comfyui

Automates image, video and audio generation workflows using ComfyUI and comfy-cli.

9|3|Updated May 18, 2026
One-click install
npx skills add https://github.com/jordanhubbard/mac --skill comfyui-jordanhubbard
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/jordanhubbard/mac/tree/main/src/mac/_hermes/skills/creative/comfyui
Command: npx skills add https://github.com/jordanhubbard/mac --skill comfyui-jordanhubbard

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires comfyui, comfy-cli, stable-diffusion, sdxl, flux, animate_diff, hunyuan, wan, audio_craft, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies the process of generating images, video, and audio content using ComfyUI, a powerful tool that leverages the official comfy-cli for setup and execution.

Core Features & Use Cases

  • Image Generation: Create custom images using Stable Diffusion, SDXL, Flux, SD3, and other models.
  • Video Generation: Produce video content with AnimateDiff, Hunyuan, Wan, and other video generation models.
  • Audio Generation: Generate audio content using various audio generation models.
  • Use Case: Imagine you want to create a video of a 3D-animated character performing a dance. Use this Skill to generate the necessary frames, combine them into a video, and output the final result.

Quick Start

Generate a video using the AnimateDiff model with the following command:

python3 scripts/run_workflow.py --workflow workflows/animatediff_video.json --args '{"prompt": "a dancing character", "seed": 12345, "steps": 50}' --output-dir ./video_output

Frequently Asked Questions about comfyui

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate video with AnimateDiff using ComfyUI workflows?

To generate video with AnimateDiff using ComfyUI workflows, execute a Python script that passes the JSON workflow file, prompt arguments, and output directory to the comfy-cli for automated frame generation and video compilation.

Can I use Stable Diffusion and SDXL models for image generation with comfy-cli?

Yes, you can use Stable Diffusion and SDXL models for image generation with comfy-cli. The framework automates setup and workflow execution to produce custom images using these and other models like Flux and SD3.

What do I need to set up before generating audio with ComfyUI?

Before generating audio with ComfyUI, you need to install the comfy-cli and configure the required audio generation models. The framework automates lifecycle management and workflow execution for audio synthesis.

What is the best way to automate image and video creation using ComfyUI?

The best way to automate image and video creation using ComfyUI is utilizing the official comfy-cli to manage setup and execute generation workflows, which processes frames and outputs final media content automatically.

Does ComfyUI support Hunyuan and Wan models for video generation?

Yes, ComfyUI supports Hunyuan and Wan models for video generation. The framework integrates these models within its automated workflows to produce video content directly through the comfy-cli.

Why use comfy-cli for managing ComfyUI workflows instead of manual execution?

Using comfy-cli for managing ComfyUI workflows automates environment setup, lifecycle management, and workflow execution, eliminating manual configuration and streamlining the generation of images, video, and audio.