ai-avatar-video
๐ฏSkillfrom prime-skills/runcomfy-agent-skills
Installation
npx vibeindex add prime-skills/runcomfy-agent-skills --skill ai-avatar-videonpx skills add prime-skills/runcomfy-agent-skills --skill ai-avatar-video~/.claude/skills/ai-avatar-video/SKILL.md
|A skill that creates AI avatar, talking-head, and lip-sync videos by routing across RunComfy models including OmniHuman, Wan 2-7, HappyHorse, and Seedance v2, selecting the best model based on whether you have pre-recorded audio, a written script, or need cinematic composition.
Overview
This skill creates AI avatar and talking-head videos through RunComfy's CLI by intelligently routing across multiple audio-driven avatar models. It classifies user intent (pre-recorded audio vs. written script, photoreal portrait vs. stylized character, single shot vs. cinematic composition) and selects the optimal model: OmniHuman for standard audio-driven avatars, HappyHorse for script-only generation without an audio file, Wan 2-7 for full scene control with audio sync, Seedance v2 Pro for multi-modal cinematic compositions, and Wan 2-2 Animate for stylized character animation.
Key Features
- Intelligent model routing: Automatically selects between 5 avatar models (OmniHuman, HappyHorse 1.0, Wan 2-7, Seedance v2 Pro, Wan 2-2 Animate) based on user intent
- Audio-driven avatar generation: Feed a portrait image + audio file to OmniHuman and get a video where the subject speaks naturally with synchronized lip movement
- Script-to-video without audio: HappyHorse 1.0 generates speech in-pass from a written script, no external audio file required
- Cinematic multi-modal composition: Seedance v2 Pro supports up to 9 reference images, 3 reference videos, and 3 reference audio tracks for complex ad-creative and monologue scenes
- Stylized character support: Wan 2-2 Animate handles illustrated characters, anime, and mascots with full-body audio-driven animation
- Common pattern recipes: Includes ready-to-use workflows for UGC product ads, multi-language brand videos, mascot animation, and talking heads from generated portraits
Who is this for?
- Content creators producing UGC-style product demos, virtual presenter videos, or multi-language dubbed clips from a single portrait
- Marketing teams building brand spokesperson videos, ad creatives, or explainer content with AI-generated talking heads
- Developers integrating audio-driven avatar generation into automated content pipelines via the RunComfy CLI
Same repository
prime-skills/runcomfy-agent-skills(25 items)
SKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that automatically selects the best model (Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, or Lucy Edit Restyle) based on what the user wants to do, from general restyling and background swaps to precise motion transfer and outfit changes.
A smart intent-routing skill that animates still images on RunComfy by selecting the optimal model: HappyHorse 1.0 I2V for general portrait and product animation with native audio, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition with image, video, and audio references.
A skill for generating images with Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family on RunComfy, optimized for rapid iteration, batch ideation, in-image typography rendering, and optional web-grounded context with support for resolutions from 0.5K to 4K.
A smart intent-routing skill for image editing on RunComfy that selects the optimal model from Nano Banana Edit (batch up to 20 images), GPT Image 2 Edit (multilingual text rewrite, multi-ref composition), Flux Kontext Pro (single-shot precise local edit), or Z-Image Turbo Inpaint (mask-driven region edit) based on user intent.
A Claude Code skill that enables precise single-image editing using Black Forest Labs's Flux 1 Kontext Pro model through the RunComfy CLI, with built-in prompting patterns for high-fidelity local edits.
A skill for generating text-to-video with Wan 2.7, Wan-AI's flagship motion model on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via custom audio tracks, smooth transition physics, prompt expansion control, and up to 1080p output at 15 seconds duration.
A Claude Code skill for generating text-to-video clips with HappyHorse 1.0 via the RunComfy CLI. HappyHorse 1.0 is currently ranked #1 on the Artificial Analysis Video Arena, producing native 1080p video with in-pass synchronized audio and multi-shot character consistency.
A Claude Code skill for generating video with Kling 3.0 via the RunComfy CLI. Covers all six Kling 3.0 endpoints across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video), with native synchronized audio and multi-shot character consistency.
A Claude Code skill that generates custom OpenAI Codex Pets from a single reference image via the RunComfy CLI. It produces a Codex-compatible spritesheet (1536x1872, 8 columns x 9 rows) and pet.json manifest using GPT Image 2 and ImageMagick, without requiring Codex Pro or an OPENAI_API_KEY.
A Claude Code skill that acts as a smart router for AI video generation across the full RunComfy model catalog. Supports text-to-video, image-to-video, and video-extend modes with models including HappyHorse 1.0, Kling 3.0, Wan 2.7, Seedance, Veo 3.1, and more.