Kling Advanced Elements creates custom AI elements from reference images or videos for consistent character and object appearance across Kling video generations. Supports multi-image elements with frontal and reference images, video character elements, and optional voice binding. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle

$0.01per run·~100 / $1
Kling Advanced Elements creates custom AI elements from reference images or videos for consistent character and object appearance across Kling video generations. Define an element with a name, description, and reference material — the model returns a reusable element ID that can be referenced in any Kling generation to maintain identity across clips. Supports both image-based and video-based element creation, with optional voice binding for speaking characters.
Two reference modes Choose image_refer (frontal image + up to 4 additional reference images) or video_refer (reference video) to best match your source material.
Multi-image support Capture different angles, expressions, and styles with a frontal image plus up to 4 additional reference images for accurate character consistency.
Video character elements Define a character's full appearance and motion style from a reference video for more dynamic identity capture.
Voice binding Optionally attach a voice ID to the element for talking avatar and dialogue-driven video workflows.
Reusable across generations Created elements can be referenced by ID in any Kling video generation — use the same character across unlimited clips.
| Parameter | Required | Description |
|---|---|---|
| name | Yes | Element name. Max 20 characters. |
| description | Yes | Element description. Max 100 characters. |
| reference_type | Yes | Reference mode: image_refer (default) or video_refer. |
| frontal_image | Yes (if image_refer) | Front-facing reference image. Required when reference_type is image_refer. |
| refer_images | No | Additional reference images (2–4) from different angles or expressions. |
| element_video_list | Yes (if video_refer) | Reference video defining the character's appearance. Required when reference_type is video_refer. |
| voice_id | No | Voice ID to bind to the element for speaking characters. |
| tag_list | No | Custom tags for organizing and categorizing elements. |
| Reference Type | Cost per Element |
|---|---|
| image_refer | $0.010 |
| video_refer | $0.015 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-elements-advanced with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Kling Elements Advanced below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"name": "example",
"description": "example",
"reference_type": "image_refer"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-elements-advanced" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/kwaivgi/kling-elements-advanced";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"name": "example",
"description": "example",
"reference_type": "image_refer"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"name": "example",
"description": "example",
"reference_type": "image_refer"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/kwaivgi/kling-elements-advanced", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Kling Elements Advanced is a Kuaishou model for AI inference, exposed as a REST API on WaveSpeedAI. Kling Advanced Elements creates custom AI elements from reference images or videos for consistent character and object appearance across Kling video generations. Supports multi-image elements with frontal and reference images, video character elements, and optional voice binding. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-elements-advanced.
Kling Elements Advanced starts at $0.010 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `description`, `element_video_list`, `frontal_image`, `name`, `refer_images`, `reference_type`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-elements-advanced.
Median end-to-end generation time on WaveSpeedAI is around 8 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Kuaishou). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.