Seedance 2.5 Now Live | Try in Video Generator →

kwaivgi/

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.

image-to-text
Input

Idle

kwaivgi/kling-elements-advanced preview unavailable

$0.01per run·~100 / $1

Next:

ExamplesView all

Related Models

README

Kling Advanced Elements

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.

Why Choose This?

  • 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.

Parameters

ParameterRequiredDescription
nameYesElement name. Max 20 characters.
descriptionYesElement description. Max 100 characters.
reference_typeYesReference mode: image_refer (default) or video_refer.
frontal_imageYes (if image_refer)Front-facing reference image. Required when reference_type is image_refer.
refer_imagesNoAdditional reference images (2–4) from different angles or expressions.
element_video_listYes (if video_refer)Reference video defining the character's appearance. Required when reference_type is video_refer.
voice_idNoVoice ID to bind to the element for speaking characters.
tag_listNoCustom tags for organizing and categorizing elements.

How to Use

  1. Enter a name — give your element a clear, identifiable name (max 20 characters).
  2. Write a description — describe the character's appearance, style, and key traits (max 100 characters).
  3. Select reference_type — choose image_refer for image-based creation or video_refer for video-based.
  4. If image_refer — upload a frontal_image (required) and optionally add 2–4 refer_images from different angles.
  5. If video_refer — upload one reference video in element_video_list.
  6. Add voice_id (optional) — attach a voice ID for speaking character workflows.
  7. Add tag_list (optional) — add custom tags to organize your element library.
  8. Submit — save the returned element ID for use in Kling video generations.

Pricing

Reference TypeCost per Element
image_refer$0.010
video_refer$0.015

Best Use Cases

  • Consistent character series — Create a reusable character ID to maintain identity across multiple Kling video generations.
  • Fashion & wardrobe elements — Define clothing and styling elements for consistent use in fashion video content.
  • Brand assets — Build reusable brand mascots, logos, and product elements for marketing video workflows.
  • Talking avatar workflows — Combine element IDs with voice IDs for dialogue-driven character video generation.
  • E-commerce product elements — Define product elements for consistent product video content at scale.

Pro Tips

  • Use clear, well-lit frontal and profile images for the most accurate character identity capture.
  • For video_refer mode, use a short clip that clearly shows the character from multiple angles.
  • Give elements descriptive names and tags to keep your library organized as it grows.
  • Once an element is created, write its name naturally in your generation prompt and enter the element ID in the element_list field — no special characters required.

Notes

  • name, description, and reference_type are always required.
  • image_refer mode requires at least a frontal_image; refer_images are optional (2–4 additional images).
  • video_refer mode requires exactly 1 reference video and costs 1.5× the image_refer price.
  • Voice binding is optional and available for both reference types.
  • Voice IDs can be obtained through the voice-related API — see the Voice Guide for details.

Related Models

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Kling Elements Advanced API — Quick start

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.

HTTP example
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
done
Node.js example
const 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));
}
Python example
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 API — Frequently asked questions

What is the Kling Elements Advanced API?

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.

How do I call the Kling Elements Advanced API?

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.

How much does Kling Elements Advanced cost per run?

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.

What inputs does Kling Elements Advanced accept?

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.

How long does Kling Elements Advanced take to generate?

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.

Can I use Kling Elements Advanced outputs commercially?

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.

Kling Elements Advanced | AI Image Understanding API on WaveSpeedAI