comfyui

Automate ComfyUI workflows by injecting parameters and retrieving outputs.

Updated May 21, 2026
One-click install
npx skills add https://github.com/samlaggz/hermes-agent-sam --skill comfyui-samlaggz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/samlaggz/hermes-agent-sam/tree/main/backup/skills/creative/comfyui
Command: npx skills add https://github.com/samlaggz/hermes-agent-sam --skill comfyui-samlaggz

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates the setup, orchestration, and execution of ComfyUI workflows across local and cloud environments, reducing manual steps and configuration drift.

Core Features & Use Cases

  • Install, launch, and manage ComfyUI via the included scripts and CLI.
  • Inject parameters, run API-format workflows, and fetch outputs (images/videos) for automation pipelines.
  • Use-case: prototype end-to-end generative pipelines for images, video, and audio with reproducible results.

Quick Start

Install and launch locally with the provided setup script, then run a sample workflow with run_workflow.py.

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 for image and video generation?

You can automate ComfyUI workflows by injecting parameters into API-format pipelines and submitting them to local or cloud servers for image and video generation, then fetching the outputs.

Can I run ComfyUI workflows on a cloud server instead of locally?

Yes, ComfyUI workflow automation supports cloud-aware routing, allowing you to submit API-format workflows to either local or cloud servers and retrieve the generated outputs.

Do I need Python 3 installed to orchestrate ComfyUI pipelines?

Yes, you need Python 3 and a ComfyUI installation to orchestrate pipelines, as the automation skill loads its operational context and interacts with the REST and WebSocket APIs for execution.

What's the best way to manage custom nodes and embeddings in automated generative pipelines?

Automating end-to-end generative pipelines supports models, embeddings, and custom nodes, allowing you to prototype multi-node pipelines with reproducible results for images, video, and audio.

How does the ComfyUI automation skill execute multi-node pipelines?

The automation skill executes multi-node pipelines by loading operational context, injecting user-provided parameters, and interacting with the REST and WebSocket APIs to manage execution and retrieve outputs.