Generate Images with KOLORS

April 24, 2025 (February 9, 2026)

Table of contents

  1. Model Support Matrix
  2. Request Headers
  3. Request Body
    1. v3 Parameters
    2. v3 Aspect Ratios
    3. v2.1 Reference Parameters
    4. Scheduler Parameters
  4. Responses
  5. Model
  6. Examples
  7. Try It

This endpoint generates images using Kling’s KOLORS. It supports KOLORS v3.0 for text-to-image with reference images, and KOLORS v2.1 for text-to-image with face, subject, and restyle reference workflows.

Note: KOLORS v2.0 and v1.5 have been retired by Kling from the website. Their features (restyle, face, subject) are now available under v2.1. The legacy versions are still accepted for backwards compatibility.

Model Support Matrix
Feature v3.0 v2.1
Text-to-image ✅ ✅
Reference images (image_1-image_10) ✅ (up to 10) ❌
Face reference (reference: face) ❌ ✅
Subject reference (reference: subject) ❌ ✅
Restyle (reference: restyle) ❌ ✅
resolution 1k, 2k (default) 1k, 2k (default, text-to-image only)
aspect_ratio default 16:9 16:9
imageCount default 2 1
aspect_ratio: auto ✅ (with images only) ❌

https://api.useapi.net/v1/kling/images/kolors

Request Headers 
Authorization: Bearer {API token}
Content-Type: application/json
# Alternatively you can use multipart/form-data
# Content-Type: multipart/form-data
Request Body 
{
  "email": "[email protected]",
  "prompt": "A woman @image_1 dancing elegantly in a ballroom",
  "version": "kling-v3-0",
  "resolution": "2k",
  "aspect_ratio": "3:4",
  "imageCount": 2,
  "image_1": "https://s21-kling.klingai.com/ai-platform/xxx/xxx.jpg"
}

  • email is optional when only one account configured.
    However, if you have multiple accounts configured, this parameter becomes required.

  • prompt is required, the text description of the image to generate. Maximum length: 2500 characters. For v3, use @image_1, @image_2, etc. to reference images in your prompt.

  • version is optional, the KOLORS model version to use. Supported values: kling-v3-0 (default), kling-v2-1. Legacy (retired): kling-v1-5, kling-v1-6, kling-v2-0 — still accepted for backwards compatibility.

  • resolution is optional, the resolution of the generated image. Supported values: 1k, 2k (default). Only available for v3.0 and v2.1 text-to-image (reference: none). Not supported by subject/face/restyle.

v3 Parameters
  • image_1 through image_10 are optional (v3 only), URLs of reference images. You can upload images using POST /assets. Reference in prompt using @image_1, @image_2, etc.

Note: v3 does not support reference, imageReference, faceStrength, subjectStrength, or faceNo parameters.

v3 Aspect Ratios

When using version: kling-v3-0, the supported aspect ratios are: 9:16, 2:3, 3:4, 1:1, 4:3, 3:2, 16:9 (default), 21:9, auto (with images only).

v2.1 Reference Parameters
  • reference is optional, the type of reference to use (v2.1). Supported values:
    • none (default) — text-to-image
    • subject — subject similarity reference
    • face — face similarity reference
    • restyle — style transfer from reference image

  • imageReference is required if reference is not none, the URL of the reference image. You can upload images using POST /assets and use the returned URL here.

  • aspect_ratio is optional, the aspect ratio of the generated image. Not supported by restyle reference type. Supported values: 1:1, 16:9 (default), 4:3, 3:2, 2:3, 3:4, 9:16, 21:9.

  • imageCount is optional, the number of images to generate. Range: 1 to 9. Default: 1 (v3 default: 2).

  • faceStrength is optional, the strength of face similarity for both face and subject reference types. Range: 1 to 100. Default: 65.

  • subjectStrength is optional, the strength of subject similarity for subject reference type. Range: 1 to 100. Default: 50.

  • faceNo is optional, the index of the face to use in multi-face images for face reference type. Default: 1. You can use POST /images/recognize-faces to detect faces in an image.
Scheduler Parameters

  • maxJobs is optional, range from 1 to 50. Specifies the maximum number of concurrent jobs.

  • replyUrl is optional, a callback URL to receive generation progress and result. See GET /tasks/task_id for response model.

  • replyRef is optional, a reference identifier for the callback.

