comfyui

Automate ComfyUI generative workflow lifecycle and execution via REST and WebSocket APIs.

Updated Jul 13, 2026
One-click install
npx skills add https://github.com/zangjeicy/Hermes --skill comfyui-zangjeicy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/zangjeicy/Hermes/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/zangjeicy/Hermes --skill comfyui-zangjeicy

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 the official ComfyUI CLI and complex workflow execution, allowing users to automate image, video, and audio generation without manual UI interaction.

Core Features & Use Cases

  • Workflow Execution: Run complex generative pipelines including SDXL, Flux, and video models via REST/WebSocket APIs.
  • Lifecycle Management: Automate installation, model downloading, and server health checks using the official comfy-cli.
  • Use Case: A user can trigger a batch of 50 image variations with randomized seeds and automatically save the outputs to a local directory, or perform automated dependency checks to ensure all custom nodes are installed before running a new workflow.

Quick Start

Use the comfyui skill to run the workflow file named flux_dev_txt2img.json with the prompt a beautiful sunset over mountains and save the output to the local outputs folder.

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 workflow execution without manual UI interaction?

You can automate ComfyUI workflow execution by using script-based control to inject parameters via REST and WebSocket APIs. This handles complex generative pipelines including SDXL and Flux models, enabling batch processing and real-time monitoring without manual UI interaction.

Can I run batch image generation with randomized seeds locally?

Yes, you can run batch image generation with randomized seeds locally. The system automates parameter injection and automatically saves the generated outputs to a local directory, handling the entire lifecycle from server setup to execution.

Do I need comfy-cli to manage generative video workflows?

Yes, you need comfy-cli for infrastructure management of generative video workflows. It handles automated installation, model downloading, and server health checks to ensure all custom nodes are installed before running a new workflow.

What is the best way to verify dependencies for ComfyUI custom nodes?

The best way to verify dependencies for ComfyUI custom nodes is through automated dependency checks provided by the lifecycle management system. This performs automated checks to ensure all custom nodes are installed before running a new workflow.

Does this approach work with cloud-based environments for generative AI media tasks?

Yes, this approach supports cloud-based environments for generative AI media tasks. It bridges the gap between the official CLI and workflow execution by handling server setup and parameter injection for both local and cloud-based environments.