comfyui

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

Updated Jul 6, 2026

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

Ready to run

npx skills add https://github.com/ghufronbagaskara/agent-im --skill comfyui-ghufronbagaskara

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/ghufronbagaskara/agent-im/tree/main/hermes-home/skills/creative/comfyui
Command: npx skills add https://github.com/ghufronbagaskara/agent-im --skill comfyui-ghufronbagaskara

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill bridges the gap between the ComfyUI web interface and automated agent workflows, allowing you to programmatically generate images, video, and audio without manual UI interaction.

Core Features & Use Cases

Workflow Execution: Run complex generative pipelines (txt2img, img2img, video) via REST/WebSocket API.
Lifecycle Management: Install, launch, and monitor ComfyUI servers and custom nodes using the official CLI.
Parameter Injection: Dynamically inject prompts, seeds, and model settings into API-format workflows for batch processing or variations.

Quick Start

Use the comfyui skill to run the workflow file flux_dev_txt2img.json with the prompt a futuristic city skyline at sunset.

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 without manual UI interaction?▼

To automate Stable Diffusion workflow execution, this skill uses REST and WebSocket APIs to programmatically run txt2img and img2img pipelines. It bridges the ComfyUI web interface and agent workflows by dynamically injecting prompts and seeds into API-format files.

Can I install and manage ComfyUI servers and custom nodes programmatically?▼

Yes, you can install, launch, and monitor ComfyUI servers and custom nodes programmatically. The skill handles lifecycle management using the official comfy-cli tool to set up your generative AI environment locally or in the cloud.

Does this support video generation and audio production alongside image creation?▼

Yes, this supports video generation and audio production alongside image creation. It automates complex generative pipelines through WebSocket API integration, allowing you to generate diverse AI media formats without manual UI interaction.

How do I inject prompts and seeds into ComfyUI workflows for batch processing?▼

You inject prompts and seeds into ComfyUI workflows using Python-based scripts. The skill dynamically modifies API-format workflow files, allowing you to automate batch processing or create media variations with different model settings.

What dependencies do I need to run ComfyUI automation scripts?▼

To run ComfyUI automation scripts, you need Python with the requests and websocket-client libraries installed. You also require the comfy-cli package to handle environment setup and server lifecycle management for generative AI media production.

Best way to run a local txt2img pipeline using a ComfyUI workflow file?▼

The best way to run a local txt2img pipeline is by passing your ComfyUI workflow JSON file to the skill and specifying your text prompt. The skill injects parameters, launches the server via comfy-cli, and monitors the job via WebSocket.