Kling 2.6 Pro Motion Control
Kling V2.6 Pro Motion Control transforms static character images into dynamically animated videos by precisely extracting and transferring motion from real reference video clips.
Motion transfer from reference video to character image
Kling V2.6 Pro Motion Control is an AI video generation model developed by Kuaishou Technology that animates static character images by extracting and transferring motion from real reference video clips. Rather than generating movement from text descriptions alone, it uses a 3D face and body reconstruction system built on deep learning-based 3D modeling to map human faces and body movements from 2D inputs, then applies those motion paths frame-by-frame to a subject image. The model runs on a Diffusion Transformer Architecture and produces output at 30 frames per second with coherent motion transitions throughout the generated clip.
The model accepts reference videos between 3 and 30 seconds in length and supports a wide range of movement types, including dance routines, martial arts, walking cycles, and subtle gestures. It preserves the subject's appearance consistently across all frames without identity drift, and it supports optional text prompts to adjust scene styling, lighting, and atmosphere while keeping the motion transfer intact. Kling V2.6 Pro Motion Control is well suited for social media character animation, brand mascot animation, film pre-production prototyping, digital human content creation, and educational demonstrations.
What Kling 2.6 Pro Motion Control supports
Motion Transfer
Extracts motion paths from a reference video clip and applies them frame-by-frame to a static subject image, supporting reference videos between 3 and 30 seconds in length.
Source Image Input
Accepts a static character image via URL as the animation subject, preserving the subject's appearance consistently across all generated frames without identity drift.
Reference Video Input
Takes a reference video URL to supply the motion sequence, supporting diverse movement types including dance, martial arts, walking cycles, and fine hand gestures.
Prompt-Guided Refinement
Accepts a text prompt to adjust scene styling, lighting, and atmosphere while keeping the extracted motion transfer faithful to the reference video.
Output Orientation Control
A select input lets users choose whether the output matches the reference image's framing or the reference video's aspect ratio.
Native Audio Support
A toggle option retains the original audio track from the reference video or produces silent output, controlled via a toggleGroup input.
3D Body Reconstruction
Uses a proprietary 3D face and body reconstruction system to accurately map human faces and full-body movements from 2D inputs, enabling precise rendering of fast and intricate actions.
30 FPS Video Output
Generates video at a native 30 frames per second using a Diffusion Transformer Architecture, maintaining smooth and coherent motion transitions throughout the clip.
Ready to build with Kling 2.6 Pro Motion Control?
Get Started FreeCommon questions about Kling 2.6 Pro Motion Control
What inputs does Kling V2.6 Pro Motion Control require?
The model requires a source image URL (the character to animate) and a reference video URL (the motion source). Optional inputs include a text prompt for scene styling, a select input for output orientation, and a toggle for audio handling.
How long can the reference video be?
The model accepts reference videos between 3 and 30 seconds in length. The motion sequence from the full clip is captured and applied to the subject image.
What is the context window for this model?
The model has a context window of 1,000 tokens, as specified in its metadata.
When was this model trained?
According to the metadata, the model's training date is August 2025.
Does the model preserve the identity of the subject across frames?
Yes. The model is designed to keep the subject's appearance consistent across all generated frames, with no identity drift, using its 3D face and body reconstruction system.
What types of motion does the model support?
The model supports a wide range of movement types including dance routines, martial arts, walking cycles, subtle gestures, and complex choreography involving precise hand movements.
Documentation & links
Parameters & options
Description of what to exclude from the video.
Explore similar models
Start building with Kling 2.6 Pro Motion Control
No API keys required. Create AI-powered workflows with Kling 2.6 Pro Motion Control in minutes — free.