comfyui-operator

Start a local ComfyUI server and generate images via API workflow overrides.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/hrdtbs/comfyui-operator-skill --skill comfyui-operator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui-operator
Source: https://github.com/hrdtbs/comfyui-operator-skill/tree/main
Command: npx skills add https://github.com/hrdtbs/comfyui-operator-skill --skill comfyui-operator

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill allows AI agents to directly interact with and control a local ComfyUI installation, automating the process of generating images without manual intervention.

Core Features & Use Cases

  • ComfyUI Automation: Start the ComfyUI server, list available models and workflows, and dynamically generate images.
  • Dynamic Image Generation: Modify ComfyUI workflows via API by overriding nodes (e.g., prompts, seeds) and save generated images.
  • Use Case: Ask your AI agent to "Generate an image of a futuristic city at sunset using the 'cyberpunk_landscape' workflow," and it will handle the entire process from starting ComfyUI to saving the final image.

Quick Start

Use the comfyui-operator skill to generate an image using the 'my_workflow.json' workflow and set the positive prompt to 'A serene landscape'.

Frequently Asked Questions about comfyui-operator

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

FAQPage Schema
How do I automate ComfyUI image generation from an AI agent?

Automate ComfyUI image generation by using Python scripts to start the server, list workflows, and override API nodes. This allows AI agents to dynamically generate and save images without manual intervention.

Can I dynamically modify ComfyUI workflows via API to change prompts and seeds?

Yes, you can modify ComfyUI workflows via API by overriding specific nodes like positive prompts and seeds. This dynamic image generation process ensures you can programmatically adjust parameters before saving the final output.

What do I need to control a local ComfyUI instance using Python scripts?

To control a local ComfyUI instance, you need Python scripts utilizing the requests and websocket-client dependencies. This setup provides native integration to start the server, list available models, and handle image generation.

How does AI agent integration with ComfyUI handle workflow selection and model listing?

AI agent integration handles workflow selection by listing available models and workflows through native API calls. It uses Python scripts to start the ComfyUI server, ensuring the agent can dynamically select and execute the appropriate generation task.

Does ComfyUI API integration require manual server startup before generating images?

No, ComfyUI API integration does not require manual server startup. The integration uses Python scripts to automatically start the local ComfyUI instance before overriding workflow nodes and generating the requested images.