JavaScript is disabled. Some features may not work.
Ai Avatar Video — ★ 5 GitHub Stars — Install Guide | SkillsNav
🇺🇸 English🇨🇳 中文
SkillsNav
Home

Ai Avatar Video

★ 5 repomlSafeIntermediateClaude
🤖 AI Summary

This skill accepts a user's video and audio/text input, then routes the request to the optimal RunComfy avatar model (e.g., OmniHuman, Wan 2.7) to generate a talking-head video where the avatar's lip movements sync with the provided audio.

How to Install

Claude Code:
git clone --depth 1 https://github.com/runcomfy-com/skills.git && cp skills/ ~/.claude/skills/ai-avatar-video -r
Put words in a face. This skill routes across RunComfy's audio-driven avatar models — OmniHuman, Wan 2-7 with audio_url, HappyHorse, Seedance v2 — picking the right path for the user's intent and ship

Details

Category AI/ML → ml
Sourceruncomfy-com/skills
SKILL.mdView on GitHub →
Repo Stars★ 5
Est. per Skill1 (shared across 30 skills from this repo)
DifficultyIntermediate
Risk LevelSafe

Related Skills

Works Well With

Skills from the same repository — often designed to work together