Responses

  • 200 OK

    {
  "task": {
    "id": 123456789,
    "userId": 12345,
    "type": "mmu_img2img_aiweb",
    "scene": "NORMAL_CREATION",
    "status": 5,
    "status_name": "submitted",
    "status_final": false,
    "taskInfo": {
      "type": "mmu_img2img_aiweb",
      "inputs": [
        {
          "name": "input",
          "inputType": "URL",
          "token": null,
          "blobStorage": null,
          "url": "https://example.com/face.jpg",
          "cover": null,
          "fromWorkId": null
        },
        {
          "name": "feature",
          "inputType": "URL",
          "token": null,
          "blobStorage": null,
          "url": "https://s21-kling.klingai.com/....jpg",
          "cover": null,
          "fromWorkId": null
        }
      ],
      "arguments": [
        {
          "name": "prompt",
          "value": "Portrait of a woman with blue eyes, detailed, photorealistic"
        },
        {
          "name": "aspect_ratio",
          "value": "16:9"
        },
        {
          "name": "imageCount",
          "value": "1"
        },
        {
          "name": "kolors_version",
          "value": "2.1"
        },
        {
          "name": "fidelity",
          "value": "0.65"
        },
        {
          "name": "style",
          "value": "默认"
        },
        {
          "name": "faceBound",
          "value": "{\"x\":120,\"y\":80,\"width\":200,\"height\":240}"
        },
        {
          "name": "referenceType",
          "value": "mmu_img2img_aiweb_v15_character"
        },
        {
          "name": "biz",
          "value": "klingai"
        }
      ],
      "extraArgs": {},
      "callbackPayloads": [
        {
          "name": "face_count",
          "value": "1"
        },
        {
          "name": "referenceImageWidth",
          "value": "724"
        },
        {
          "name": "referenceImageHeight",
          "value": "1268"
        }
      ],
      "scene": "NORMAL_CREATION"
    },
    "favored": false,
    "deleted": false,
    "viewed": false,
    "createTime": 1745376611075,
    "updateTime": 1745376611075
  },
  "works": [],
  "status": 5,
  "status_name": "submitted",
  "status_final": false,
  "message": "",
  "limitation": {
    "type": "mmu_img2img_aiweb",
    "remaining": 10000,
    "limit": 10000
  },
  "userPoints": {
    "points": [],
    "total": 0
  },
  "userTickets": {
    "ticket": []
  },
  "editProject": null
}

  • 400 Bad Request

    {
  "error": "reference \"face\" does not support subjectStrength"
}

  • 401 Unauthorized

    {
  "error": "Unauthorized",
  "code": 401
}

  • 404 Not Found

    Kling was unable to locate one of the referenced assets. Make sure to use POST /assets to upload assets.

    {
    "error": "Sorry, the requested resource was not found (VALID.ResourceNotFound)",
    "message": "Not Found"
}

  • 500 Internal Server Error

    Kling uses a 500 response to indicate moderation and other issues with the input. It may be hard to separate actual 500 errors from moderation errors, so use the error field text and your best judgement to tell them apart, since the message field most often has very generic and perhaps misleading text.

    {
  "error": "The content you uploaded appears to violate the community guidelines. (CM_EXT.POther)",
  "message": "Service busy (CM_EXT.POther)"
}

When successful, the response includes a task ID which can be used to check the status using GET /tasks/task_id.

Model 
{ // TypeScript, all fields are optional
    task: {
        id: number
        userId: number
        type: string
        scene: string
        status: number
        status_name: 'submitted' | 'failed' | 'processing' | 'succeed'
        status_final: boolean
        taskInfo: {
            type: string
            inputs: Array<{
                name: string
                inputType: string
                token: string | null
                blobStorage: any | null
                url: string
                cover: string | null
                fromWorkId: number | null
            }>
            arguments: Array<{
                name: string
                value: string
            }>
            extraArgs: Record<string, any>
            callbackPayloads: any[]
            scene: string
        }
        favored: boolean
        deleted: boolean
        viewed: boolean
        createTime: number
        updateTime: number
        viewTime: number
    }
    works: Array<any>
    status: number
    status_name: 'submitted' | 'failed' | 'processing' | 'succeed'
    status_final: boolean
    message: string
    error: string
    limitation: {
        type: string
        remaining: number
        limit: number
    }
    userPoints: {
        points: Array<{
            orderId: string
            type: string
            amount: number
            balance: number
            startTime: number
            endTime: number
        }>
        total: number
    }
    userTickets: {
        ticket: Array<{
            orderId: string
            type: string
            packageType: string
            amount: number
            balance: number
            startTime: number
            endTime: number
        }>
    }
    editProject: any | null
}
Examples 
  • curl -X POST "https://api.useapi.net/v1/kling/images/kolors" \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer …" \
   -d '{
     "email": "[email protected]",
     "prompt": "Portrait of a woman with blue eyes, detailed, photorealistic",
     "reference": "face",
     "imageReference": "https://example.com/face.jpg",
     "faceStrength": 65,
     "faceNo": 1
   }'

  • const token = "API token";
const email = "Previously configured account email";
const apiUrl = "https://api.useapi.net/v1/kling/images/kolors"; 
const response = await fetch(apiUrl, {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer ${token}`,
  },
  body: JSON.stringify({
    email: email,
    prompt: "Portrait of a woman with blue eyes, detailed, photorealistic",
    reference: "face",
    imageReference: "https://example.com/face.jpg",
    faceStrength: 65,
    faceNo: 1
  })
});
const result = await response.json();
console.log("response", {response, result});

  • import requests
token = "API token"
email = "Previously configured account email"
apiUrl = "https://api.useapi.net/v1/kling/images/kolors"
headers = {
    "Content-Type": "application/json", 
    "Authorization" : f"Bearer {token}"
}
data = {
    "email": email,
    "prompt": "Portrait of a woman with blue eyes, detailed, photorealistic",
    "reference": "face",
    "imageReference": "https://example.com/face.jpg",
    "faceStrength": 65,
    "faceNo": 1
}
response = requests.post(apiUrl, headers=headers, json=data)
print(response, response.json())
Try It