Skip to main content
POST
/
kling
/
v1
/
images
/
generations
cURL
curl https://api.cometapi.com/kling/v1/images/generations \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model_name": "kling-v3",
  "prompt": "A paper boat floating on calm water at sunrise",
  "n": 1,
  "aspect_ratio": "1:1"
}'
{
  "code": 123,
  "message": "<string>",
  "data": {
    "task_id": "<string>",
    "created_at": 123,
    "updated_at": 123,
    "task_status_msg": "<string>",
    "task_info": {
      "external_task_id": "<string>"
    },
    "task_result": {}
  },
  "request_id": "<string>"
}

​
Image generation

For the complete parameter reference, see the official Kling documentation.
Use this endpoint to create still images through Kling’s image generation API. It supports text-only requests and image-reference requests through the same async task flow.

​
First request

Start with model_name: kling-v3, prompt, n, and aspect_ratio. Add reference images, fidelity controls, or advanced fields only after the first request returns a usable task. Omitting model_name uses a legacy compatibility default, so send kling-v3 explicitly for new integrations.

​
Read the response

Save the returned task_id, then poll the matching Kling image query route until task_status reaches a terminal state. If your workflow needs durable storage, copy the final asset into your own storage layer after generation completes.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Headers

​
Content-Type
string
default:application/json

Must be application/json.

Body

application/json
​
prompt
string
required

Text prompt describing the image to generate. Maximum 2500 characters.

​
model_name
enum<string>
default:kling-v1

Kling image model variant. Use kling-v3 for new requests. Omitting model_name uses the legacy CometAPI route default.

Available options:
kling-v1,
kling-v1-5,
kling-v2,
kling-v2-1,
kling-v3
​
negative_prompt
string

Elements to exclude from the image. Maximum 2500 characters. Not supported when image is provided.

​
image
string

Reference image as a raw Base64 string without a data: prefix, or a public URL. Accepted formats: JPG, JPEG, PNG. Maximum 10 MB, minimum 300x300 px, aspect ratio between 1:2.5 and 2.5:1.

​
image_reference
enum<string>

Reference mode for legacy image-to-image requests when image is provided.

Available options:
subject,
face
​
image_fidelity
number
default:0.5

How closely the output follows the reference image. Range: 0-1. Used by legacy image-reference models.

Required range: 0 <= x <= 1
​
human_fidelity
number
default:0.45

Human-subject fidelity control. Range: 0-1. Used only by legacy subject-reference requests.

Required range: 0 <= x <= 1
​
element_list
object[]

Optional Kling element references. The total count of element references and input images must not exceed 10.

​
resolution
enum<string>
default:1k

Output resolution. Defaults to 1k.

Available options:
1k,
2k
​
n
integer
default:1

Number of images to generate. Range: 1-9.

Required range: 1 <= x <= 9
​
aspect_ratio
enum<string>
default:16:9

Output aspect ratio (width:height).

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

Watermark options.

​
callback_url
string

Webhook URL to receive task status updates when the task completes.

​
external_task_id
string

Optional user-defined task ID for your own tracking. Must be unique per account.

Response

200 - application/json

Task request accepted or an error response returned by the API.

​
code
required

Response code. 0 means the task request was accepted.

​
message
string
required

Response message.

​
data
object
required
​
request_id
string

Request identifier returned when present.