Wan Text to Video
Applies to Wan series text-to-video models. The platform currently supports Ali wan2.7-t2v. After submitting a task, query its status via GET /v1/videos/{task_id}.
Public fields: model, prompt, seconds, size, prompt_extend, watermark, seed, negative_prompt.
Authorizations
Pass Authorization: Bearer <token> in the request header.
Body
Model name. Available value: wan2.7-t2v.
wan2.7-t2v Text prompt describing the desired video content and visual characteristics. Supports Chinese and English; each character or letter counts as one. Excess characters are automatically truncated.
wan2.7-t2v: up to 5000 characters.
Important: seconds directly affects cost. Confirm the model pricing before calling.
Video duration in seconds.
wan2.7-t2v: range [2, 15]. Default: 5.
2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 Important: size directly affects cost. Confirm the model pricing before calling.
Output video resolution tier, controlling video clarity (total pixels).
wan2.7-t2v: available values 720P, 1080P. Default: 1080P.
720P, 1080P Whether to enable intelligent prompt rewriting. When enabled, a large language model rewrites the input prompt intelligently, significantly improving results for short prompts but increasing processing time.
true(default): enable intelligent rewriting.false: disable intelligent rewriting.
Whether to add a watermark to the video. The watermark is positioned at the bottom-right corner with the text 'AI生成'.
false(default): no watermark.true: add watermark.
Random seed, range [0, 2147483647]. If not specified, the system automatically generates a random seed. To improve reproducibility of generation results, it is recommended to fix the seed value.
Note: Due to the probabilistic nature of model generation, the same seed does not guarantee identical results every time.
Negative prompt describing content you do not want to see in the video. Limits unwanted visual elements. Supports Chinese and English, up to 500 characters.
Example: low resolution, error, worst quality, low quality, deformed, extra fingers, bad proportions, etc.
Response
Submitted successfully. Returns a video task object.
Unique task identifier.
Task ID (same as id).
"video"
Model name used.
Task status.
pending, queued, running, succeeded, failed, cancelled Task progress (percentage).
Creation time as a Unix timestamp (seconds).