comfyui

Execute and monitor ComfyUI workflows on local or cloud servers.

13|3|Updated May 12, 2026
One-click install
npx skills add https://github.com/kevinnft/ai-agent-skills --skill comfyui-kevinnft
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/kevinnft/ai-agent-skills/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/kevinnft/ai-agent-skills --skill comfyui-kevinnft

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Coordinate and automate end-to-end ComfyUI workflows across local and cloud environments, enabling parameter injection, execution monitoring, and output retrieval with resilient error handling.

Core Features & Use Cases

  • End-to-end workflow orchestration: inject parameters, submit to a local server or Comfy Cloud, monitor progress, and download outputs.
  • Cloud and local routing: automatic API-key handling, endpoint renames, and safe redirects to keep credentials secure.
  • Dependency visibility: surface missing models, embeddings, and custom nodes, with guidance to install or fetch required assets.
  • Scripted extension: leverage the included scripts/references to customize onboarding, testing, and batch experiments.

Quick Start

Install the skill and run a sample workflow using the included example workflow and the run_workflow.py helper.

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I automate ComfyUI workflows to run on cloud servers?

You can automate ComfyUI workflows by injecting parameters and submitting jobs to local or cloud servers with automatic API-key routing. The execution layer monitors WebSocket progress and handles HTTP retries to securely retrieve generated image and video outputs.

What is the best way to manage missing models and custom nodes in ComfyUI pipelines?

Managing missing ComfyUI dependencies involves detecting absent models, embeddings, and custom nodes during workflow execution. The system surfaces these missing assets and provides actionable guidance to install or fetch required components for your pipeline.

Can I execute batch image generation pipelines using a CLI helper?

Yes, you can execute batch image generation pipelines using the included run_workflow.py CLI helper. The scripted extension lets you customize onboarding, automate batch experiments, and submit multiple parameter variations to local or cloud ComfyUI servers.

Does ComfyUI workflow automation handle HTTP and WebSocket connection failures?

ComfyUI workflow automation includes robust retry logic designed for HTTP and WebSocket interactions. This resilient error handling manages connection failures during execution monitoring to ensure pipeline completion across both local and cloud environments.

Do I need an API key to route image generation workflows to Comfy Cloud?

Yes, an API key is required to route image generation workflows to Comfy Cloud. The orchestration layer manages automatic API-key handling, endpoint renames, and safe redirects to keep your cloud credentials secure during execution.

Why does my ComfyUI workflow fail when moving between local and cloud environments?

ComfyUI workflows often fail across environments due to missing dependencies or incorrect path handling. The automation enforces safe path handling, detects missing models and custom nodes, and manages cloud routing to prevent these execution failures.