ai-avatar-video
Create AI Avatar Videos with RunComfy
Creating lip-synced avatar videos often requires choosing the right model and input format. This skill routes requests to RunComfy models and provides ready CLI invocations.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "ai-avatar-video" from https://skillstore.io/skills/runcomfy-com-ai-avatar-video.md and its manifest at https://skillstore.io/api/skills/runcomfy-com-ai-avatar-video/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 "ai-avatar-video". I have a presenter portrait and a clean voiceover file for a 15-second product intro.
Expected outcome:
The skill recommends OmniHuman, explains why portrait plus audio fits, and returns a RunComfy command with image and audio inputs.
Using "ai-avatar-video". I need a mascot to say a scripted welcome line, but I do not have a recorded voice file.
Expected outcome:
The skill recommends HappyHorse for script-driven generation and gives a short prompt that quotes the spoken line clearly.
Using "ai-avatar-video". I want a cinematic monologue using a subject photo, voice reference, and widescreen framing.
Expected outcome:
The skill recommends Seedance v2 Pro, maps each reference asset to its role, and suggests lens, lighting, and motion language.
Security Audit
SafeAll 93 static findings were adjudicated as false positives. The backtick findings are Markdown code spans or fences, hardcoded URLs are documentation or example RunComfy links, token storage is disclosed CLI behavior, and the “Avoid for” lines are model-routing guidance. No prompt injection attempt or malicious data-exfiltration intent was found in SKILL.md.
Risk Factors
⚙️ External commands (55)
🌐 Network access (31)
📁 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/runcomfy-com-ai-avatar-video/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/runcomfy-com-ai-avatar-video?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/runcomfy-com-ai-avatar-video?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/runcomfy-com-ai-avatar-video/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/runcomfy-com-ai-avatar-video.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
runcomfy-com. (2026). ai-avatar-video security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/runcomfy-com-ai-avatar-video/audits/4BibTeX citation
@techreport{runcomfy-com-runcomfy-com-ai-avatar-video-2026,
author = {runcomfy-com},
title = {ai-avatar-video security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/runcomfy-com-ai-avatar-video/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: "ai-avatar-video security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "runcomfy-com"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/runcomfy-com-ai-avatar-video/audits/4"
identifiers:
- type: other
value: "skillstore:runcomfy-com-ai-avatar-video:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
11 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
runcomfy-com-ai-avatar-video
2026-08-21
inference-sh-skills-ai-avatar-video
2026-08-21
infsh-skills-ai-avatar-video
2026-08-21
inference-skills-ai-avatar-video
2026-08-21
skills-shell-ai-avatar-video
2026-08-21
halt-catch-fire-ai-avatar-video
2026-08-21
qu-skills-ai-avatar-video
2026-08-21
agentspace-so-ai-avatar-video
2026-08-21
doany-ai-ai-avatar-video
2026-08-21
inference-sh-ai-avatar-video
2026-08-21
101-skills-ai-avatar-video
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Produce Product Presenter Clips
Create short UGC-style videos from a presenter portrait and a clean voiceover file.
Localize Brand Videos
Generate multiple dubbed clips from the same portrait by changing the audio track.
Animate Stylized Characters
Choose character-focused or cinematic models for mascots, illustrated subjects, and reference-driven scenes.
Try These Prompts
Create an AI avatar video from this portrait URL and this voiceover URL. Choose the best RunComfy model and give me the command to run.
I only have this short script. Pick a RunComfy route that can generate speech in the video and format a concise prompt for a vertical talking-head clip.
Compare the RunComfy avatar routes for this project. Explain which model fits a photoreal portrait, a stylized character, and a cinematic monologue.
Plan a three-video avatar campaign using my reference subject, voice tracks, aspect ratios, and brand tone. Select models and provide generation steps for each deliverable.
Best Practices
- Confirm rights to the subject likeness and speaker voice before generating avatar videos.
- Use clean voiceover audio and clear portrait framing for stronger lip sync.
- Keep spoken scripts short and test one clip before generating a full sequence.
Avoid
- Do not animate or imitate real people without consent.
- Do not use mixed music beds when precise mouth sync matters.
- Do not choose cinematic multi-reference models for simple portrait plus audio jobs.
Frequently Asked Questions
Does this skill create video files directly?
Which model is the default choice?
Can it work without an audio file?
Can it animate illustrated characters?
What inputs should I prepare?
What safety checks should users apply?
Developer Details
Author
runcomfy-comLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
4 downloads · 0 views
File structure
📄 SKILL.md