Generate Images with Omni

December 10, 2025 (November 19, 2026)

Table of contents

  1. Version Comparison
  2. Request Headers
  3. Request Body
    1. Reference Images
    2. Saved Elements
    3. Prompt Reference Syntax
    4. Presets (v4)
    5. Scheduler Parameters
  4. Responses
  5. Model
  6. Examples
  7. Try It

This endpoint generates images with Kling Image 4.0 (v4), Omni 3.0 (v3) and Omni O1 (o1), from a prompt and up to 10 reference images and saved elements named in it. Kling Image 4.0 adds 8K images, Series Mode from the prompt alone, style, tone and font presets in the prompt, and two design skills that each make one long page image: a product detail page from a product photo, and a web page design.

Version Comparison
Feature v4 (Kling Image 4.0) v3 O1
Resolution 2k, 4k (VIP), 8k (VIP) 1k, 2k, 4k (VIP) 1k, 2k
Default resolution 2k 1k 1k
Default aspect_ratio auto auto 16:9
auto aspect ratio Yes Yes No
story_mode (Series Mode) Yes 2 to 10 images, with or without references Yes with a reference No
Style, tone and font presets Yes No No
skill: product detail page, web design Yes No No
Credits per image 4 at 2K, 6 at 4K, 10 at 8K 1 at 1K, 2 at 2K, 4 at 4K 1

Prices for every plan are in the Kling price calculator.

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

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": "@tone:Morandi_Palette A woman @image_1 dancing elegantly in a ballroom",
  "omni_version": "v4",
  "resolution": "4k",
  "aspect_ratio": "16:9",
  "imageCount": 2,
  "image_1": "https://s21-kling.klingai.com/ai-platform/xxx/xxx.jpg"
}
  • email is optional. Leave it out and the job goes to one of your accounts that has a free job slot, picked at random. Each account runs at most its maxJobs jobs at once, and GET scheduler/available shows the free slots. If no account has a free slot, the response is 429.
    Pass email to run the job on that account (429 if it is busy). Uploaded files, elements, voices, avatars and earlier tasks belong to one account, so pass the email of the account they came from.
    With more than one account, reading the task with GET tasks/task_id needs its account’s email. The response’s task.userId is that account’s session.userId in GET accounts, and GET scheduler lists each running task with its email.

  • prompt is required, the text description of the image to generate. Maximum length: 1700 characters. Use @image_1, @image_2, etc. to reference images in your prompt. Use @element_1, @element_2, etc. (or @object_1, etc.) to reference saved elements. With v4 the prompt can also name presets: @style:<id>, @tone:<id> and @font:<id>. Put text that should appear in the image in quotation marks.

  • omni_version is optional, the Omni model version to use. Supported values: o1, v3 (default), v4 (Kling Image 4.0).

  • resolution is optional, the resolution of the generated image. v4: 2k (default), 4k (VIP required), 8k (VIP required). With a skill: 1k or 2k (default). v3: 1k (default), 2k, 4k (VIP required). o1: 1k (default), 2k.

  • aspect_ratio is optional, the aspect ratio of the generated image. Supported values: auto (v4 and v3), 16:9 (default for O1), 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9. v4 and v3 default to auto. auto is NOT available for O1. Not used with a skill.

  • imageCount is optional, the number of images to generate. Range: 1 to 10. Default: 1. Up to 9, and up to 10 only in a v4 Series Mode: with v4 and story_mode it is 2 to 10, or leave it out and Kling decides how many images the series needs (each image is charged).

  • story_mode is optional, enables Series Mode for coherent multi-image generation (v4 and v3). A Series Mode generates a coherent set of images, like the panels of a story, rather than independent images. v3 requires at least one reference image or element. v4 also makes a series from the prompt alone. Default: false.

  • skill is optional, a Kling Image 4.0 design skill (v4 only). It makes one long page image instead of imageCount images. Supported values: product_detail, web_design.
    • product_detail makes a product detail page from your product photo in image_1, which is required.
    • web_design makes a web page design. image_1 is optional, a style reference for the page. Kling writes the page’s text in Chinese unless the prompt names the language, so end the prompt with, for example, “All text on the page in English.”

    With a skill, resolution is 1k or 2k (default) and imageCount is 1. aspect_ratio, story_mode, unlimited, image_2 to image_10, elements and presets are not used.

