Kling 2.6 Pro Motion Control API

kwaivgi/kling-v2.6-pro/motion-control

Kling 2.6 Pro Motion Control (Motion-Control) transforms a character image and reference video into 1080p motion-transfer clips, with high-fidelity skeletal tracking, complex-action synthesis, and prompt-guided environment control. It preserves facial features, proportions, and character identity while delivering production-ready choreography, stunts, and athletic performances.

Input

Prompt

247/2500

Character Image

Drag and drop files, paste from clipboard, or provide a URL.

1/1 files added

Reference Video

Drag and drop files, paste from clipboard, or provide a URL.

1/1 files added

Character Orientation

Output

Ready

Continue with

Kling 2.6 Standard Motion Control Kling 3.0 Motion Control Seedance 2.5

Examples

The athletic man in the black sleeveless training top performs the explosive acrobatic backflip from the reference video on the open grass field, keeping his face, body build and outfit perfectly consistent, distant trees and bright sky behind him

The dancer in the reference image performs the contemporary stage choreography from the reference video: sweeping arm lines, a controlled turn, and an expressive floor-to-stand transition. Keep her face and flowing burgundy dress consistent with the reference image. Dark theater stage with a single soft blue spotlight from above, theatrical atmosphere, full-body framing, fluid cinematic motion.

The basketball player in the reference image executes the dribble-and-drive moves from the reference video: crossover dribble, explosive first step, and a layup finish. Keep his face, red sleeveless jersey and black shorts consistent with the reference image. Outdoor asphalt court with chain-link fence and city skyline, golden afternoon light, full-body dynamic framing, realistic motion.

REST API

Quick Start

Authenticate, submit a valid input object, then use task_id to retrieve the video.

Connect to the Vidgo API

Create an API key, keep it only on your server, and send Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one generation task

Run the smallest valid payload for this workflow. The model must be kwaivgi/kling-v2.6-pro/motion-control. A successful submission immediately returns task_id without waiting for the video.

Submit request

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "kwaivgi/kling-v2.6-pro/motion-control",
  "input": {
    "prompt": "The athletic man in the black sleeveless training top performs the explosive acrobatic backflip from the reference video on the open grass field, keeping his face, body build and outfit perfectly consistent, distant trees and bright sky behind him",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-v2.6-pro/motion-control/v1/01/input-image.png"
    ],
    "video_urls": [
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-v2.6-pro/motion-control/v1/01/input-video.mp4"
    ],
    "character_orientation": "video",
    "resolution": "1080p"
  }
}
JSON
)

RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
  printf 'API error: %s
' "$RESPONSE" >&2
  exit 1
fi
printf '%s
' "$RESPONSE"

Wait for the result

Query with task_id, continue for not_started/running, and stop for finished/failed. On success, read data.files[].file_url.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll about every 2 seconds, then back off gradually. Continue only for not_started or running and stop on finished or failed. You can instead add callback_url to the same top-level request contract.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "running",
    "created_time": "2025-12-25T10:59:37Z"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "finished",
    "files": [
      {
        "file_url": "https://storage.vidgo.ai/generated/video.mp4",
        "file_type": "video"
      }
    ],
    "created_time": "2026-08-22T10:00:00Z",
    "progress": 100,
    "error_message": null
  }
}

Complete runnable example

Expand for a complete script with HTTP and business-code checks, task_id validation, polling, terminal-state handling, and a timeout boundary.

Complete runnable example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "kwaivgi/kling-v2.6-pro/motion-control",
  "input": {
    "prompt": "The athletic man in the black sleeveless training top performs the explosive acrobatic backflip from the reference video on the open grass field, keeping his face, body build and outfit perfectly consistent, distant trees and bright sky behind him",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-v2.6-pro/motion-control/v1/01/input-image.png"
    ],
    "video_urls": [
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-v2.6-pro/motion-control/v1/01/input-video.mp4"
    ],
    "character_orientation": "video",
    "resolution": "1080p"
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
  printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
  if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
    printf 'Timed out after 600 seconds
' >&2
    exit 1
  fi
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
  BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
  if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
    printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
    exit 1
  fi

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep "$POLL_DELAY"
      if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Input parameters

These are the fields accepted inside input. The request example shows the required top-level model field.

