跳至主要内容
返回 Skills 索引

ELELAND INTELLIGENCE

SKILL 131 OF 500 · github

ai-avatar-video

prime-skills/runcomfy-agent-skills

> 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). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced character,

348,547次安装

第 131 位,共 500 · 前 26.2%

在 Top 500 安装量曲线上的位置(对数刻度) · 数据截至 2026-08-24

安全审计

SAFE

The skill provides instructions for using the runcomfy CLI to generate AI avatar and talking-head videos. It defines clear routing logic for different user intents and includes security guidance for handling external media assets and API credentials. The primary risk identified is potential indirect prompt injection via user-supplied image or audio files.

审计方 Gen Agent Trust Hub · 2026-07-13 · pass

MARKET SIGNALS · SKILL INDEX