comfyui

Automate ComfyUI workflow lifecycle and execution via REST and WebSocket APIs.

1|Updated May 12, 2026
One-click install
npx skills add https://github.com/projectedanx/hermes-agent --skill comfyui-projectedanx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/projectedanx/hermes-agent/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/projectedanx/hermes-agent --skill comfyui-projectedanx

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 solves the complexity of managing local or cloud-based generative AI workflows by automating the lifecycle of ComfyUI, including installation, dependency management, and parameter-injected execution.

Core Features & Use Cases

  • Lifecycle Management: Automates installation, server launching, and custom node/model management via comfy-cli.
  • Workflow Execution: Enables programmatic execution of complex generative pipelines (image, video, audio) with dynamic parameter injection.
  • Use Case: A user can automate the generation of a batch of images using a specific Flux or SDXL workflow, monitor progress via WebSockets, and automatically download the resulting assets to a local directory.

Quick Start

Use the comfyui skill to run the workflow file named flux_dev_txt2img.json with the prompt a beautiful sunset over mountains and save the output to the ./outputs directory.

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 workflow execution with dynamic parameters?

Automate ComfyUI generative AI workflows by injecting dynamic parameters into image, video, and audio synthesis pipelines via REST and WebSocket APIs, enabling programmatic execution and progress monitoring without manual UI interaction.

What do I need to set up before running ComfyUI workflows programmatically?

Before running ComfyUI workflows programmatically, you need comfy-cli for server management, Python-based scripts for workflow orchestration, and the requests and websocket-client libraries to handle REST API integration and real-time execution monitoring.

Can I use this to manage local and cloud-based generative AI environments?

Yes, you can manage both local and cloud-based generative AI environments. The automation handles ComfyUI installation, server launching, custom node management, and dependency resolution through comfy-cli across different deployment targets.

How does WebSocket integration work for monitoring generative AI pipelines?

WebSocket integration monitors generative AI pipelines by establishing a persistent connection to the ComfyUI server, allowing real-time tracking of workflow execution progress, parameter injection status, and asset generation completion for image, video, and audio outputs.

Is there a way to automatically download generated images and videos after workflow completion?

Yes, generated images and videos are automatically downloaded to a local directory after workflow completion. The Python-based scripts orchestrate the execution pipeline and handle asset retrieval once the WebSocket connection confirms the generative AI synthesis is finished.