  • length is optional, the length of the product detail page (skill product_detail only). Supported values: short (2 to 5 sections), medium (default, 6 to 10 sections), long (11 to 18 sections).

  • unlimited is optional, enables unlimited generation mode for eligible Pro and above accounts (subscribed prior December 15, 2025). Default: false.
Reference Images
  • image_1 through image_10 are optional, URLs of reference images. You can upload images using POST /assets. Reference in prompt using @image_1, @image_2, etc.
Saved Elements
  • element_1 through element_10 are optional, IDs of saved elements. Create elements using POST /elements. Reference in prompt using @element_1 or @object_1, etc.

Note: Images and elements share the same pool of 10 slots. Combined total cannot exceed 10.

Prompt Reference Syntax
Input Type Prompt Syntax Example
Images @image_1, @image_2, … "A woman @image_1 in a ballroom"
Elements @element_1 or @object_1, … "Character @element_1 sitting..."
Style preset (v4) @style:<id> "@style:3d_cartoon_pro a fox on a skateboard"
Tone preset (v4) @tone:<id> "@tone:Nostalgic_Wuxia a swordsman in the rain"
Font preset (v4) @font:<id> before the quoted text "a cafe sign that reads @font:elegant_brush_hand \"Jade Dragon\""
Presets (v4)

Kling Image 4.0 has three kinds of presets you can name in the prompt. GET images/presets lists the current ones with their ids and sample images.

  • A style (@style:<id>) sets the look of the image: 3D, 2D, material craft or photography styles. It is sent to Kling as the style’s name, the same as writing that name in the prompt.
  • A tone (@tone:<id>) applies one of Kling’s color and lighting presets: director styles, camera simulation, classic styles, advanced color and visual lighting.
  • A font (@font:<id>) sets the lettering of the quoted text that follows it. Fonts come in English, Japanese, Korean and Chinese.

An unknown id is refused with 400, before anything is sent to Kling.

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_omni_image",
        "scene": "NORMAL_CREATION",
        "status": 5,
        "status_name": "submitted",
        "status_final": false,
        "taskInfo": {
          "type": "mmu_omni_image",
          "inputs": [
            {
              "name": "image_1",
              "inputType": "URL",
              "token": null,
              "blobStorage": null,
              "url": "https://s21-kling.klingai.com/ai-platform/xxx/xxx.jpg",
              "cover": null,
              "fromWorkId": null
            }
          ],
          "arguments": [
            {
              "name": "prompt",
              "value": "A woman Image1 dancing elegantly in a ballroom"
            },
            {
              "name": "rich_prompt",
              "value": "A woman <<<image_1>>> dancing elegantly in a ballroom"
            },
            {
              "name": "kolors_version",
              "value": "3.0-omni"
            },
            {
              "name": "img_resolution",
              "value": "2k"
            },
            {
              "name": "aspect_ratio",
              "value": "16:9"
            },
            {
              "name": "imageCount",
              "value": "1"
            }
          ],
          "extraArgs": {},
          "callbackPayloads": [],
          "scene": "NORMAL_CREATION"
        },
        "favored": false,
        "deleted": false,
        "viewed": false,
        "createTime": 1733836800000,
        "updateTime": 1733836800000
      },
      "works": [],
      "status": 5,
      "status_name": "submitted",
      "status_final": false,
      "message": "",
      "limitation": {
        "type": "mmu_omni_image",
        "remaining": 10000,
        "limit": 10000
      },
      "userPoints": {
        "points": [],
        "total": 0
      },
      "userTickets": {
        "ticket": []
      },
      "editProject": null
    }
    
  • 400 Bad Request

    The parameters are invalid. When Kling refuses the submitted parameters, error carries Kling’s own message.

    {
      "error": "<error message>"
    }
    
  • 401 Unauthorized

    {
      "error": "Unauthorized",
      "code": 401
    }
    
  • 404 Not Found

    {
      "error": "<error message>"
    }
    
  • 412 Precondition Failed

    The Kling account named in error is out of credits, and Kling did not create a task. Add credits or upgrade the plan of that account on kling.ai, or send the job to another account with email. message keeps Kling’s own text.

    {
      "error": "Kling account [email protected] is out of credits: Credit are insufficient, you can upgrade your membership or purchase credit. (TASK.PointNotEnough)",
      "message": "积分消费失败 (TASK.PointNotEnough)"
    }
    
  • 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. A skill task has task.type design_ecommerce_detail (product detail page) or design_web_design (web design) and makes one tall image, for example 2048 x 13084 pixels for a 2K web design.

