Appearance

Wan 2.7 Exp0622

POST/v1/run

Wan 2.7 Exp0622 generates premium videos from a single input image with native audio, flexible 2–15 second durations, and built-in prompt optimization. Supports 720p and 1080p output.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to alibaba/wan2.7-i2v-exp0622.

Default: alibaba/wan2.7-i2v-exp0622

stringimagerequired

Input image to animate (URL or Base64-encoded string). Maximum file size is 50 MB.

stringpromptrequired

Text prompt to guide the video generation. Built-in prompt optimization is applied automatically.

Optional<string>negative_prompt

Text description of elements to exclude from the generated video.

Optional<integer>duration

Video duration in seconds. Range: 2–15 seconds.

Range: 2 to 15

Default: 5

Optional<string>resolution

Output video resolution.

Allowed values: 720p, 1080p

Default: 1080p

Optional<string>audio

Optional URL of an audio file to include in the generated video.

Optional<boolean>generate_auto

Enable native audio generation in the output video.

Default: true

Optional<boolean>prompt_optimizer

Enable built-in prompt optimization to enhance generation quality.

Default: true

Optional<integer>seed

Random seed. Omit for an auto-generated seed.

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated videos with native audio. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async