comfyui

Execute generative AI workflows via the ComfyUI REST and WebSocket API.

Updated May 4, 2026
One-click install
npx skills add https://github.com/InverterNetwork/hermes-agent --skill comfyui-inverternetwork
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/InverterNetwork/hermes-agent/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/InverterNetwork/hermes-agent --skill comfyui-inverternetwork

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill bridges the gap between complex generative AI workflows and automated execution, allowing you to run, manage, and scale image, video, and audio generation tasks without manual UI interaction.

Core Features & Use Cases

  • Automated Workflow Execution: Run complex diffusion pipelines (SDXL, Flux, AnimateDiff) via REST/WebSocket APIs.
  • Lifecycle Management: Install, launch, and monitor ComfyUI servers and custom nodes using the official CLI.
  • Use Case: Automatically generate a batch of 50 variations of a product image using a specific ControlNet workflow, then monitor the progress and download the results to your local machine.

Quick Start

Use the comfyui skill to run the workflow file named flux_dev_txt2img.json with the prompt a futuristic city skyline at sunset.

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I run stable diffusion workflows without using the ComfyUI interface?

You can execute stable diffusion workflows without manual UI interaction by sending API requests to programmatically control parameter injection, batch processing, and job monitoring for diffusion pipelines.

What is the best way to automate image and video generation pipelines via ComfyUI?

The best way to automate image and video generation is using the REST and WebSocket API to manage complex diffusion pipelines, enabling real-time job monitoring and automated batch processing.

Can I run batch processing for ControlNet workflows via the ComfyUI API?

Yes, you can programmatically run batch processing workflows like ControlNet via the API, allowing you to automatically generate multiple image variations and download the results locally.

Do I need to manually manage custom nodes and server lifecycle for automated diffusion pipelines?

No, you do not need to manually manage server lifecycle or custom nodes; the system automatically handles installation, launching, monitoring of ComfyUI servers, and model downloads.

Does this approach support generative AI video and audio synthesis alongside image generation?

Yes, this approach supports generative AI video and audio synthesis alongside image generation, executing complex workflows like AnimateDiff and SDXL directly through the API.

Why use websocket connections for stable diffusion video generation instead of standard REST?

WebSocket connections provide real-time job monitoring for video generation, allowing continuous progress tracking and immediate result retrieval compared to standard REST API polling.