Skip to main content
POST
/
kling
/
v1
/
images
/
omni-image
cURL
curl https://api.cometapi.com/kling/v1/images/omni-image \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-v3-omni",
    "prompt": "Using <<<image_1>>> as a visual reference, generate a cinematic portrait of a product designer in a sunlit studio.",
    "image_list": [
      {
        "image": "https://your-image-host/reference.png"
      }
    ],
    "resolution": "2k",
    "result_type": "single",
    "n": 1,
    "aspect_ratio": "3:2"
  }'
{
  "code": 0,
  "message": "SUCCEED",
  "data": {
    "task_id": "<task_id>",
    "task_info": {
      "external_task_id": null
    },
    "task_status": "submitted",
    "created_at": 1782436687105,
    "updated_at": 1782436687105
  }
}
Use this endpoint to create an asynchronous Kling Omni Image task through CometAPI. The create request returns a task_id; use Get a Kling Omni image task to poll the task until the generated image URLs are available.
For the complete provider parameter reference, see the Kling Image O1 documentation.

​
Choose the request shape

  • Single-image generation: send prompt, image_list, resolution, result_type: single, n, and aspect_ratio
  • Image-series generation: send prompt, image_list, result_type: series, series_amount, and aspect_ratio
  • Element-referenced generation: send element_list only when you already have valid Kling element IDs from a compatible element workflow
  • Model ID: omit model_name to use kling-image-o1, or send kling-v3-omni for Kling 3.0 Omni Image requests
Reference images use image_list items with an image field. The prompt can cite them by index, such as <<<image_1>>> for the first item and <<<image_2>>> for the second item.

​
Task flow

1

Create the task

Submit POST /kling/v1/images/omni-image and store the returned data.task_id.
2

Query the task

Poll GET /kling/v1/images/omni-image/ until data.task_status is succeed or failed.
3

Persist the images

When the task succeeds, copy data.task_result.images[].url into your own storage if you need durable access.
For the full response schema and polling examples, see Get a Kling Omni image task. The following short example polls one task until it reaches a terminal state: 
TASK_ID="<task_id>"

while true; do
  STATUS=$(curl -s "https://api.cometapi.com/kling/v1/images/omni-image/$TASK_ID" \
    -H "Authorization: Bearer $COMETAPI_KEY" \
    | python3 -c "import json,sys; print(json.load(sys.stdin)['data']['task_status'])")

  echo "status: $STATUS"
  case "$STATUS" in succeed | failed) break;; esac
  sleep 30
done

​
Result fields

Successful query responses return generated images under data.task_result.images. Each item can include:
FieldDescription
indexPosition of the generated image in the task result.
urlGenerated image URL.
watermark_urlWatermarked image URL when watermark output is requested.
Generated asset URLs can expire or be cleared by the provider service. Store the finished images in your own storage layer when your workflow needs long retention.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI API key.

Headers

​
Content-Type
string

Must be application/json.

Body

application/json
​
prompt
string
required

Text prompt for the generated image. The prompt can include positive and negative instructions and can reference images with <<<image_1>>>, <<<image_2>>>, and matching indexes from image_list. Maximum length is 2,500 characters.

​
model_name
enum<string>
default:kling-image-o1

Model ID for this Omni Image request. Omit to use kling-image-o1; use kling-v3-omni for Kling 3.0 Omni Image requests.

Available options:
kling-image-o1,
kling-v3-omni
​
image_list
object[]

Reference images that the prompt can cite with <<<image_1>>>, <<<image_2>>>, and so on. The total number of reference images and reference elements must not exceed 10.

​
element_list
object[]

Reference element IDs that the prompt can cite with <<<element_1>>>, <<<element_2>>>, and so on. Use only element IDs from a compatible Kling element workflow. The total number of reference images and reference elements must not exceed 10.

​
resolution
enum<string>
default:1k

Requested output resolution. Use 1k, 2k, or 4k; omitted requests use 1k.

Available options:
1k,
2k,
4k
​
result_type
enum<string>
default:single

Control whether the task generates independent images or a related image series. When series, n is ignored.

Available options:
single,
series
​
series_amount
enum<integer>
default:4

Number of images to generate when result_type is series. Ignored when result_type is single.

Available options:
2,
3,
4,
5,
6,
7,
8,
9
​
n
integer
default:1

Number of single-image results to generate. Range: 1 to 9. Ignored when result_type is series.

Required range: 1 <= x <= 9
​
aspect_ratio
enum<string>
default:auto

Requested output aspect ratio in width:height format. Use auto to let the provider choose from the prompt and references.

Available options:
16:9,
9:16,
1:1,
4:3,
3:4,
3:2,
2:3,
21:9,
auto
​
watermark_info
object

Watermark options. When enabled is true, the task can return watermarked result URLs in addition to the original result URLs.

​
callback_url
string<uri>

Webhook URL that receives task status notifications when the task status changes. Omit this field to poll manually.

​
external_task_id
string

User-defined task ID for your own tracking. It does not replace the system-generated task_id and must be unique per account.

Response

200 - application/json

Task accepted.

​
code
integer
required

Response code. 0 means the task request was accepted.

​
message
string
required

Response message.

​
data
object
required
​
request_id
string

Request identifier returned by CometAPI when present.