comfyui

Deploy, configure, and execute ComfyUI generative media workflows locally or in the cloud.

2|Updated May 10, 2026
One-click install
npx skills add https://github.com/freedomw1987/tree_monstor --skill comfyui-freedomw1987
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/freedomw1987/tree_monstor/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/freedomw1987/tree_monstor --skill comfyui-freedomw1987

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, websocket-client, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill eliminates the complexity of setting up and operating ComfyUI for generative media tasks, which normally requires manual server management, workflow JSON formatting, model dependency tracking, and API authentication for local or cloud execution.

Core Features & Use Cases

  • Full Lifecycle Management: Install, launch, and manage ComfyUI servers and custom nodes using the official comfy-cli, with hardware-aware setup scripts that recommend local vs cloud deployment based on GPU VRAM.
  • Workflow Execution & Parameter Injection: Run API-format ComfyUI workflows with dynamic parameter injection (prompts, seeds, dimensions), batch sweeps, img2img/inpainting support, and real-time WebSocket progress monitoring.
  • Cross-Platform Cloud & Local Support: Seamlessly switch between local ComfyUI instances and Comfy Cloud hosted services, with automatic URL routing, auth header handling, and model list normalization across both environments.

Quick Start

Use the comfyui skill to generate an image by first running the hardware check script to determine if your machine should use local ComfyUI or Comfy Cloud, then execute a sample workflow with your custom prompt and save the resulting image to an output directory.

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I automate Stable Diffusion and Flux workflow execution across local and cloud environments?

To automate Stable Diffusion and Flux workflow execution, this Skill deploys and configures ComfyUI servers using comfy-cli, dynamically injecting API-format workflow parameters and routing execution between local GPU hardware and Comfy Cloud based on VRAM availability.

What hardware do I need to run ComfyUI generative media workflows locally?

Running ComfyUI generative media workflows locally requires Python 3 and GPU hardware with sufficient VRAM to support Stable Diffusion, Flux, SD3, Wan, and Hunyun model families. A hardware check script evaluates your system to recommend local versus cloud deployment.

Can I monitor real-time progress for batch image generation and inpainting tasks?

Yes, you can monitor real-time progress for batch image generation and inpainting tasks using the WebSocket client integration, which provides live execution updates as ComfyUI processes your dynamically injected parameters across local or cloud environments.

Does this support img2img and video generation with Wan and Hunyuan models?

Yes, it supports img2img, inpainting, and video generation using the Wan and Hunyuan model families, alongside Stable Diffusion, Flux, and SD3. It normalizes model lists and handles authentication headers automatically for both local and Comfy Cloud instances.

What is the best way to manage ComfyUI custom nodes and server dependencies?

The best way to manage ComfyUI custom nodes and server dependencies is using the official comfy-cli through this Skill, which handles full lifecycle installation, launch, and configuration while tracking model dependencies required for your generative workflows.

Why does my ComfyUI workflow fail when switching between local instances and Comfy Cloud?

ComfyUI workflow execution can fail during environment switching due to mismatched URL routing or authentication headers. This Skill resolves this by automatically handling auth headers, normalizing model lists, and managing API access across local and Comfy Cloud platforms.