Kling 2.6 Motion Control

NamiFusion Kling 2.6 Motion Control

AI motion-controlled video generation: upload a character image and a motion reference video to create an animated video that preserves the character's identity.

NamiFusion Kling 2.6 Motion Control is a video generation service designed for motion transfer scenarios. It takes a character image and a motion reference video, transfers the dance, action, or gesture from the reference video onto the target character, and outputs a result video with better identity consistency and temporal coherence.

---

Key Features

• Motion Transfer: Transfer body movements from a reference video to a target character, suitable for dance, performance, and action demonstration scenarios.
• Character Consistency: Uses the character image as the visual subject of the generated video and preserves the person's appearance and identity features as much as possible.
• Optional Prompt Control: Supports prompt and negative_prompt to provide additional guidance for style and undesired content.
• Async Tasks: Returns a task_uuid after submission, and you can retrieve processing status and final results through polling.

---

Technical Specifications

Parameter	Details
Model ID	kwaivgi/kling-v2.6-pro/motion-control
Request Method	Async POST (submit task + poll for results)
Input	Character image URL + motion reference video URL
Output	Generated video URL
Processing Time	Typically tens of seconds to several minutes, with a maximum polling wait time of 10 minutes
Pricing	$0.07 / second for 720P, $0.112 / second for 1080P, minimum charge of 3 seconds

---

Quick Start

API Endpoints

Endpoint	Method	Description
/api/v1/marketplace/run/kwaivgi/kling-v2.6/motion-control	POST	Submit a motion control task
/api/v1/marketplace/run/tasks/{task_uuid}	GET	Query task status and results

Authentication

Include your API Key in the request header:

X-API-Key: sk-your-api-key

---

Usage Example

Step 1: Submit a Task

curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v2.6/motion-control" \
  -H "X-API-Key: sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "image": "https://static.example.com/character.png",
      "video": "https://static.example.com/motion.mp4",
      "character_orientation": "image",
      "prompt": "full body, natural motion, cinematic lighting",
      "negative_prompt": "blur, distortion, extra limbs, low quality",
      "keep_original_sound": true
    }
  }'

Response Example:

{
  "task_uuid": "443ea3cd-4025-40d2-901f-ef18970dbc43",
  "status": "pending",
  "cost_credits": 0
}

Step 2: Poll Task Status

curl -X GET "https://www.namifusion.com/api/v1/marketplace/run/tasks/443ea3cd-4025-40d2-901f-ef18970dbc43" \
  -H "X-API-Key: sk-your-api-key"

Processing:

{
  "task_uuid": "443ea3cd-4025-40d2-901f-ef18970dbc43",
  "status": "processing"
}

Completed:

{
  "task_uuid": "443ea3cd-4025-40d2-901f-ef18970dbc43",
  "model_id": "kwaivgi/kling-v2.6-pro/motion-control",
  "status": "completed",
  "output": {
    "video_url": "https://cdn.example.com/results/kling_motion_control_output.mp4"
  },
  "cost_credits": 0,
  "created_at": "2026-03-27T11:40:00Z",
  "completed_at": "2026-03-27T11:41:20Z"
}

---

Python Example

import requests
import time

API_KEY = "sk-your-api-key"
BASE_URL = "https://www.namifusion.com/api/v1/marketplace/run"
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json",
}

payload = {
    "input": {
        "image": "https://static.example.com/character.png",
        "video": "https://static.example.com/motion.mp4",
        "character_orientation": "image",
        "prompt": "full body, natural motion, cinematic lighting",
        "negative_prompt": "blur, distortion, extra limbs, low quality",
        "keep_original_sound": True,
    }
}

submit_resp = requests.post(
    f"{BASE_URL}/kwaivgi/kling-v2.6-pro/motion-control",
    headers=HEADERS,
    json=payload,
)
submit_resp.raise_for_status()
task = submit_resp.json()

task_uuid = task["task_uuid"]
print(f"Task submitted: {task_uuid}")

while True:
    status_resp = requests.get(
        f"{BASE_URL}/tasks/{task_uuid}",
        headers=HEADERS,
    )
    status_resp.raise_for_status()
    result = status_resp.json()

    status = result["status"]
    print(f"Status: {status}")

    if status == "completed":
        print("Result:", result["output"]["video_url"])
        break

    if status == "failed":
        print("Failed:", result.get("error_message", "Unknown error"))
        break

    time.sleep(5)

