comfyui

Create, manage, and execute ComfyUI workflows for image, video, and audio generation.

Updated Jun 15, 2026
One-click install
npx skills add https://github.com/Piaoxuemoli/qoobeeHermes --skill comfyui-piaoxuemoli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/Piaoxuemoli/qoobeeHermes/tree/main/hermes/skills/creative/comfyui
Command: npx skills add https://github.com/Piaoxuemoli/qoobeeHermes --skill comfyui-piaoxuemoli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires comfy, comfy-cli, torch, torchvision, torchaudio, and includes scripts (resource) and references (resource) and workflows (resource) components.

What problem does it solve?

This Skill simplifies the creation, management, and execution of complex creative workflows using ComfyUI, an AI-powered platform.

Core Features & Use Cases

  • Workflow Creation: Design and export workflows in ComfyUI's web UI.
  • Workflow Management: Execute, monitor, and manage workflows from the command line.
  • Use Case: Generate images, videos, and audio through ComfyUI, leveraging the power of Stable Diffusion, Flux, and other AI models.

Quick Start

Run the 'comfyui' skill to execute the 'flux_dev_txt2img.json' workflow with the prompt 'a fox in a misty forest'.

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I run ComfyUI workflows from the command line?

You can execute ComfyUI workflows from the command line by invoking the skill with your desired workflow file, such as 'flux_dev_txt2img.json', along with your text prompt to generate images, videos, or audio.

What AI models are supported for image and video generation in ComfyUI?

ComfyUI supports various AI models for image, video, and audio generation, explicitly including Stable Diffusion and Flux models to execute creative workflows.

Do I need Python packages like Torch to manage creative workflows with ComfyUI?

Yes, you need Python packages including torch, torchvision, torchaudio, comfy, and comfy-cli installed in your environment to perform model inference and execute ComfyUI workflows.

How do I create and export creative workflows for ComfyUI?

You design and export creative workflows using ComfyUI's web UI, then execute, monitor, and manage those exported workflows directly through the command-line interface.

Can I generate audio and video using ComfyUI workflows?

Yes, ComfyUI supports audio generation and video generation alongside image generation, leveraging associated Python packages and AI models to execute diverse creative workflows.