Omni Video (Beta)
beta CometAPI Omni Video 엔드포인트(POST /kling/v1/videos/omni-video)를 통해 Kling O1 비디오를 생성하고 Omni Query로 작업 상태를 추적합니다.
입력 모드 선택
- 텍스트-투-비디오:
prompt,mode,aspect_ratio,duration을 전송합니다. - 이미지 참조 생성:
image_list를 추가합니다. - 요소 안내 생성:
element_list를 추가합니다. - 비디오 변환:
refer_type: base와 함께video_list를 추가합니다.
기간 및 종횡비
| Setting | Supported values | Default | Boundary behavior |
|---|---|---|---|
duration for text or first-frame video | 5, 10 | 5 | 두 개의 고정 생성 길이 중 하나를 사용합니다. |
duration with reference video input | input video length from 3 to 10 seconds | input length | 생성된 duration은 기준 비디오를 따르며 요청 값은 무시됩니다. |
aspect_ratio | 16:9, 9:16, 1:1 | 16:9 | 첫 프레임 이미지나 기준 비디오가 프레임을 제어하지 않을 때 필요합니다. |
mode | std, pro | pro | pro는 Omni Video의 기본값입니다. |
size 필드를 제공하지 않습니다. aspect_ratio를 프레임 형태 요청으로 간주하세요. 16:9 텍스트-투-비디오 요청은 풀 HD 1920x1080으로 렌더링될 수 있습니다.
작업 흐름
Omni 작업 폴링
인증
Bearer token authentication. Use your CometAPI key.
헤더
Content type of the request body.
본문
Text prompt describing the desired video. Max 2500 characters. Reference images or elements inline using <<<image_1>>>, <<<element_1>>>, <<<video_1>>> syntax.
Model to use for Omni Video. Use kling-video-o1 for this endpoint.
Reference images for the generation. Each entry can optionally include a type field set to first_frame or end_frame to pin the image as the video's start or end frame. Accepts URLs or Base64 strings. Formats: JPG, JPEG, PNG. Max 10 MB per image, minimum 300 px per side, aspect ratio 1:2.5-2.5:1. When used with reference videos, image + element count must not exceed 4; without reference videos, the limit is 7.
Pre-registered element references by ID. Combined with images, the total count must not exceed 4 (with reference video) or 7 (without).
Generation mode. std (standard, faster and more cost-effective) or pro (professional, higher quality output). The default is pro.
Aspect ratio request for beta Kling Omni generation. The endpoint does not expose an exact size field; a 16:9 text-to-video request can render as 1920x1080.
Video length in seconds. Values: 3-10. Text-to-video and first-frame-to-video only support 5 and 10. When editing an existing video, duration matches the input and this parameter is ignored.
Reference video for style transfer or the base video to edit. Use refer_type to distinguish: feature for style reference, base for the video to modify. Set keep_original_sound to yes or no to control audio retention. Only MP4/MOV, 3-10 seconds, 720-2160 px, 24-60 fps, max 200 MB. Only one video is accepted.
Webhook URL for task status notifications. The server sends a callback when the task status changes.
Optional user-defined task ID for your own tracking. Does not replace the system-generated task ID. Must be unique per account.
응답
Success
The response is of type object.