---

Detailed Parameters and Return Values

Request Parameters

The request body is JSON, and all parameters are placed inside the input object:

{
  "input": {
    "image": "https://...",
    "video": "https://...",
    "character_orientation": "image",
    "prompt": "full body, natural motion",
    "negative_prompt": "blur, low quality",
    "keep_original_sound": true
  }
}

Parameter	Type	Required	Default	Description
image	string	Yes	-	Character image URL. Supports .jpg, .jpeg, and .png, with a maximum file size of 10MB, minimum dimensions of 300x300, and an aspect ratio range from 1:2.5 to 2.5:1.
video	string	Yes	-	Motion reference video URL. Supports .mp4 and .mov, with a maximum file size of 10MB, minimum dimensions of 300x300, and an aspect ratio range from 1:2.5 to 2.5:1.
character_orientation	string	No	"image"	Character source type. The current model configuration uses image as the default. Supported values: image, video.
prompt	string	No	null	Optional positive prompt for describing motion style, camera mood, character expression, and similar guidance. Maximum length is 500 characters.
negative_prompt	string	No	null	Optional negative prompt for constraining unwanted content. Maximum length is 500 characters.
keep_original_sound	boolean	No	true	Whether to preserve the original audio from the motion reference video.

Task Status

After submitting the task, query its status by polling. A 5-second polling interval is recommended:

Status	Description
pending	The task has been created and is waiting to be processed.
processing	The task is being processed.
completed	The task is completed, and the result video URL is available in output.video_url.
failed	The task failed. Check error_message for the reason.

Return Value Structure

Task Submission Response

Field	Type	Description
task_uuid	string	Unique task identifier used for later status queries.
status	string	Initial task status, usually pending.
cost_credits	number	Credits consumed by this task.

Task Completion Response

Field	Type	Description
task_uuid	string	Unique task identifier.
model_id	string	Model ID (kwaivgi/kling-v2.6-pro/motion-control).
status	string	Task status.
output.video_url	string	Generated result video URL.
cost_credits	number	Credits consumed.
created_at	string	Task creation time (ISO 8601).
completed_at	string	Task completion time (ISO 8601).
error_message	string	Error message, returned only when failed.

---

How Parameters Affect the Output

Parameter	Effect on Output
image	Determines the appearance of the main character in the final video. A clear character image with no occlusion and complete framing is recommended.
video	Provides the motion trajectory and rhythm reference. Clearer movement and a more prominent subject usually lead to more stable transfer results.
prompt	Adds guidance for camera style, motion atmosphere, clothing details, or scene tendencies, but does not replace the reference motion itself.
negative_prompt	Helps reduce issues such as blur, distortion, extra limbs, and low-quality details.
keep_original_sound: true	The output video preserves the original sound from the reference video as much as possible, making it more suitable for dance and performance scenarios.
keep_original_sound: false	The output video does not preserve the original sound from the reference video, making it more suitable for later audio replacement or editing.

---

Notes

1. Input URLs must be publicly accessible: Both image and video should be public URLs that the server can download directly.
2. Using an image as the character input is recommended: The current model configuration defaults to character_orientation: "image", which is also the most stable and clearly defined integration method.
3. Keep prompts concise and specific: prompt and negative_prompt work best as supplemental guidance. Avoid stacking too many conflicting descriptions.
4. A 5-second polling interval is recommended: This model uses async task processing. Query the task status every 5 seconds, with a maximum wait time of 600 seconds.
5. The result field is a single video URL: After task completion, read the result from output.video_url rather than from an array field like videos.