ControlNet & Pose

Pose-conditioned image and video generation routed across Kling Motion Control, Wan 2-2 Animate, and Z-Image ControlNet LoRA.

- Routes video pose-transfer requests to Kling 2-6 Motion Control (Pro or Standard) to apply reference video motion onto a target character, or to Wan 2-2 Animate for audio-driven stylized animation with pose conditioning

- Routes still-image pose-conditioned generation to Z-Image Turbo ControlNet LoRA, accepting OpenPose, DWPose, canny, or depth control images paired with a text prompt

- Triggered by keywords including "controlnet," "pose control," "openpose," "motion control," "depth control," and related pose-driven or skeleton-based generation requests

- Invoked via runcomfy run CLI with reference video/character URLs or control image URLs and prompts; supports multi-condition ControlNet stacks via dedicated ComfyUI workflows for complex conditioning needs

ControlNet & Pose

Condition image or video generation on a pose, skeleton, or motion reference. This skill routes across the pose-driven Model API endpoints reachable today and points the agent at ComfyUI workflows for richer ControlNet rigs.

runcomfy.com · Kling motion control · CLI docs

Powered by the RunComfy CLI

# 1. Install (see runcomfy-cli skill for details)
npm i -g @runcomfy/cli      # or:  npx -y @runcomfy/cli --version

# 2. Sign in
runcomfy login              # or in CI: export RUNCOMFY_TOKEN=<token>