comfyui

Execute image, video, and audio generation workflows via ComfyUI REST and WebSocket APIs.

Updated Jun 17, 2026
One-click install
npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill comfyui-cxnaive
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/cxnaive/hermes-agent-llbot/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill comfyui-cxnaive

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 monitor ComfyUI pipelines without manual web interface interaction.

Core Features & Use Cases

  • Workflow Execution: Run image, video, and audio generation pipelines via REST/WebSocket APIs.
  • Lifecycle Management: Install, launch, and verify ComfyUI servers and custom nodes using the official CLI.
  • Batch Processing: Execute complex sweeps or variations across multiple seeds and parameters in parallel.

Quick Start

Use the comfyui skill to run the workflow file named flux_dev.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 automate stable diffusion workflows without using the web interface?

You can automate stable diffusion workflows by executing generative AI pipelines directly via the ComfyUI REST and WebSocket APIs. This allows you to run, manage, and monitor image, video, and audio generation without manual web interface interaction.

What is the best way to run batch processing across multiple seeds for generative AI?

The best way to run batch processing for generative AI is to execute complex sweeps or variations across multiple seeds and parameters in parallel. This is facilitated by injecting parameters into local or cloud-hosted diffusion pipelines.

Can I manage ComfyUI server lifecycle and custom node dependencies programmatically?

Yes, you can manage the ComfyUI server lifecycle programmatically. The skill installs, launches, and verifies ComfyUI servers and custom nodes using the official CLI, handling dependencies for local or cloud-hosted environments.

How does real-time monitoring work for video generation pipelines using WebSocket?

Real-time monitoring for video generation pipelines works by connecting to the ComfyUI WebSocket APIs. This allows you to track the progress and status of complex diffusion pipelines as they execute in real-time.

Do I need the requests and websocket-client libraries to execute ComfyUI workflows?

Yes, you need the requests and websocket-client libraries to interact with the ComfyUI APIs. These dependencies are required to execute generative AI workflows and facilitate real-time monitoring over WebSocket connections.

How do I inject custom parameters into a flux_dev.json workflow file?

You inject custom parameters into a flux_dev.json workflow file by passing them through the API request. The skill manages parameter injection to execute generative AI workflows with specific prompts or variables.