Create an Omni video generation task. The Omni model can achieve various capabilities through Prompt with elements, images, videos, and other content.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Model name
kling-v3-omni "kling-v3-omni"
Text prompt for video generation. Supports positive and negative descriptions. Use <<<element_1>>>, <<<image_1>>>, <<<video_1>>> to reference elements/images/videos. Required when multi_shot is false.
2500"A cat walking gracefully across a sunlit garden"
Video generation mode. std: Standard mode (cost-effective). pro: Professional mode (higher quality).
std, pro "pro"
Aspect ratio of generated video (width:height). Required when NOT using first-frame reference or video editing.
16:9, 9:16, 1:1 "16:9"
Video duration in seconds (3–15).
3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 "5"
Whether to generate multi-shot video. When true, prompt is ignored; use multi_prompt instead.
Storyboard method. Required when multi_shot is true.
customize Storyboard information (1–6 shots). Required when multi_shot is true and shot_type is customize.
Reference image list. Supports first/end frame, scene, style references. Formats .jpg/.jpeg/.png, max 10MB, min 300px, aspect ratio 1:2.5–2.5:1.
Reference element list from Kling element library.
Reference video list. MP4/MOV only, ≥3s, 720px–2160px, 24–60fps, max 200MB.
Whether to generate sound with the video. Must be off when video_list is present.
on, off Watermark configuration
Callback URL for task status notifications
Custom task ID. Must be unique per account.
Task created successfully