comfyui

Execute ComfyUI API-format workflows via REST/WebSocket with parameter injection.

Updated May 26, 2026
One-click install
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill comfyui-ruiyangruiyi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill comfyui-ruiyangruiyi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of installing, validating, and running ComfyUI workflows so you can reliably generate images, video, and audio without manually wiring parameters or debugging missing nodes and models.

Core Features & Use Cases

  • Workflow execution with parameter injection: run API-format ComfyUI workflows while safely injecting controllable parameters (prompt text, seed, steps, CFG/denoise, dimensions, model names).
  • Dependency verification and auto-fixing: detect missing custom nodes, checkpoints, and embeddings against a live ComfyUI server (local or Comfy Cloud) and produce actionable remediation commands.
  • Local vs Cloud routing + monitoring: automatically route requests to the correct REST/WebSocket endpoints, stream downloads, and watch progress in real time.
  • Creative outputs beyond images: supports advanced pipelines like img2img, inpainting, upscaling, AnimateDiff, and modern video workflows by selecting the right output nodes and timeouts.

Quick Start

Ask for a ComfyUI image generation by running the hosted workflow flux_dev_txt2img.json with prompt text "a futuristic city at night" and saving outputs to ./outputs on Comfy Cloud using your COMFY_CLOUD_API_KEY.

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I run ComfyUI API-format workflows to generate images and video?

To run ComfyUI API-format workflows for image and video generation, execute REST/WebSocket requests with safe parameter injection for prompt text, seed, steps, and model names.

How does ComfyUI dependency checking handle missing custom nodes and embeddings?

ComfyUI dependency checking detects missing custom nodes, checkpoints, and embeddings against a live server, producing actionable remediation commands to fix the environment.

Can I use ComfyUI workflows for advanced pipelines like AnimateDiff and inpainting?

Yes, ComfyUI workflows support advanced generative pipelines like img2img, inpainting, upscaling, and AnimateDiff by selecting the right output nodes and timeouts.

How do I route ComfyUI workflow requests between local servers and cloud endpoints?

ComfyUI workflow execution automatically routes requests to the correct local or cloud REST/WebSocket endpoints, streaming downloads and watching progress in real time.

What parameters can I inject when executing ComfyUI text-to-image workflows?

When executing ComfyUI text-to-image workflows, you can safely inject controllable parameters including prompt text, seed, steps, CFG/denoise values, dimensions, and model names.

Why does my ComfyUI workflow execution fail when using advanced video pipelines?

ComfyUI workflow execution fails when required model or node dependencies are missing, but the dependency verification feature checks against the live server and provides remediation commands.