Skip to content

Kling Image · O3 · Image to Image

Integrate

Model id kling-image/o3/image-to-image
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/kling-image/o3/image-to-image?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

This request: $0.028 28 API credits Run it on this page

Get API key
Kling Image Editing 4K outputReference inputsup to 4K #image-to-image

O3 image editing from up to 10 reference images, with 1K-4K output and series mode

Made on Doitong

Public works made with Kling Image by the Doitong community. Reuse a prompt in one click.

Public works shown: 16
Ultra-realistic cinematic video of a young adult woman walking naturally toward the camera while ... Video

Ultra-realistic cinematic video of a young adult woman walking naturally toward the camera while speaking, with realistic facial expressions and synchronized lip movements, as if she is promoting something to the viewer. She maintains eye contact with the camera, smiles slightly, and uses subtle...

Slow, subtle push-in on the woman's face. The light from the laptop flickers softly across her ey... Video

Slow, subtle push-in on the woman's face. The light from the laptop flickers softly across her eyes and cheeks, as if the blurry image on the screen is changing. Her eyes move slightly as she studies the screen, and she takes one slow, tense breath. Behind her, shadows of the snowstorm move...

The enormous ancient dragon descends slowly toward the snowy cliff and lands at the cave mouth. I... Video

The enormous ancient dragon descends slowly toward the snowy cliff and lands at the cave mouth. Its huge dark leathery wings beat twice with slow, heavy strokes, sending snow swirling off the cliff in big clouds. Then it folds its wings and settles on the rock, the giant elk still held in its...

**Duration: 5 seconds | Aspect ratio: 16:9 | Children's YouTube Intro | Video with Audio** Animat... Video

**Duration: 5 seconds | Aspect ratio: 16:9 | Children's YouTube Intro | Video with Audio** Animate the provided image into a bright, magical, energetic, professional YouTube intro for a children's entertainment channel, with perfectly synchronized sound effects, cheerful music, and a cute child's...

Authentic 1990s wide-angle film footage. The left man slowly pulls one wooden block from the Jeng... Video

Authentic 1990s wide-angle film footage. The left man slowly pulls one wooden block from the Jenga tower. As the block comes out, the tower naturally loses balance and realistically collapses onto the table. Frustrated, he angrily sweeps all the fallen wooden blocks off the table with both hands....

Thermal-camera view of a snowy mountain cliff at night in false-color, deep blue and violet cold ... Video

Thermal-camera view of a snowy mountain cliff at night in false-color, deep blue and violet cold rock, a huge orange-white heat shape hidden inside a rock crevice, two small bright amber spots glowing like eyes, faint noise grain. Cinematic videorealistic, ultra detailed, 16:9, volumetric light,...

**Duration: 4 seconds | Aspect ratio: 16:9 | Children's YouTube Intro | Video with Audio** Animat... Video

**Duration: 4 seconds | Aspect ratio: 16:9 | Children's YouTube Intro | Video with Audio** Animate the provided image into a bright, magical, energetic, professional YouTube intro for a children's entertainment channel, with perfectly synchronized sound effects, cheerful music, and a cute child's...

**Duration: 4 seconds | Aspect ratio: 16:9 | Children's YouTube Intro | Video with Audio** Animat... Video

**Duration: 4 seconds | Aspect ratio: 16:9 | Children's YouTube Intro | Video with Audio** Animate the provided image into a bright, magical, energetic, professional YouTube intro for a children's entertainment channel, with perfectly synchronized sound effects, cheerful music, and a cute child's...

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required 88 / 2500

Image-generation prompt limited to 2500 characters. Refer to images with @Image1, @Image2, and so on, or @Image for a single image.

•required image_urls
Drop a file, or

Reference image list, limited to 10 images; cite them in the prompt as @Image1, @Image2, and so on, with numbering starting at 1. Each file must be no larger than 10.0 MB, with width and height each at least 300px and an aspect ratio from 0.40 to 2.50.

resolution default 1K

Output image resolution: 1K for standard, 2K for high, or 4K for ultra-high resolution.

aspect_ratio default auto

Generated-image aspect ratio, selected automatically from the input content when set to 'auto'.

num_images default 1

Output image count, from 1 to 9; applies only if `result_type` is `single`.

Advanced result_type · output_format · series_amount · enable_safety_checker · elements
result_type default single

Output type: `single` produces one image, while `series` produces multiple related images.

output_format default png

File format for the resulting image.

Series image count, from 2 to 9; applies only if `result_type` is `series`.

Optional face-control elements representing characters or objects, addressed within the prompt by @Element1, @Element2, etc.

POST /run/kling-image/o3/image-to-image?wait=20 quote → $0.028
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/kling-image/o3/image-to-image?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Kling Image · O3 · Image to Image

Transforms or combines reference images (`image_urls`, up to 10) following a prompt that cites them as @Image1, @Image2 and so on. `resolution` is 1K, 2K or 4K, and `aspect_ratio` includes auto plus eight fixed ratios up to 21:9. Produce 1-9 single images with `num_images`, or a related set of 2-9 using `result_type` series and `series_amount`. Output is jpeg, png or webp.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptrequired
Typestring
≤ 2,500 characters
Image-generation prompt limited to 2500 characters. Refer to images with @Image1, @Image2, and so on, or @Image for a single image.
image_urlsrequired images
Typeurl[] · image
Reference image list, limited to 10 images; cite them in the prompt as @Image1, @Image2, and so on, with numbering starting at 1. Each file must be no larger than 10.0 MB, with width and height each at least 300px and an aspect ratio from 0.40 to 2.50.
elementsoptional
Typeobject[]
Optional face-control elements representing characters or objects, addressed within the prompt by @Element1, @Element2, etc.
elements[].frontal_image_urloptional
Typeurl · image
Optional front-facing image providing the element's main view. File size cannot exceed 10.0 MB; width and height must each be at least 300px, with an aspect ratio from 0.40 to 2.50.
elements[].reference_image_urlsoptional
Typeurl[] · image
Optional set of 0–3 additional images showing other angles. Each file must be no larger than 10.0 MB, with width and height each at least 300px and an aspect ratio from 0.40 to 2.50.
resolutionoptional
Typeenum
Default1K
1K2K4K
Output image resolution: 1K for standard, 2K for high, or 4K for ultra-high resolution.
result_typeoptional
Typeenum
Defaultsingle
singleseries
Output type: `single` produces one image, while `series` produces multiple related images.
num_imagesoptional num_outputs
Typeinteger
Default1
1 – 9
Output image count, from 1 to 9; applies only if `result_type` is `single`.
series_amountoptional
Typeinteger | null
2 – 9
Series image count, from 2 to 9; applies only if `result_type` is `series`.
aspect_ratiooptional
Typeenum
Defaultauto
16:99:161:14:33:43:22:321:9auto
Generated-image aspect ratio, selected automatically from the input content when set to 'auto'.
output_formatoptional
Typeenum
Defaultpng
jpegpngwebp
File format for the resulting image.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Screening can be relaxed by setting false, provided the caller is authorized.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "kling-image/o3/image-to-image",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 28,
    "usd": "0.028",
    "charged": 28,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200,
        "width": 1024,
        "height": 768
      }
    ]
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
images
array of object {url, content_type, file_name, file_size, width, height}Images produced by the model.

More models: Image Editing

For AI agents: this page as Markdown is at https://doitong.com/developers/models/kling-image/o3/image-to-image.md. All models and guides: https://doitong.com/developers/llms.txt