Kling 3.0 Omni Pro Reference to Video
/v1/runGenerate a video from multiple reference images and text guidance with Kling 3.0 Omni Pro.
Request body
Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.
Model identifier. Set to kwaivgi/kling-video/3.0/omni/pro/reference-to-video.
Default: kwaivgi/kling-video/3.0/omni/pro/reference-to-video
Take @Element1, @Element2 to reference elements and @Image1, @Image2 to reference images in order.
Additional reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 7 total (elements + reference images + start image).
Video duration in seconds.
Allowed values: 3, 4, 5, 6, 7, 8, 9, 10
Default: 5
Elements (characters/objects) to include in the video. Reference in prompt as @Element1, @Element2, etc. Maximum 7 total (elements + reference images + start image).
The aspect ratio of the generated image.
Allowed values: 16:9, 9:16, 1:1
Response Schema
The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.
Error message if the task failed. Empty on success.
Unique identifier for the generation task.
Model ID used for the prediction.
Array of generated content. Empty when status is not completed.
Status of the task: pending, running, completed, failed, or timeout.
Allowed values: pending, running, completed, failed, timeout
Model capabilities
Capabilities declared by the model registry.
Default: image-to-video
Execution mode declared by the model registry.
Default: async

