Video Omni

Buat video Kling O1 melalui endpoint CometAPI Omni Video (POST /kling/v1/videos/omni-video) dan lacak status task dengan Omni Query.

POST /kling/v1/videos/omni-video

cURL

Default

curl --request POST \
  --url https://api.cometapi.com/kling/v1/videos/omni-video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "The boy in <<<image_1>>> is wearing <<<element_1>>> and, together with the girl in <<<image_2>>>, sits side by side in <<<element_2>>>, playfully and intimately chatting, close-up shot."
}
'

200

{}

Gunakan endpoint ini untuk workflow Kling Omni, termasuk text-to-video biasa, generasi dengan referensi gambar, dan alur transformasi video.

​

Pilih mode input

• Text-to-video: kirim prompt, mode, aspect_ratio, dan duration
• Generasi dengan referensi gambar: tambahkan image_list
• Generasi dengan panduan elemen: tambahkan element_list
• Transformasi video: tambahkan video_list dengan refer_type: base

​

Alur task

1. Buat task Omni

   Kirim request dan simpan task_id yang dikembalikan.

2. Poll task Omni

   Lanjutkan dengan Omni Query sampai task selesai.

3. Simpan video yang sudah selesai

   Pindahkan URL MP4 yang dikembalikan ke storage Anda sendiri jika memerlukan akses yang tahan lama.

Validasi langsung pada 2026-03-12 mengonfirmasi bahwa request text-to-video minimal mengembalikan task_status: submitted, dan Omni query lanjutan kemudian mencapai SUCCESS dengan URL MP4 final.

Otorisasi

Authorization · string · header · wajib

Bearer token authentication. Use your CometAPI key.

Header

Content-Type · string

Content type of the request body.

Body

application/json

prompt · string · default: Hello · wajib

Text prompt describing the desired video. Max 2500 characters. Reference images or elements inline using <<<image_1>>>, <<<element_1>>>, <<<video_1>>> syntax.

model_name · string

Model to use. Currently only kling-video-o1 is supported.

image_list · object[]

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.

Show child attributes

element_list · object[]

Pre-registered element references by ID. Combined with images, the total count must not exceed 4 (with reference video) or 7 (without).

Show child attributes

mode · string

Generation mode. std (standard, faster and more cost-effective) or pro (professional, higher quality output).

aspect_ratio · string

Output video aspect ratio (width:height). Values: 16:9, 9:16, 1:1. Required when not using a first-frame reference image or video editing.

duration · string

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.

video_list · string[]

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.

callback_url · string

Webhook URL for task status notifications. The server sends a callback when the task status changes.

external_task_id · string

Optional user-defined task ID for your own tracking. Does not replace the system-generated task ID. Must be unique per account.

Respons

200 - application/json

Success

The response is of type object.