Field	Type	Required	Default	Description
prompt	string	No	—	Optional; null, empty, and whitespace-only prompts are treated as omitted. Nonempty text is trimmed and limited to 2,500 characters.
image_urls	array	Yes	—	Single character image URL (JPEG, PNG, WEBP, max 10MB). Exactly one URL.
video_urls	array	Yes	—	Single reference video URL (MP4, MOV, MKV, max 100MB). Exactly one URL.
character_orientation	string	Yes	—	Character orientation mode. image or video.
resolution	string	No	1080p	Optional; defaults to 1080p. Explicit values must be 1080p.

Response Fields

Submission returns task identity immediately. Status responses add progress, every output file, or a failure message.

Field	Type	Description
code	integer	Application result code; successful responses use 0 or 200.
message	string	Human-readable message or error detail when present.
data.task_id	string	Task ID used in the status endpoint path.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation time in date-time format.
data.progress	integer	Task progress from 0 to 100, when included in the response.
data.files[]	array	All output files from a successful task, in response order.
data.files[].file_url	string	Public URL for a generated video.
data.files[].file_type	string	File type, such as video.
data.error_message	string \| null	Failure detail when status is failed.

Task Lifecycle

Treat not_started and running as non-terminal states. finished and failed are terminal alternatives; stop polling when either is returned.

not_started
The task was accepted and is waiting to begin.
running
Generation is in progress. Continue polling the same task_id.
finished
Generation succeeded. Read every video URL from data.files[].file_url.
failed
Generation stopped with an error. Read data.error_message and stop polling.

Polling and Errors

AuthenticationA 401 response means the Bearer API key is missing or invalid. Correct it before retrying.
ValidationA 400 response identifies an invalid field, unsupported media key, or insufficient credit balance. Correct the request before resubmitting.
Network and timeoutA transport failure is different from a failed task. Retry status checks with a bounded timeout before deciding that the task failed.
Polling intervalStart around every 2 seconds and increase the interval gradually for a long-running task.
Terminal statesContinue only for not_started or running. Stop immediately on finished or failed.
Callback optionProvide callback_url at the request top level to receive the final flat task object; polling remains available if delivery fails.

Endpoint limits

Specification	Value	Details
Input mode	1 image + 1 video	image_urls and video_urls each require exactly one URL. prompt is optional.
Output	Video task	The endpoint returns an asynchronous task ID.
Resolution	1080p	Required and fixed by model ID kwaivgi/kling-v2.6-pro/motion-control.
Reference duration	3–10s / 3–30s	image orientation: 3–10 seconds. video orientation: 3–30 seconds. Do not send duration; the backend probes the file.
Billing basis	12 credits/sec	Credits = ceil(detected seconds × 12); multiply by the per-second rate before rounding the total credits up.

View Kling 2.6 Pro Motion Control API documentation

Kling 2.6 Pro Motion Control

Kling 2.6 Pro Motion Control transfers movement from a reference video onto a character image at 1080p. Use one character image and one motion clip to drive high-fidelity skeletal tracking, timing, and expressions while keeping identity consistent for production delivery.

Core Features of Kling 2.6 Pro Motion Control

Reference-Video Motion TransferMove complete motion sequences from any reference video onto your target character. The model mirrors body movement, facial expression, and timing while keeping your character's identity and appearance intact.
Full-Body Motion TrackingCapture motion at a professional level, from subtle hand cues to acrobatic sequences. The system understands skeletal dynamics and reproduces complex body mechanics with high fidelity.
Complex Action SynthesisSupport demanding movement patterns such as martial arts, choreography, and athletic drills. Motion stays coherent through fast transitions and multi-limb coordination.
Character Identity PreservationKeep facial features, proportions, and overall look consistent during transfer. Movements adapt to your character while preserving visual identity across the clip.
Environment FlexibilitySwap environments with text prompts without disturbing the motion. Reuse the same performance across multiple scenes for varied storytelling.
Camera Motion ControlDefine camera paths and angles while applying motion transfer. Achieve cinematic viewpoints and dynamic shots with precise control.

