Controlnet Pose

Routes pose-conditioned generation across three backends depending on what you're making. Video motion transfer (dance onto a new character, sports motion onto a cartoon) hits Kling Motion Control. Still images locked to a pose skeleton go to Z-Image ControlNet LoRA. Audio-driven character animation lands on Wan 2-2. The skill picks the route based on whether you're working with video or stills and photoreal versus stylized. Works through the runcomfy CLI, so you're feeding reference videos or OpenPose skeletons as URLs and getting output directories back. For multi-condition stacks like pose plus depth plus reference, you'll need to jump into the ComfyUI workflows directly since the CLI only handles single-condition runs.

skills.sh installs: 117.4K
GitHub stars: 11
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add agentspace-so/runcomfy-agent-skills --skill controlnet-pose --agent claude-code

Installs into .claude/skills of the current project.

Files

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>

# 3. Pose-conditioned generate
runcomfy run <vendor>/<model> \
  --input '{"reference_video_url": "...", "character_image_url": "..."}' \
  --output-dir ./out

CLI deep dive: runcomfy-cli skill.