What problem does it solve? Conditioning AI generation on a specific pose, skeleton, depth map, or motion reference requires choosing the right model and routing inputs correctly, which is hard to do manually across video and image models. ## Core Features & Use Cases - Video motion transfer: Route to Kling 2-6 Motion Control Pro/Standard to transfer a reference video's motion and blocking onto a target character image. - Image pose conditioning: Use Z-Image Turbo ControlNet LoRA to generate images conditioned on OpenPose, DWPose, canny, or depth control images. - Stylized animation: Route to Wan 2-2 Animate for audio-driven character animation with pose conditioning. - Use Case: Transfer the choreography from a dance reference video onto an illustrated character, or generate a samurai illustration locked to a specific OpenPose skeleton. ## Quick Start Ask the agent to transfer the motion from a reference video onto a character image, or to generate an image conditioned on a pose skeleton control image, using the runcomfy CLI.
