comfyui

Execute ComfyUI API-format workflows with parameter injection for image, video, and audio generation.

Updated Apr 9, 2026

Search Tags:#image-generation #workflow-automation #flux #video-generation #stable-diffusion #comfyui #rest-websocket

Ready to run

npx skills add https://github.com/MarbleSodas/Mavis --skill comfyui-marblesodas

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/MarbleSodas/Mavis/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/MarbleSodas/Mavis --skill comfyui-marblesodas

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, requests, websocket-client, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill removes the trial-and-error of setting up ComfyUI and running workflows by giving you an install-and-execute path with parameter injection, dependency checks, and reliable output downloads.

Core Features & Use Cases

Run ComfyUI workflows with parameters: inject prompt/seed/steps/dimensions (and more) into API-format workflows and download every produced output.
Auto-detect and fix missing dependencies: inspect a running server to find missing custom nodes, models, and prompt-embedded embeddings, then suggest install commands.
Support local or Comfy Cloud execution: route REST/WebSocket calls correctly for both environments, including queue/status monitoring and error-safe handling.

Quick Start

Ask: “Generate an image using the provided Flux Dev workflow JSON, set prompt to ‘a cat in a neon cyberpunk street’, and save the results into ./outputs.”

Frequently Asked Questions about comfyui

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

FAQPage Schema

How do I execute Stable Diffusion or Flux workflows via the ComfyUI API?▼

Executing ComfyUI API-format workflows involves injecting parameters like prompt, seed, and dimensions into the JSON, then routing REST/WebSocket calls to the server and safely downloading the generated outputs. This automates the queue monitoring and execution lifecycle.

Can I run ComfyUI image generation locally or on Comfy Cloud?▼

Yes, ComfyUI image generation supports both local and Comfy Cloud execution scenarios. The system correctly routes REST/WebSocket calls for either environment, handling queue monitoring and error-safe execution for your generated images and video.

How do I fix missing custom nodes or model dependencies in ComfyUI?▼

To fix missing dependencies, the system inspects your running ComfyUI server to detect missing custom nodes, models, and prompt-embedded embeddings, then suggests the appropriate install commands. This auto-detection removes the trial-and-error of manual setup.

What environment and Python dependencies do I need to automate ComfyUI workflows?▼

Automating ComfyUI workflows requires python3, the requests library, and the websocket-client package. It also relies on comfy-cli for lifecycle management to validate the environment and ensure the server API is ready for REST/WebSocket execution.

Why does my ComfyUI workflow fail validation before image generation starts?▼

ComfyUI workflow validation fails when the API-format JSON is malformed or lacks required parameter injections. This performs safe workflow format validation and dependency checks before execution to prevent errors and ensure successful image generation.