Kwaivgi Kling Image V4.0 Edit API Documentation
Playground
Try it on WaveSpeedAI!Kling Image 4.0 Edit transforms and combines reference images through natural-language instructions, supporting multi-image composition, subject and style consistency, product imagery, creative edits, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Kling Image 4.0 Edit generates images guided by a text prompt and 1–10 reference images. Use it to explore changes to subjects, backgrounds, clothing, products, or visual styles at 2K, 4K, or 8K.
Why Choose This?
- Reference-guided editing — Use uploaded images to guide the requested changes.
- Multiple references — Combine guidance from up to 10 input images.
- Framing options — Choose an aspect ratio or leave it unset for automatic selection.
- Batch generation — Request 1–9 independent output images.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the requested changes. Refer to inputs as <<<image_1>>>, <<<image_2>>>, and so on, in array order. |
| images | Yes | 1–10 reference image URLs. |
| aspect_ratio | No | 1:1, 3:2, 2:3, 3:4, 4:3, 9:16, 16:9, or 21:9. If omitted, the model selects the ratio automatically using the input images. |
| resolution | No | Output resolution tier: 2k, 4k, or 8k. Default: 2k. |
| num_images | No | Number of independent output images, from 1 to 9. Default: 1. |
| output_format | No | Output format: png, jpeg, or webp. Default: png. |
How to Use
- Add reference images — Upload 1–10 images in the order you will reference them.
- Describe the edit — State what should change and which details should be retained.
- Choose output settings — Set the resolution, image count, and format; optionally choose an aspect ratio.
- Submit and review — Check the generated images against your references.
Pricing
Pricing is based on the selected resolution and num_images.
| Resolution | Price per output image |
|---|---|
| 2K | $0.063 |
| 4K | $0.094 |
| 8K | $0.157 |
Each input image adds $0.003 per request.
Total price = num_images × the resolution rate + input image count × $0.003.
Example Costs
| Configuration | Price |
|---|---|
| 1 output at 2K + 1 input image | $0.066 |
| 2 outputs at 4K + 3 input images | $0.197 |
| 1 output at 8K + 10 input images | $0.187 |
Best Use Cases
- Product imagery — Explore new backgrounds, arrangements, and styling.
- Portrait variations — Request changes to clothing or surroundings.
- Visual combinations — Use several references to describe a new composition.
Pro Tips
- Use clear references with the relevant subject or detail visible.
- Assign a specific role to each reference in the prompt.
- Describe both the requested changes and the details you want to retain.
Notes
- Both
promptandimagesare required. - Each reference image must be no larger than 30 MB.
- Reference images guide generation; exact identity, text, and detail preservation can vary. Review the output before use.
Related Models
- Kling Image 4.0 Text-to-Image — Generate images from text prompts.
- Kling Image 4.0 Image Set — Generate related images in one request.
- Kling Image 4.0 Long Image — Create ecommerce or webpage design images.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "2k",
"num_images": 1,
"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/edit" \
-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
doneRetry temporary errors only while polling, never the submit request. Errors, retries and timeouts
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text prompt describing the image to create from the input images. Refer to the input images as <<<image_1>>>, <<<image_2>>>, etc. in array order. | |
| images | array<string> | Yes | - | 1 ~ 10 items | Input images (1-10): subjects, products, styles or scenes to combine or transform. |
| aspect_ratio | string | No | - | 1:1, 3:2, 2:3, 3:4, 4:3, 9:16, 16:9, 21:9 | The aspect ratio of the generated image. If not specified, it is determined automatically from the input image. |
| resolution | string | No | 2k | 2k, 4k, 8k | Output resolution. 2k, 4k or native 8k. |
| num_images | integer | No | 1 | 1 ~ 9 | Number of independent images to generate. |
| output_format | string | No | png | png, jpeg, webp | Output image format. |
Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<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.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |