Video Continuation
Submit an asynchronous Ali wan2.7-i2v video continuation task.
Use first_clip to specify the initial video clip to continue from, optionally paired with last_frame to guide the continuation toward a target ending frame.
Supported media combinations:
first_clipfirst_clip + last_frame
The prompt field is optional for this capability. size only supports 720P and 1080P. seconds only supports integer strings from 2 to 15. Also supports official fields negative_prompt, prompt_extend, watermark, seed.
Authorizations
Pass Authorization: Bearer <token> in the request header.
Body
Ali wan2.7-i2v model.
wan2.7-i2v Multimodal input field. This scenario allows first_clip and last_frame types. first_clip is required; last_frame is optional.
Optional text prompt. When omitted, generation relies primarily on the input media assets.
Supported output resolution tiers.
720P, 1080P Video duration as a string. Supports integer strings from 2 to 15.
2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 Optional negative prompt describing content you do not want in the video.
Whether to enable intelligent prompt rewriting. Defaults to true.
Whether to add a watermark. Defaults to false.
Random seed. Automatically generated by the system when not provided.
0 <= x <= 2147483647Response
Submitted successfully. Returns an OpenAI-compatible video task object.
Public task ID.
Backward-compatible alias for the public task ID.
"video"
Model name.
Unified video task status.
queued, in_progress, completed, failed, unknown Task progress percentage.
Creation time as a Unix timestamp (seconds).