Kling Image V3 Image To Image

From 34 credits/call
ae_kling_image_v3_image_to_image

Transform a single reference image with a text prompt to create up to nine new images, with optional character or object control and resolutions up to 2K.

Image
From 34 credits/call

Pricing

From 34 credits/call
ConditionCharge
Per image34 credits/image

Charges depend on image count.

An omitted image count is charged as one image.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.promptstringYesText prompt for image generation. Max 2500 characters.—
request_body.elementsarray | unknownNoOptional: Elements (characters/objects) to include in the image for face control.—
request_body.elements[].frontal_image_urlstring | unknownNoThe frontal image of the element (main view). Optional.—
request_body.elements[].reference_image_urlsarray | unknownNoAdditional reference images from different angles. 0-3 images supported. Optional.—
request_body.image_urlstringYesReference image for image-to-image generation. Max file size: 10.0MB, Min width: 300px, Min height: 300px, Min aspect ratio: 0.40, Max aspect ratio: 2.50, Timeout: 20.0s—
request_body.sync_modebooleanNoIf `True`, the media will be returned as a data URI.false
request_body.num_imagesintegerNoNumber of images to generate (1-9).1
request_body.resolutionenum (1K | 2K)NoImage generation resolution. 1K: standard, 2K: high-res.1K
request_body.aspect_ratioenum (16:9 | 9:16 | 1:1 | 4:3 | 3:4 | 3:2 | 2:3 | 21:9)NoAspect ratio of generated images.16:9
request_body.output_formatenum (jpeg | png | webp)NoThe format of the generated image.png

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_kling_image_v3_image_to_image' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "aspect_ratio": "3:4",
      "image_url": "https://agentearth.ai/fileserver/file/e2922fad-4164-4a98-a444-1fe4e90d0d66.jpg",
      "num_images": 1,
      "output_format": "jpeg",
      "prompt": "Professional half-body waist-up LinkedIn portrait photograph of this exact Asian woman physician in her 40s, keeping her exact face shape, real skin texture unchanged. She has a calm gentle expression in the original — keep it warm and approachable but add a subtle confident closed-mouth smile. Restyle her hair into a smarter polished bob or shoulder-length layered cut, neat and elegant, with a few discreet silver-grey strands at the temples for a distinguished touch. DRESS her in a dark navy blue women'\''s tailored suit jacket with a crisp white blouse underneath, and add a vivid bright scarlet red silk scarf loosely knotted at the collar instead of a necktie. Keep her jade pendant necklace if visible. Background: mottled blue-grey painted canvas studio backdrop with soft cloudy watercolour texture, brighter behind her head and darker toward the corners, gently out of focus — exactly the same backdrop style as a male doctor executive portrait. Frontal pose, shoulders square, soft directional key light from upper left, faint rim light on the shoulders, 85mm lens, realistic unretouched photograph, natural skin pores, no beauty retouching, no airbrushing. No text, no watermark.",
      "resolution": "2K"
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "b8a1ffd6-1e23-4a7a-bdff-ead83356dea3"
}