comfyui

Automate AI image, video, and audio generation workflows via ComfyUI APIs.

Updated Jun 22, 2026
One-click install
npx skills add https://github.com/ashiqcodeleaf/long-Run-Agents --skill comfyui-ashiqcodeleaf
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/ashiqcodeleaf/long-Run-Agents/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/ashiqcodeleaf/long-Run-Agents --skill comfyui-ashiqcodeleaf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires comfy-cli, comfy, requests, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables users to generate images, video, and audio through ComfyUI, automating the setup, management, and execution of complex workflows involving AI-driven content creation.

Core Features & Use Cases

  • Image Generation: Create custom images using Stable Diffusion, SDXL, Flux, SD3, etc., with parameterized control over various parameters like prompt, seed, steps, and models.
  • Video Generation: Generate videos using AnimateDiff, Hunyuan, Wan, AudioCraft, etc., with detailed control over the output parameters.
  • Audio Generation: Create audio content with various AI models, including voice generation and music composition.
  • Use Case: Imagine you want to create a short promotional video for a new product. You can use this Skill to generate a video with the product featured, with custom text and style, using AI-generated imagery and motion.

Quick Start

Use the comfyui skill to generate an image based on the prompt "a futuristic cityscape at night" with the SDXL model, using the seed value 42 and 20 steps.

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 for image and video generation?

You can automate AI-driven content generation by applying this skill to manage ComfyUI setup and execute workflows via REST/WebSocket APIs. It handles parameter injection for prompts, seeds, and steps, allowing you to generate images, video, and audio through automated scripts.

Does ComfyUI support audio generation alongside image and video creation?

Yes, ComfyUI supports audio generation using models like AudioCraft for voice and music composition. This skill automates the execution of these audio workflows alongside image and video generation, providing parameterized control over the AI-driven content creation process.

Do I need to install ComfyUI locally to run automated generation workflows?

You need ComfyUI installed locally or access to Comfy Cloud infrastructure, along with Python dependencies like comfy-cli and requests. This skill utilizes these components to manage and execute your image, video, and audio generation workflows.

What is the best way to control parameters like seed and steps in Stable Diffusion workflows?

The best way to control Stable Diffusion parameters is by injecting values like seed, steps, and prompts directly into the workflow via REST or WebSocket APIs. This skill automates parameterized control over models like SDXL and Flux for custom AI image generation.

Can I use this to generate a promotional video with AnimateDiff or Hunyuan?

Yes, you can generate promotional videos using models like AnimateDiff and Hunyuan with detailed control over output parameters. This skill automates the creation and execution of these AI-driven video generation workflows through ComfyUI.