Kling Motion Control

Kling Motion Control — transfer real motion from a driver video to a character image. Preserves authentic gestures, idle motion, and expressions. v3 supports face reference binding for identity lock.

Try Kling Motion Control in the playground

Last updated View as MarkdownAgent setup

Kling Motion Control

Badge: New
Node type: video:kling_video_3_pro_motion_control
Category: video

Description

Kling Motion Control animates a character image with the real motion of a driver video: wire the character into Character Image and a 3 to 30 second clip into Driver Video, choose Character Orientation, and run the node to get a Generated Video. It preserves the driver's gestures, idle motion and expressions, so keep the body clearly visible and unoccluded in both. To lock the face, wire a frontal face image into Face Frontal (Identity Lock), optionally add 1 to 3 other angles in Face References (angles), set orientation to video, and refer to the face as @Element1 in the Prompt; this binding works on v3 only. Turn on Keep Driver Audio to keep the clip's sound. It costs about 27 credits per second, which is the rate for a 5-second clip; shorter clips can cost a bit more per second, and you're charged for the real length.

Pricing

  • Cost: ~27 credits per second
  • Per-second rate: The figure is the rate for a 5-second clip. Shorter clips can cost a bit more per second. You're always charged for the real length.

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
image_url Character Image IMAGE (required) — The character to animate. Body should be clearly visible and unoccluded.
video_url Driver Video VIDEO (required) — Reference video — the generated character will mirror this motion. 3–30s. Character should be upper-body or full-body visible with no occlusion.
prompt Prompt TEXT · multiline — Optional scene description. Reference the face element as @Element1 when using element binding (v3 only).
element_frontal_image_url Face Frontal (Identity Lock) IMAGE — Optional frontal face image for identity preservation. Reference as @Element1 in prompt. Only used when orientation is "video".
element_reference_image_urls Face References (angles) IMAGE — Optional 1–3 additional face images from different angles (side profile, open mouth, etc). Requires Face Frontal and orientation=video.

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
model_version Version TEXT · options: 3.0-pro, 3.0-standard, 2.6-pro, 2.6-standard
character_orientation Character Orientation TEXT (required) · options: video, image
keep_original_sound Keep Driver Audio BOOLEAN — Keep the audio track from the driver video in the output.

Outputs

ID Label Type
video Generated Video VIDEO

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.