Generate talking-photo digital human videos with Dreamina (ByteDance OmniHuman) via AceDataCloud API. Use when animating a portrait image with a driving audio track to produce a lip-synced video where the person speaks. Supports mask-based multi-person targeting and async task polling.
Install
npx skills add AceDataCloud/Skills --skill dreamina-videonpx skills add AceDataCloud/Skills --skill dreamina-video -a claude-code -gnpx skills add AceDataCloud/Skills --skill dreamina-video -a codex -ggemini skills install https://github.com/AceDataCloud/Skills.git --path skills/dreamina-videogh skill install AceDataCloud/Skills dreamina-videogit clone --depth 1 https://github.com/AceDataCloud/Skills /tmp/AceDataCloud__Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/AceDataCloud__Skills/skills/dreamina-video ~/.claude/skills/dreamina-video # Claude Code
cp -R /tmp/AceDataCloud__Skills/skills/dreamina-video ~/.agents/skills/dreamina-video # Codex, Cursor, Gemini CLI, Copilot, OpenCode