---
title: Kling IMAGE O1 | Runware Docs
url: https://runware.ai/docs/models/klingai-image-o1
description: High control AI image model for consistent characters
---
# Kling IMAGE O1

![Kling IMAGE O1](https://assets.runware.ai/covers/klingai-image-o1.jpg)

Kling IMAGE O1 is a high control image generation model for stable characters and precise edits. It supports detailed composition control, strong style handling, and localized modifications without structural drift. Ideal for pipelines that need repeatable shots and complex visual continuity.

- **Status**: live
- **ID**: `klingai:kling-image@o1`
- Try in Playground
- **Creator**: Kling AI
- **Release Date**: December 2, 2025
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.028 per run · ~38s per request

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/klingai-image-o1/examples#example-estuary-electronic-music-festival-poster) · 1248×832: `$0.028` (~30s)
- [reference-to-image](https://runware.ai/docs/models/klingai-image-o1/examples#example-lowrider-bicycle-builder-editorial-portrait) · 2k: `$0.028` (~48s)
- [reference-to-image](https://runware.ai/docs/models/klingai-image-o1/examples#example-mobile-library-archive-photo-restoration) · 2k: `$0.028` (~31s)
- [text-to-image](https://runware.ai/docs/models/klingai-image-o1/examples#example-varroa-mite-test-kit-carton) · 1248×832: `$0.028` (~45s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Either provide `inputs.referenceImages`, or specify `width/height`.

---

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.referenceImages` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1K (1:1)` | `1024x1024` |
| `1K (3:2)` | `1248x832` |
| `1K (2:3)` | `832x1248` |
| `1K (4:3)` | `1168x880` |
| `1K (3:4)` | `880x1168` |
| `1K (9:16)` | `768x1360` |
| `1K (16:9)` | `1360x768` |
| `1K (21:9)` | `1552x656` |
| `2K (1:1)` | `2048x2048` |
| `2K (3:2)` | `2496x1664` |
| `2K (2:3)` | `1664x2496` |
| `2K (4:3)` | `2336x1760` |
| `2K (3:4)` | `1760x2336` |
| `2K (9:16)` | `1536x2720` |
| `2K (16:9)` | `2720x1536` |
| `2K (21:9)` | `3104x1312` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/klingai-image-o1#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/klingai-image-o1#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/klingai-image-o1#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/klingai-image-o1#request-outputformat)

- **Type**: `string`
- **Default**: `JPG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/klingai-image-o1#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/klingai-image-o1#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/klingai-image-o1#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/klingai-image-o1#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/klingai-image-o1#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (1 property)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/klingai-image-o1#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

### [ttl](https://runware.ai/docs/models/klingai-image-o1#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/klingai-image-o1#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/klingai-image-o1#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/klingai-image-o1#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `10`

List of reference images (UUID, URL, Data URI, or Base64).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/klingai-image-o1#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `klingai:kling-image@o1`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/klingai-image-o1#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `3`
- **Max**: `2500`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/klingai-image-o1#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.referenceImages is not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/klingai-image-o1#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.referenceImages is not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/klingai-image-o1#request-resolution)

- **Type**: `string`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `1K` `2K`

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/klingai-image-o1#request-advancedfeatures-watermark)

- **Path**: `advancedFeatures.watermark`
- **Type**: `object (6 properties)`

Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both.

**Text watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "© 2025 Company",
    "displayPosition": "bottom-right",
    "opacity": 0.6,
    "fontColor": "#ffffff",
    "bgColor": "#000000"
  }
}
```

**Image watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "image": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "displayPosition": "top-left",
    "opacity": 0.6
  }
}
```

