comfyui

Execute generative AI workflows via ComfyUI REST and WebSocket APIs.

7|1|Updated Jul 26, 2026

Search Tags:#automation #image generation #video generation #generative ai #comfyui #stable diffusion

Ready to run

npx skills add https://github.com/paxlabs-inc/ion-agent --skill comfyui-paxlabs-inc

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/paxlabs-inc/ion-agent/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/paxlabs-inc/ion-agent --skill comfyui-paxlabs-inc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill bridges the gap between the official ComfyUI CLI and complex generative AI workflows, enabling automated image, video, and audio production without manual UI interaction.

Core Features & Use Cases

Workflow Execution: Run complex generative pipelines (SDXL, Flux, AnimateDiff) with dynamic parameter injection.
Lifecycle Management: Automate the installation, server management, and dependency resolution for custom nodes and models.
Use Case: A user can automate the generation of 50 variations of a product image by programmatically sweeping through seeds and prompts, then automatically downloading the results to a local directory.

Quick Start

Use the comfyui skill to run the workflow file named flux_dev_txt2img.json with the prompt a futuristic city skyline and save the output to the local folder named outputs.

Frequently Asked Questions about comfyui

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

FAQPage Schema

How do I automate Stable Diffusion image generation without manual UI interaction?▼

You can automate Stable Diffusion image generation by executing complex generative AI workflows programmatically using the ComfyUI REST and WebSocket APIs. This allows dynamic parameter injection for models like SDXL and Flux without manual UI interaction.

Can I run ComfyUI workflows for video generation like AnimateDiff programmatically?▼

Yes, you can run ComfyUI workflows for video generation like AnimateDiff programmatically. The skill executes complex generative pipelines using the ComfyUI REST and WebSocket APIs for video and audio synthesis with dynamic parameter injection.

Do I need Python 3.10 and comfy-cli to manage local ComfyUI environments?▼

Yes, you need Python 3.10+ and the official comfy-cli to manage local ComfyUI environments. These dependencies are required to coordinate server state, execute workflow files, and handle custom node and model dependency resolution.

What is the best way to automate batch processing of product image variations?▼

The best way to automate batch processing of product image variations is by programmatically sweeping through seeds and prompts in generative AI workflows. This skill executes the workflows and automatically downloads the results to a local directory.

How does dependency resolution work for custom nodes in ComfyUI?▼

Dependency resolution for custom nodes in ComfyUI is managed by automating the installation process via the official comfy-cli. The skill coordinates server state and handles model dependencies to ensure complex generative AI workflows execute correctly.