Model

The new task, with its task.id and status_name: poll it with GET /tasks/task_id until status_final is true.

The task record, field by field
{ // 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
  • # Using reference image
    curl -X POST "https://api.useapi.net/v1/kling/images/omni" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer ..." \
       -d '{
         "email": "[email protected]",
         "prompt": "A woman @image_1 dancing elegantly in a ballroom",
         "resolution": "2k",
         "aspect_ratio": "16:9",
         "image_1": "https://s21-kling.klingai.com/ai-platform/xxx/xxx.jpg"
       }'
    
    # Using story_mode (Series Mode) for coherent multi-image generation
    curl -X POST "https://api.useapi.net/v1/kling/images/omni" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer ..." \
       -d '{
         "email": "[email protected]",
         "prompt": "A series of @image_1 in different seasons",
         "resolution": "2k",
         "aspect_ratio": "16:9",
         "imageCount": 3,
         "story_mode": true,
         "image_1": "https://s21-kling.klingai.com/ai-platform/xxx/xxx.jpg"
       }'
    
    # Using saved element
    curl -X POST "https://api.useapi.net/v1/kling/images/omni" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer ..." \
       -d '{
         "email": "[email protected]",
         "prompt": "Character @element_1 in a garden setting",
         "resolution": "2k",
         "aspect_ratio": "16:9",
         "element_1": "u_123456789012345"
       }'
    
    # Kling Image 4.0 at 8K
    curl -X POST "https://api.useapi.net/v1/kling/images/omni" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer ..." \
       -d '{
         "prompt": "Macro photo of a dew-covered spider web at sunrise, every droplet catching the light",
         "omni_version": "v4",
         "resolution": "8k",
         "aspect_ratio": "16:9"
       }'
    
    # Kling Image 4.0 Series Mode from the prompt alone, Kling decides how many images
    curl -X POST "https://api.useapi.net/v1/kling/images/omni" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer ..." \
       -d '{
         "prompt": "A four-panel story: a paper boat sails down a rainy city gutter, reaches a river and finally the sea",
         "omni_version": "v4",
         "story_mode": true
       }'
    
    # Kling Image 4.0 with a tone preset and a font preset (ids from GET images/presets)
    curl -X POST "https://api.useapi.net/v1/kling/images/omni" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer ..." \
       -d '{
         "prompt": "@tone:Morandi_Palette A small tea house at dusk with a wooden sign that reads @font:elegant_brush_hand \"Jade Dragon\"",
         "omni_version": "v4"
       }'
    
    # Kling Image 4.0 skill: a long product detail page from a product photo
    curl -X POST "https://api.useapi.net/v1/kling/images/omni" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer ..." \
       -d '{
         "prompt": "Insulated steel water bottle: keeps drinks cold 24 hours, leak-proof lid, fits car cup holders",
         "omni_version": "v4",
         "skill": "product_detail",
         "length": "short",
         "image_1": "https://s21-kling.klingai.com/ai-platform/xxx/xxx.jpg"
       }'
    
    # Kling Image 4.0 skill: a web page design
    curl -X POST "https://api.useapi.net/v1/kling/images/omni" \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer ..." \
       -d '{
         "prompt": "Landing page for a small-batch coffee roaster: warm browns, serif headlines, a subscription offer",
         "omni_version": "v4",
         "skill": "web_design"
       }'
    
  • const token = "API token";
    const email = "Previously configured account email";
    const apiUrl = "https://api.useapi.net/v1/kling/images/omni";
    const response = await fetch(apiUrl, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        "Authorization": `Bearer ${token}`,
      },
      body: JSON.stringify({
        email: email,
        prompt: "@tone:Morandi_Palette Character @element_1 in a garden setting",
        omni_version: "v4",
        resolution: "4k",
        aspect_ratio: "16:9",
        element_1: "u_123456789012345"
      })
    });
    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/omni"
    headers = {
        "Content-Type": "application/json",
        "Authorization" : f"Bearer {token}"
    }
    data = {
        "email": email,
        "prompt": "@tone:Morandi_Palette Character @element_1 in a garden setting",
        "omni_version": "v4",
        "resolution": "4k",
        "aspect_ratio": "16:9",
        "element_1": "u_123456789012345"
    }
    response = requests.post(apiUrl, headers=headers, json=data)
    print(response, response.json())
    
Try It