curl --request POST \
  --url https://api.modellix.ai/api/v1/kling/kling-v2.1-mi2i \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "subject_images": [
    "https://example.com/subject1.jpg",
    "https://example.com/subject2.jpg",
    "https://example.com/subject3.jpg"
  ],
  "prompt": "Three people collaborating in a modern workspace",
  "aspect_ratio": "21:9",
  "n": 3
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-mi2i-stu901",
    "model_id": "model-123",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-mi2i-stu901"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: parameter 'image' is required"
}

{
  "code": 401,
  "message": "Authentication failed: invalid API key"
}

{
  "code": 429,
  "message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}

{
  "code": 500,
  "message": "Internal server error"
}

Kling V2.1 MI2I

[Core Function] Kling V2.1 MI2I is an older generation image-to-image editing model. [Strengths] Offered improved multi-subject tracking and better texture details over V1. Maintained for backward compatibility. [Best For] Existing legacy integrations and workflows that strictly depend on this specific model version’s quirks. [Limitations] Do NOT use this for new creations. It is a legacy model maintained for backward compatibility. [Routing] Only use if explicitly requested; otherwise use Kling V3 I2I.

POST

kling

kling-v2.1-mi2i

curl --request POST \
  --url https://api.modellix.ai/api/v1/kling/kling-v2.1-mi2i \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "subject_images": [
    "https://example.com/subject1.jpg",
    "https://example.com/subject2.jpg",
    "https://example.com/subject3.jpg"
  ],
  "prompt": "Three people collaborating in a modern workspace",
  "aspect_ratio": "21:9",
  "n": 3
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-mi2i-stu901",
    "model_id": "model-123",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-mi2i-stu901"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: parameter 'image' is required"
}

{
  "code": 401,
  "message": "Authentication failed: invalid API key"
}

{
  "code": 429,
  "message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}

{
  "code": 500,
  "message": "Internal server error"
}

Authorizations

Authorization

string

header

required

API Key authentication. Format: Bearer YOUR_API_KEY.

Body

application/json

Note: All parameters are optional, but at least one of prompt, subject_images, scene_image, or style_image should be provided. This model does NOT support: negative_prompt, resolution, image, image_reference, image_fidelity, or human_fidelity parameters.

prompt

string

Image description text, supports Chinese and English. Optional but recommended for better results

Required string length: 1 - 2500

Example:

"Family gathering in an elegant dining room"

subject_images

string[]

List of subject image URLs or Base64 strings. Simplified flattened parameter. Minimum 1 image, maximum 4 images

Required array length: 1 - 4 elements

Subject image URL or Base64 encoded data

Minimum string length: 1

Example:

[
  "https://example.com/person1.jpg",
  "https://example.com/person2.jpg",
  "https://example.com/person3.jpg"
]

scene_image

string

Scene reference image (Base64 encoded or URL). Used for scene replacement. Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB

Minimum string length: 1

Example:

"https://example.com/dining-room.jpg"

style_image

string

Style reference image (Base64 encoded or URL). Used for style transfer. Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB

Minimum string length: 1

Example:

"https://example.com/elegant-style.jpg"

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:

"3:2"

integer

default:1

Number of images to generate per request

Required range: 1 <= x <= 9

Example:

1

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.

Show child attributes

Kling v2 1 master t2v Kling v2 1 t2i