comfyui

Execute ComfyUI API-format workflows with parameter injection and output downloads.

Updated May 5, 2026
One-click install
npx skills add https://github.com/Z43L/zeus-agent --skill comfyui-z43l
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/Z43L/zeus-agent/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/Z43L/zeus-agent --skill comfyui-z43l

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill removes the friction of setting up, validating, parameterizing, and running ComfyUI workflows so you can reliably generate images, video, audio, and 3D outputs without manual trial-and-error.

Core Features & Use Cases

  • Workflow execution with parameter injection: Runs ComfyUI API-format workflow JSON while injecting user-specified values (prompt, seed, steps, dimensions, denoise, and more).
  • Fast dependency readiness checks: Inspects a workflow against a running ComfyUI server (nodes, models, embeddings) and suggests exact install commands for missing pieces.
  • Local vs Comfy Cloud routing: Executes against either local ComfyUI or Comfy Cloud, including REST/WebSocket monitoring and streaming output downloads.

Quick Start

Use the comfyui skill to generate an image from an API-format workflow named 'sdxl_txt2img.json' by asking it to run locally and save the results into an 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 ComfyUI workflow execution with parameter injection?

To automate ComfyUI workflow execution, you can run API-format workflow JSON while injecting user-specified values like prompts, seeds, steps, and dimensions. This allows you to reliably generate images, video, audio, and 3D outputs without manual trial-and-error.

Why does my ComfyUI workflow fail to run due to missing dependencies?

ComfyUI workflows often fail due to missing nodes, models, or embeddings. You can inspect the workflow against a running ComfyUI server to perform fast dependency readiness checks and receive exact install commands for any missing pieces.

Can I run ComfyUI API-format workflows on both local servers and Comfy Cloud?

Yes, you can run ComfyUI API-format workflows against either a local ComfyUI server or Comfy Cloud. The execution includes REST and WebSocket monitoring to validate readiness and safely stream output downloads from either environment.

How do I generate images and video using Stable Diffusion workflows with batch sweeps?

You can generate images and video by running Stable Diffusion API-format workflow JSON with optional batch sweeps. This process supports image, inpainting, upscaling, and video/audio/3D generation scenarios by injecting parameters like seed and denoise.

Do I need comfy-cli to manage the ComfyUI lifecycle for automated workflow execution?

Yes, you need ComfyUI along with the comfy-cli lifecycle to manage the server environment for automated workflow execution. This setup allows the skill to use REST and WebSocket endpoints to validate readiness and monitor runs safely.