skills.rest
doany-ai
doany-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

controlnet-pose

Routes pose-conditioned generation tasks to RunComfy model APIs via CLI inputs and outputs to a user-specified directory.

5|2|Updated May 18, 2026
Search Tags:#workflow#image-generation#video-generation#controlnet#motion-transfer#pose-conditioning#runcomfy-cli
One-click install
npx skills add https://github.com/doany-ai/skills --skill controlnet-pose-doany-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: controlnet-pose
Source: https://github.com/doany-ai/skills/tree/main/controlnet-pose
Command: npx skills add https://github.com/doany-ai/skills --skill controlnet-pose-doany-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pose-conditioned generation of images or video using RunComfy, enabling creators to transfer poses, skeletons, or motion references onto characters.

Core Features & Use Cases

  • Route selection between video pose transfer (Kling Motion Control Pro/Standard, Wan Animate) and image pose-conditioned generation (Z-Image Turbo ControlNet LoRA).
  • Supports multiple control modalities (pose skeletons, depth maps, canny edges) and provides suggested workflows via comfyUI references.
  • Use cases include creating pose-consistent animation, stylized character poses, and pose-guided image generation for concept art.

Quick Start

Provide a source pose reference (video or image) and a target character, then run the RunComfy CLI to generate outputs into a specified directory.

Frequently Asked Questions about controlnet-pose

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

FAQPage Schema
How do I transfer a pose from a reference video to a target character?▼

Pose-conditioned generation applies a pose skeleton, depth map, or canny edge from a reference input onto a target character, using RunComfy CLI and models like Z-Image Turbo ControlNet LoRA to maintain structural consistency.

What inputs do I need to run pose-conditioned image generation?▼

You need a control image URL containing your pose reference and a target character image, which the RunComfy CLI processes to output pose-guided images into a specified directory.

Can I use canny edges and depth maps for pose conditioning?▼

Yes, pose conditioning supports multiple control modalities including canny edges, depth maps, and pose skeletons, allowing flexible structural guidance for generating consistent character animation and concept art.

Does RunComfy CLI support both image and video pose transfer?▼

Yes, RunComfy CLI supports both video pose transfer using Kling Motion Control Standard or Pro and image pose-conditioned generation using Z-Image Turbo ControlNet LoRA based on your input type.

Why use Z-Image Turbo ControlNet LoRA for pose-guided image generation?▼

Z-Image Turbo ControlNet LoRA is used for image pose-conditioned generation to accurately transfer pose references onto stylized characters, making it ideal for creating consistent concept art and character poses.

Related Skills

Explore More Design & Creative Skills→
prime-skillsprime-skills
31

controlnet-pose

Route pose-conditioned image and video generation through RunComfy models.

Official
Advanced
agentspace-soagentspace-so
31

controlnet-pose

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

Official
Intermediate
jackspacejackspace
16

comfyui-workflow-helper

Guide ComfyUI workflow creation, node configuration, and optimization.

Community
Advanced
runcomfy-comruncomfy-com
12

controlnet-pose

Generates pose-conditioned images or video motion transfers using RunComfy CLI and JSON inputs.

Official
Intermediate