**Tiled watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "PREVIEW",
    "tiled": true,
    "opacity": 0.4,
    "fontColor": "#cccccc"
  }
}
```

#### [text](https://runware.ai/docs/models/klingai-image-o1#request-advancedfeatures-watermark-text)

- **Path**: `advancedFeatures.watermark.text`
- **Type**: `string`
- **Min**: `2`
- **Max**: `32`

Watermark text.

#### [image](https://runware.ai/docs/models/klingai-image-o1#request-advancedfeatures-watermark-image)

- **Path**: `advancedFeatures.watermark.image`
- **Type**: `string`

Watermark image (UUID, URL, Data URI, or Base64).

#### [displayPosition](https://runware.ai/docs/models/klingai-image-o1#request-advancedfeatures-watermark-displayposition)

- **Path**: `advancedFeatures.watermark.displayPosition`
- **Type**: `string`

Watermark position.

**Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled`

#### [opacity](https://runware.ai/docs/models/klingai-image-o1#request-advancedfeatures-watermark-opacity)

- **Path**: `advancedFeatures.watermark.opacity`
- **Type**: `float`
- **Min**: `0.1`
- **Max**: `1`
- **Step**: `0.01`

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/klingai-image-o1#request-advancedfeatures-watermark-fontcolor)

- **Path**: `advancedFeatures.watermark.fontColor`
- **Type**: `string`

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/klingai-image-o1#request-advancedfeatures-watermark-bgcolor)

- **Path**: `advancedFeatures.watermark.bgColor`
- **Type**: `string`

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/klingai-image-o1#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/klingai-image-o1#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/klingai-image-o1#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/klingai-image-o1#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/klingai-image-o1#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/klingai-image-o1#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [NSFWContent](https://runware.ai/docs/models/klingai-image-o1#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/klingai-image-o1#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-image (text-to-image)

![Estuary Electronic Music Festival Poster](https://assets.runware.ai/examples/klingai-image-o1/2dac3b72-0f32-4bb9-9d68-aa1905d51309.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "a29b2cab-1e70-4174-a108-011649c0be0f",
  "model": "klingai:kling-image@o1",
  "positivePrompt": "Finished landscape event poster artwork for TIDELINE, an experimental electronic music and field-recording festival held at a monumental coastal flood barrier. Edge-to-edge flat design, not a photographed poster or mockup. The central image is a stark side-on silhouette of a vast concrete storm-surge gate crossing a tidal estuary at low water; tiny performers with modular synthesizers and hydrophones stand on the maintenance deck, giving an immense sense of scale. Concentric sonar rings, waveform traces, tide-chart lines, and small flocks of shorebirds travel across the composition like musical notation. Bold contemporary screen-print aesthetic combining Dutch modernist graphics, technical maritime diagrams, and underground music-poster energy. Restricted palette of deep navy, safety orange, pale aqua, and warm off-white; rough ink texture, halftone gradients, crisp geometric forms, slight misregistration. Strong directional sunset light casts long angular shadows across reflective mudflats. Asymmetrical composition with generous negative space and an authoritative typographic grid. Large condensed sans-serif headline: “TIDELINE”. Directly beneath: “ESTUARY SOUND FESTIVAL”. Clear event details: “14–16 SEPTEMBER 2026” and “EAST GATE TIDAL BARRIER”. Smaller lineup block: “LINA RAINE • KMRU • LAUREL HALO • CHRIS WATSON • IKONIKA • 12 ENSEMBLE”. Footer line: “LIVE ELECTRONICS • HYDROPHONE WALKS • SPATIAL AUDIO”. Make all lettering clean, correctly spelled, highly legible, and integrated into the poster hierarchy. Sophisticated, atmospheric, industrial, windswept, culturally credible, print-ready festival identity.",
  "width": 1248,
  "height": 832
}
```

