comfyui

Execute ComfyUI image and video workflows with parameter injection and dependency validation.

19|4|Updated Apr 22, 2026
One-click install
npx skills add https://github.com/carterwayneskhizeine/hermes-agent-windows-R --skill comfyui-carterwayneskhizeine
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/carterwayneskhizeine/hermes-agent-windows-R/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/carterwayneskhizeine/hermes-agent-windows-R --skill comfyui-carterwayneskhizeine

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

ComfyUI image/video generation often stalls due to missing nodes, model folders, workflow format issues, and manual parameter wiring, so this Skill makes runs repeatable by validating dependencies, injecting parameters, and executing workflows via the ComfyUI REST/WebSocket APIs.

Core Features & Use Cases

  • Workflow execution with parameter injection: Submit API-format workflows while overriding prompt, seed, steps, CFG/guidance, dimensions, and other exposed inputs.
  • Dependency discovery and repair: Check required custom nodes, models, and prompt-embedded embeddings against a running server and suggest or auto-install missing components locally.
  • Local or Comfy Cloud execution: Route endpoints correctly for both local ComfyUI and Comfy Cloud, including streaming downloads and WebSocket progress monitoring.

Quick Start

Run the ComfyUI workflow located at workflows/sdxl_txt2img.json using a fresh prompt by telling the agent to execute run_workflow.py with the workflow file and args set to a JSON object like {"prompt":"a photorealistic robot holding a bouquet","seed":-1,"steps":30}.

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 with parameter injection?

To automate ComfyUI workflows, submit API-format workflow JSON files while overriding exposed inputs like prompt, seed, steps, and CFG. The Skill validates dependencies and executes runs via REST or WebSocket APIs against a local server or Comfy Cloud.

How does ComfyUI workflow execution handle missing custom nodes and models?

ComfyUI workflow execution handles missing components by checking required custom nodes, models, and prompt-embedded embeddings against a running server. It then suggests or auto-installs missing dependencies locally to ensure runs are repeatable.

Can I use this for Stable Diffusion text-to-image and AnimateDiff video generation?

Yes, you can use this for Stable Diffusion text-to-image and AnimateDiff video generation. It supports SD1.5, SDXL, Flux, and SD3 text-to-image workflows, along with video workflows like AnimateDiff, Wan, and Hunyuan.

Do I need API-format workflow JSON to run ComfyUI automation?

Yes, API-format workflow JSON is required to run ComfyUI automation. The Skill takes these workflow files, injects your specified parameters, and executes them through the ComfyUI REST or WebSocket APIs for local or cloud processing.

What is the best way to run SDXL text-to-image workflows via ComfyUI APIs?

The best way to run SDXL text-to-image workflows is to execute a workflow script with a JSON object containing your prompt, seed, and steps. The Skill routes endpoints correctly for local ComfyUI or Comfy Cloud and monitors progress via WebSocket.