Parameters

Parameter	Requirement	Description
prompt	Optional	Optional; null, empty, and whitespace-only prompts are treated as omitted. Nonempty text is trimmed and limited to 2,500 characters.
image_urls	Required	Single character image URL (JPEG, PNG, WEBP, max 10MB). Must clearly show the subject's head, shoulders, and torso. Exactly one URL.
video_urls	Required	Single reference video URL for motion transfer (MP4, MOV, MKV, max 100MB, 3-30 seconds). Must clearly show the subject's head, shoulders, and torso. Exactly one URL. When character_orientation is image, the reference video must be 3–10 seconds; when video, 3–30 seconds.
character_orientation	Required	Character orientation mode: 'image' matches the person's orientation in the photograph (max 10 seconds output), 'video' maintains consistency with character orientation from the reference video (max 30 seconds output). `imagevideo`
resolution	Optional	Optional; defaults to 1080p. Explicit values must be 1080p. Default`1080p`

How to Use Kling 2.6 Motion Control API on Vidgo API

Step 1: Register & Create API KeySign up on Vidgo API and generate your API key instantly. Access professional motion control technology with no setup complexity or technical barriers.
Step 2: Prepare Your AssetsUpload your character image and reference video. The API accepts various video formats and automatically processes motion data for optimal transfer results.
Step 3: Generate Motion TransferSubmit your API request with motion control parameters. Receive high-quality 1080p video with precise motion transfer in minutes.

Kling 2.6 Pro Motion Control Pricing

1080p: 12 credits/sec ($0.06/sec). Credits = ceil(detected seconds × 12); multiply by the per-second rate before rounding the total credits up.

Usage	Rate	Details
1080p	12 credits/sec ($0.06/sec)	Credits = ceil(detected seconds × 12); multiply by the per-second rate before rounding the total credits up.

Who Benefits from Kling 2.6 Pro Motion Control API?

Professional Action CoachingBuild detailed instruction for sports, martial arts, and dance training. Transfer expert demonstrations to learner characters for personalized practice.
Film & VFX ProductionCreate stunt and high-risk sequences safely. Replace performers in complex shots while preserving realistic motion and character consistency.
Sports Analysis & TrainingShow ideal athletic technique with precise motion. Transfer pro movement to training characters for comparison and improvement.
Dance ChoreographyProduce choreography demos and instruction clips. Apply choreographer motion to different characters for flexible dance content.
Martial Arts InstructionPresent complex forms and techniques clearly. Transfer master movements to student characters for detailed analysis and practice.
Motion Research & DevelopmentRun movement studies and biomechanical tests. Generate controlled sequences for research in human motion and performance.

Why Use Vidgo API for Kling 2.6 Motion Control API Access

Full sequence transfer
Accurate timing retention
Identity-aware mapping
Comprehensive skeletal tracking
Fine-grained gesture capture
Realistic weight shifts
Martial arts routines
Dance choreography
Athletic performance
Consistent facial features
Proportion-aware adaptation
Visual identity retention
Text-based environment control
Background replacement
Scene context adaptation
Planned camera paths
Cinematic angles
Professional viewpoints

Notes

The current endpoint requires exactly one image in image_urls and exactly one video in video_urls. Reference video length must be at least 3 seconds. When character_orientation is set to image, the reference video cannot exceed 10 seconds; when set to video, it cannot exceed 30 seconds.
Character image supports JPEG, PNG, and WEBP, max 10MB.
Reference video supports MP4, MOV, and MKV, max 100MB.
Do not send duration or mode. The backend probes the reference video.
resolution is optional and defaults to 1080p; explicit values must be 1080p.

