Kwaivgi Kling Image V4.0 Image Set API Documentation

Kwaivgi Kling Image V4.0 Image Set API Documentation

Playground

Try it on WaveSpeedAI!

Kling Image 4.0 Image Set generates cohesive image sets with consistent subjects and visual style for storyboards, product angle variations, character sheets, campaign assets, and multi-image creative workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Kling Image 4.0 Image Set generates a coordinated set of 2–10 images from one prompt, with optional guidance from up to 10 reference images. Describe a shared subject and style, then outline the content of each image for storyboards, product views, or campaign concepts.


Why Choose This?

  • Planned image sets — Describe several related images within one request.
  • Optional references — Use up to 10 images to guide the set.
  • Configurable set size — Choose 2–10 output images; the default is 4.
  • Resolution options — Choose 2K, 4K, or 8K for the set.

Parameters

ParameterRequiredDescription
promptYesDescribe the shared subject and style, followed by what each image should show.
imagesNoUp to 10 reference image URLs. Refer to them as <<<image_1>>>, <<<image_2>>>, and so on, in array order.
aspect_ratioNo1:1, 3:2, 2:3, 3:4, 4:3, 9:16, 16:9, or 21:9. If omitted, the model selects the ratio from the prompt and references.
resolutionNoOutput resolution tier: 2k, 4k, or 8k. Default: 2k.
num_imagesNoNumber of images in the set, from 2 to 10. Default: 4.
output_formatNoOutput format: png, jpeg, or webp. Default: png.

How to Use

  1. Plan the set — Describe the shared subject, style, and the intended content of each image.
  2. Add references if needed — Upload images and explain their roles in the prompt.
  3. Choose output settings — Set the image count, resolution, and format; optionally choose an aspect ratio.
  4. Submit and review the set — Check the sequence and visual continuity across the returned images.

Pricing

Pricing is based on the selected resolution and num_images.

ResolutionPrice per output image
2K$0.063
4K$0.094
8K$0.157

Each reference image adds $0.003 per request.

Total price = num_images × the resolution rate + reference image count × $0.003.

Example Costs

ConfigurationPrice
4 outputs at 2K, no references$0.252
4 outputs at 4K + 2 reference images$0.382
10 outputs at 8K + 10 reference images$1.600

Best Use Cases

  • Storyboards — Outline a sequence of scenes or narrative moments.
  • Product views — Explore several angles or presentation ideas.
  • Campaign concepts — Develop related images around a shared visual brief.

Pro Tips

  • Number the requested images and describe the purpose of each.
  • Keep shared subject and style instructions together, then list variations.
  • Match the number of described images to num_images.

Notes

  • Only prompt is required. Reference images are optional.
  • Each reference image must be no larger than 30 MB.
  • Images are generated as a related set; subject details, wording, and visual continuity can vary between images.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "resolution": "2k",
  "num_images": 4,
  "output_format": "png"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-image-v4.0/image-set" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Describe the image set: the shared subject and style, and what each image shows (for example a story in panels, a product from several angles, a character sheet). Refer to the input images as <<<image_1>>>, <<<image_2>>>, etc. in array order.
imagesarray<string>No-0 ~ 10 itemsOptional reference images (up to 10) shared by every image in the set.
aspect_ratiostringNo-1:1, 3:2, 2:3, 3:4, 4:3, 9:16, 16:9, 21:9The aspect ratio of every image in the set. If not specified, it is determined automatically from the prompt and the reference images.
resolutionstringNo2k2k, 4k, 8kOutput resolution. 2k, 4k or native 8k.
num_imagesintegerNo42 ~ 10Number of images in the set (2-10). They keep the same subjects and style.
output_formatstringNopngpng, jpeg, webpOutput image format.

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.