MCKRUZ/ComfyUI-Expert

66 stars · Last commit 2026-03-18

Session-scoped Claude Code agent for ComfyUI video production — 12 specialized skills for image gen, video, voice cloning, LoRA training, and publishing

README preview

# VideoAgent - ComfyUI Video Production Orchestrator

A session-scoped AI orchestrator for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) that turns Claude into a senior video production technical director. It routes natural-language requests to 13 specialized skill modules covering the full pipeline: character image generation, video production, voice synthesis, LoRA training, and publishing -- all driven by [ComfyUI](https://github.com/comfyanonymous/ComfyUI).

## Why This Exists

Producing AI-generated video with ComfyUI involves juggling dozens of models, custom nodes, prompt styles, and hardware constraints. VideoAgent wraps all of that domain knowledge into a structured skill system that Claude reads on demand, so you can say things like:

- _"Generate a photorealistic portrait of a dog using InstantID"_
- _"Make a talking head video where she says 'Welcome to my channel'"_
- _"Train a LoRA from these 20 reference images"_
- _"Check for new ComfyUI video models released this month"_

...and get validated, hardware-aware ComfyUI workflows without memorizing node names or VRAM budgets.

## How It Works

```
video-agent.bat
  |

View full repository on GitHub →