---

### text-to-image (text-to-image)

![Varroa Mite Test Kit Carton](https://assets.runware.ai/examples/klingai-image-o1/62427989-3bea-4c66-93ac-5699efde8456.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "a53cd931-b38c-4ba8-9524-ccde283ad058",
  "model": "klingai:kling-image@o1",
  "positivePrompt": "Create a polished packaging design presentation for HIVE/SCAN, a professional field test kit used by beekeepers to detect varroa mites. The clear hero subject is one compact rectangular folding carton, photographed at a three-quarter angle so the front and right side panels are both visible. Place it upright on a seamless pale gray studio surface with ample negative space, a crisp grounding shadow, and hard directional product lighting from the upper left.\n\nDesign the carton in a bold Swiss scientific style: warm off-white uncoated paper stock, safety orange and electric cyan color blocks, precise black rules, modular grid, registration-mark details, small numbered specimen symbols, and one large abstract halftone illustration derived from the oval form and eight legs of a varroa mite. Keep the visual language clinical, contemporary, and trustworthy rather than rustic. No honey drips, honeycomb pattern, flowers, vintage engraving, or cute bee mascots.\n\nTypography must be clean, high-contrast, and deliberately composed. The front panel should clearly read “HIVE/SCAN” at the top, “VARROA FIELD TEST” as the primary product name, “10 TESTS” in a cyan circular badge, and “APIARY DIAGNOSTICS” in small type near the bottom. The side panel should feature a simple three-step pictogram sequence labeled “SAMPLE / SHAKE / COUNT” plus a compact orange lot-number field. Use only these prominent words; avoid filler copy and illegible pseudo-text.\n\nPremium commercial product visualization, tactile paper fibers, sharp carton folds, accurate perspective, immaculate print alignment, restrained shadows, realistic materials, editorial industrial-design photography. Landscape composition, carton occupying roughly two-thirds of the frame, no hands, no loose tools, no secondary packages, no retail shelf, no website interface.",
  "width": 1248,
  "height": 832
}
```

---

### reference-to-image (reference-to-image)

![Lowrider Bicycle Builder Editorial Portrait](https://assets.runware.ai/examples/klingai-image-o1/85f3050d-913a-433d-85ee-7ceecfac2d3f.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e2e0d66d-6b78-432a-9e59-2bc0eb9a2a95",
  "model": "klingai:kling-image@o1",
  "positivePrompt": "Create a finished vertical editorial photoshoot portrait using both reference images. Preserve the exact facial identity, age, skin tone, hair, and body proportions of the woman in reference image 1. Include the exact custom lowrider bicycle from reference image 2, retaining its cobalt frame, silver pinstriping, elongated chrome fork, high-rise handlebars, white banana saddle, twisted spokes, reflectors, and distinctive geometry.\n\nPhotograph her as an accomplished custom bicycle builder in a monumental concrete flood-control channel beneath a broad overpass at sunrise. She stands beside the bicycle with one hand resting lightly on the saddle and the other holding a small chrome spoke wrench. Style her in an ecru short-sleeve mechanic jumpsuit tailored like high fashion, with cobalt topstitching, rolled cuffs, sturdy white work boots, and understated silver jewelry. Confident, composed expression directed toward the camera.\n\nFull-length environmental portrait with a slightly low camera position, generous vertical architecture, and the bicycle fully visible rather than cropped. Clean 1990s Japanese bicycle-catalog precision interpreted as contemporary editorial photography. Hard direct flash defines the subject and polished chrome while a narrow band of warm sunrise creates tangerine highlights in the background. Restrained palette of concrete gray, ecru, cobalt blue, chrome, and sunrise orange. Crisp realistic skin texture, believable fabric, accurate hands, mechanically coherent bicycle, subtle fine-grain finish. Premium magazine portrait, self-possessed and celebratory. No visible logos, captions, typography, borders, or watermarks.",
  "resolution": "2k",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/6baa7fa0-8300-447c-93db-a11182118671.jpg",
      "https://assets.runware.ai/assets/inputs/d9a227d3-75d1-499e-b60b-e6c79f33fed8.jpg"
    ]
  }
}
```

---

### reference-to-image (reference-to-image)

![Mobile Library Archive Photo Restoration](https://assets.runware.ai/examples/klingai-image-o1/85fa64cb-87b8-4828-acfd-561c84f34513.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "46522561-253b-4a68-ad0e-53f5ca3f4bb0",
  "model": "klingai:kling-image@o1",
  "positivePrompt": "Create a museum-grade restoration and historically restrained colorization of reference image 1. Preserve its exact documentary composition, camera angle, people, poses, facial identities, clothing, stone village hall, road and natural 1950s photographic character. Repair the diagonal crease, missing lower-right corner, scratches, dust, silvering, water stains and faded tonal areas without smoothing away genuine film grain or changing anatomy. Use reference image 2 as the factual guide for reconstructing the damaged portions of the mobile-library bus: retain the same rounded body, chrome grille, windows, wheels and trim, with its deep burgundy lower body, warm cream upper panels and fine gold lining. Rebuild only details obscured or lost in the damaged source. Preserve any genuinely legible wording from reference image 1, but do not invent extra lettering. Apply subtle, plausible period color: natural British skin tones, modest wool clothing in muted navy, brown, moss and maroon, weathered gray stone, damp olive grass and a softly overcast sky. Keep realistic fabric texture, bus paint wear, chrome reflections and masonry detail. The finished image should look like a carefully conserved original 1956 color photograph prepared as a large archival exhibition print, not a modern reenactment, not glossy, not oversaturated, and not artificially sharpened. Landscape 3:2 framing with all original subjects retained.",
  "resolution": "2k",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/b638d0d2-5f8f-4f0f-a9c7-94d8fbb2927c.jpg",
      "https://assets.runware.ai/assets/inputs/e854e053-05e5-4f9f-89b6-4b41ba7ceeb2.jpg"
    ]
  }
}
```