skills.rest
brillianodhiya
brillianodhiyaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

controlnet-pose

Generates pose-conditioned images and motion-transfer videos via the RunComfy CLI.

Updated Jun 11, 2026
Search Tags:#image generation#video generation#ControlNet#motion control#runcomfy#openpose#pose transfer
One-click install
npx skills add https://github.com/brillianodhiya/VisionScript --skill controlnet-pose-brillianodhiya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: controlnet-pose
Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/controlnet-pose
Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill controlnet-pose-brillianodhiya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Conditioning AI image or video generation on a specific pose, skeleton, depth map, or motion reference requires choosing the right model and wiring the correct inputs, which is error-prone without guidance. ## Core Features & Use Cases - Video motion transfer: Route to Kling 2-6 Motion Control Pro/Standard to transfer a reference video's motion onto a target character image. - Image pose conditioning: Use Z-Image Turbo ControlNet LoRA with OpenPose, DWPose, canny, or depth control images for pose-locked generation. - Stylized animation: Wan 2-2 Animate handles audio-driven character animation with pose conditioning. - Use Case: Transfer a dance choreography video onto an illustrated mascot character, or generate a samurai image locked to a specific OpenPose skeleton. ## Quick Start Ask the agent to generate an image of a character conditioned on your OpenPose skeleton image URL using the controlnet-pose skill.

Frequently Asked Questions about controlnet-pose

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transfer motion from a video onto a character image?▼

Use Kling 2-6 Motion Control Pro via the runcomfy CLI, passing a reference_video_url for the motion and a character_image_url for identity. The model produces video of the target character performing the reference motion and blocking.

How to generate an image conditioned on an OpenPose skeleton?▼

Use the Z-Image Turbo ControlNet LoRA endpoint with a prompt and a control_image_url pointing to your OpenPose, DWPose, canny, or depth image. Generate the control image separately with a pose-estimation tool, host it, and pass the URL.

Kling Motion Control vs Wan 2-2 Animate for character animation?▼

Kling Motion Control suits photoreal subjects and direct video motion transfer, while Wan 2-2 Animate is a community model for stylized character animation with audio-driven and pose conditioning. Pick Kling for realism, Wan for mascots and illustration.

Can I combine multiple ControlNet conditions like pose plus depth?▼

The CLI routes cover single-condition generation only. Multi-condition stacks such as pose plus depth plus reference require hosted ComfyUI workflows on runcomfy.com, which are GUI-based and not reachable through the CLI.

Why does runcomfy CLI return exit code 77?▼

Exit code 77 means you are not signed in or the token was rejected. Run runcomfy login to authenticate, or set the RUNCOMFY_TOKEN environment variable in CI and container environments.

Related Skills

Explore More Design & Creative Skills→
agentspace-soagentspace-so
31

controlnet-pose

Generate pose-conditioned images or videos using OpenPose, depth, or canny controls.

Official
Intermediate
hanzoaihanzoai

faceswap

Swap a face from a source image into a target video via HeyGen API.

Official
Advanced
ModelsLabModelsLab
10

modelslab-deepfake

Swap faces in images and videos via the Deepfake API.

Official
Advanced
hatch3rhatch3r
26

hatch3r-visual-refactor

Execute design-faithful UI refactors with WCAG AA and responsiveness verification.

Official
Advanced