Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject).
Install
npx skills add prime-skills/runcomfy-agent-skills --skill ai-avatar-videonpx skills add prime-skills/runcomfy-agent-skills --skill ai-avatar-video -a claude-code -gnpx skills add prime-skills/runcomfy-agent-skills --skill ai-avatar-video -a codex -ggemini skills install https://github.com/prime-skills/runcomfy-agent-skills.git --path ai-avatar-videogh skill install prime-skills/runcomfy-agent-skills ai-avatar-videogit clone --depth 1 https://github.com/prime-skills/runcomfy-agent-skills /tmp/prime-skills__runcomfy-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/prime-skills__runcomfy-agent-skills/ai-avatar-video ~/.claude/skills/ai-avatar-video # Claude Code
cp -R /tmp/prime-skills__runcomfy-agent-skills/ai-avatar-video ~/.agents/skills/ai-avatar-video # Codex, Cursor, Gemini CLI, Copilot, OpenCode