controlnet-pose
Create Pose-Controlled Images and Videos
Pose and motion control workflows can be hard to route across image and video models. This skill selects the right RunComfy path and prepares clear CLI guidance.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "controlnet-pose" from https://skillstore.io/skills/doany-ai-controlnet-pose.md and its manifest at https://skillstore.io/api/skills/doany-ai-controlnet-pose/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "controlnet-pose". I have a dance reference video and a mascot image.
Expected outcome:
The skill selects Kling Motion Control, asks for hosted asset URLs, and prepares motion-transfer CLI guidance.
Using "controlnet-pose". I want a portrait that follows my OpenPose skeleton.
Expected outcome:
The skill selects Z-Image Turbo ControlNet LoRA and describes the needed prompt and control image input.
Using "controlnet-pose". I need pose, depth, canny, and a character reference together.
Expected outcome:
The skill explains that this needs a RunComfy ComfyUI workflow instead of the simple CLI routes.
Security Audit
SafeThe static command findings are false positives caused by Markdown code fences, inline model names, and documented RunComfy CLI examples. The URL findings are expected RunComfy documentation, model catalog links, or placeholder asset URLs, and no prompt injection or covert exfiltration intent was found. The token path note documents normal CLI credential storage with restrictive permissions, not hidden-file abuse.
Risk Factors
⚙️ External commands (33)
🌐 Network access (23)
📁 Filesystem access (2)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/doany-ai-controlnet-pose/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-controlnet-pose?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-controlnet-pose?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-controlnet-pose/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-controlnet-pose.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
doany-ai. (2026). controlnet-pose security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-controlnet-pose/audits/4BibTeX citation
@techreport{doany-ai-doany-ai-controlnet-pose-2026,
author = {doany-ai},
title = {controlnet-pose security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/doany-ai-controlnet-pose/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "controlnet-pose security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/doany-ai-controlnet-pose/audits/4"
identifiers:
- type: other
value: "skillstore:doany-ai-controlnet-pose:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
3 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
runcomfy-com-controlnet-pose
2026-08-21
doany-ai-controlnet-pose
2026-08-21
agentspace-so-controlnet-pose
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Transfer Choreography
Apply a performer video to a target character image for draft or final motion-control video.
Pose Lock an Illustration
Use an OpenPose, DWPose, canny, or depth control image to guide a still generation.
Plan a Model Route
Compare RunComfy routes and choose the endpoint that matches asset type, style, and quality needs.
Try These Prompts
Create a still image from this hosted pose control image and prompt: [control URL], [prompt].
Transfer the motion from this reference video to this character image: [video URL], [image URL].
Compare the RunComfy route for this project: [video or still], [style], [control type], [quality target].
Plan a pose workflow with pose, depth, and character reference. Tell me if CLI endpoints are enough.
Best Practices
- Use clean, single-subject reference videos with steady framing for motion transfer.
- Host only assets you are allowed to send to RunComfy cloud endpoints.
- Confirm model inputs before running the CLI, especially URLs, prompt text, and output directory.
Avoid
- Do not send private or licensed assets without permission.
- Do not use video motion routes for still image pose control.
- Do not expect the CLI routes to handle pose, depth, canny, and reference images together.