Skip to main content
POST
/
kling
/
kling-v3-i2i
curl --request POST \
  --url https://api.modellix.ai/api/v1/kling/kling-v3-i2i \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "Restyle the photo as a cinematic cyberpunk portrait",
  "image": "https://example.com/portrait.jpg"
}
'
{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-v3-i2i-123",
    "model_id": "model-123",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-v3-i2i-123"
    }
  }
}

Authorizations

​
Authorization
string
header
required

API Key authentication. Format: Bearer YOUR_API_KEY.

Body

application/json
​
prompt
string
required

Image editing prompt, supports Chinese and English

Required string length: 1 - 2500
Example:

"Restyle the photo as a cinematic cyberpunk portrait"

​
image
string
required

Reference image (URL or Base64 encoded). Kling V3 image-to-image requires one input image.

Minimum string length: 1
Example:

"https://example.com/portrait.jpg"

​
n
integer
default:1

Number of images to generate per request

Required range: 1 <= x <= 9
Example:

2

​
aspect_ratio
enum<string>
default:16:9

Image aspect ratio

Available options:
16:9,
9:16,
1:1,
4:3,
3:4,
3:2,
2:3,
21:9
Example:

"3:4"

​
resolution
enum<string>
default:1k

Output resolution. Kling V3 supports both 1K and 2K output.

Available options:
1k,
2k
Example:

"2k"

Response

Task submitted successfully

​
code
integer
required

Response code, 0 indicates success

Example:

0

​
message
string
required

Response message

Example:

"success"

​
data
object
required

Detailed data about the submitted asynchronous task.