Related Models

Gemini Omni 1.1 Flash Text-to-Video preview

Gemini Omni 1.1 Flash Text-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Image-to-Video preview

Gemini Omni 1.1 Flash Image-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Reference-to-Video preview

Gemini Omni 1.1 Flash Reference-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Video Edit preview

Gemini Omni 1.1 Flash Video EditGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

MiniMax H3 Max Turbo Text to Video preview

MiniMax H3 Max Turbo Text to VideoMiniMax H3 Max Turbo Text to Video turns text into coherent 5–15 second videos with synchronized native stereo audio and fast generation. It follows physical motion while rendering subtle changes in light and shadow.

MiniMax H3 Max Turbo Image to Video preview

MiniMax H3 Max Turbo Image to VideoMiniMax H3 Max Turbo Text to Video turns text into coherent 5–15 second videos with synchronized native stereo audio and fast generation. It follows physical motion while rendering subtle changes in light and shadow.

MiniMax H3 Max Text to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

MiniMax H3 Max Image to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

MiniMax H3 Max Reference to Video preview

MiniMax H3 Max Reference to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

Wan 3.0 Prime Text-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Prime Image-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Prime Reference-to-Video preview

Wan 3.0 Prime Reference-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Text-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Image-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Reference-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

FLUX 3 Text to VideoBlack Forest Labs FLUX 3 video model with text-to-video, image-to-video, first-last-frame, extend-video, and keyframes workflows at 720p or 1080p for 5 to 20 seconds, with optional native audio.

Kling 2.6 Pro Motion Control — Frequently asked questions

What is Kling 2.6 Pro Motion Control (Motion-Control) API?

Kling 2.6 Pro Motion Control is Kuaishou's model for transferring motion from a reference video onto a character image, producing 1080p clips billed at 12 credits per second. From one character image, one reference video, and an optional scene prompt, it delivers high-fidelity skeletal tracking, complex-action synthesis, and prompt-guided environment control. Built on identity-aware motion mapping, it preserves facial features and proportions while applying production-ready choreography, stunts, and athletic timing. You can call it programmatically or try it from the playground above.

How accurate is Kling 2.6 Pro Motion Control tracking?

Pro targets high-fidelity full-body tracking that mirrors reference timing, facial expression, and multi-limb coordination. Use a clear character image with visible head, shoulders, and torso, plus an unobstructed reference performance, so the transfer can follow fine gestures and weight shifts.

Does Kling 2.6 Pro Motion Control support complex motions?

Yes. It is built for demanding patterns such as martial arts, dance choreography, athletic drills, and fast multi-limb transitions. Choose character_orientation video when spatial orientation should follow the reference clip for longer, more complex performances.

What resolution does Kling 2.6 Pro Motion Control output?

This endpoint outputs 1080p only. Resolution is optional and defaults to 1080p for model kwaivgi/kling-v2.6-pro/motion-control, making it the higher-fidelity tier for client delivery and production review.

How long can Kling 2.6 Pro Motion Control reference videos run?

Reference videos must be at least 3 seconds. With character_orientation set to image, the clip can run up to 10 seconds; with video, up to 30 seconds. Do not send duration—the backend probes the reference file and bills by that probed length.

How does Kling 2.6 Pro Motion Control pricing differ from Standard?

Standard 720p costs 8 credits/sec; Pro 1080p costs 12 credits/sec. Both multiply detected seconds by the rate before rounding total credits up. A 5.2-second clip costs 42 credits on Standard or 63 on Pro.

Can Kling 2.6 Pro Motion Control preserve character identity?

Yes. The model maps reference motion onto your character while keeping facial features, proportions, and overall look consistent across the clip. Clear, well-framed character images give the strongest identity retention for 1080p delivery.

Which character_orientation mode should Kling 2.6 Pro Motion Control use?

Use image when the output should match the photograph's facing direction and you want stronger camera-follow behavior within a 10-second window. Use video when orientation should follow the reference clip for complex motions up to 30 seconds.