skills.rest
AjayRajan05
AjayRajan05COMMUNITY
Explore all skills by this author →
WebsiteGitHub

comfyui

Generate images, video, and audio by running ComfyUI workflows via REST and WebSocket APIs.

5|2|Updated Mar 12, 2026
Search Tags:#workflow automation#image generation#video generation#flux#comfyui#stable diffusion#comfy-cli
One-click install
npx skills add https://github.com/AjayRajan05/VoiceOS --skill comfyui-ajayrajan05
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/AjayRajan05/VoiceOS/tree/main/skills/bundled/community/creative/comfyui
Command: npx skills add https://github.com/AjayRajan05/VoiceOS --skill comfyui-ajayrajan05

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Setting up ComfyUI and executing its node-based workflows programmatically is error-prone: hardware requirements vary, workflows must be in API format, dependencies (custom nodes, models, embeddings) are often missing, and the official CLI lacks workflow execution support. This Skill handles the full lifecycle from hardware detection and installation to parameterized workflow execution and output retrieval. ## Core Features & Use Cases - Guided Setup: Hardware check (GPU/VRAM/disk) routes users to local install via comfy-cli or Comfy Cloud, with automated install, launch, and health verification scripts. - Workflow Execution: Inject parameters (prompt, seed, steps, dimensions) into API-format workflow JSON, submit to local or cloud servers, monitor progress via WebSocket, and download outputs safely. - Dependency Management: Extract a workflow's controllable parameters, check required nodes/models/embeddings against a running server, and auto-install missing custom nodes via comfy-cli. - Use Case: A user asks to generate 8 variations of an SDXL image with random seeds; the Skill validates the workflow, checks the model is installed, runs a parallel batch, and returns the output file paths. ## Quick Start Ask the assistant to generate an image with ComfyUI, for example: "Run the SDXL text-to-image workflow with the prompt 'a fox in a misty forest' and save the output."

Frequently Asked Questions about comfyui

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

FAQPage Schema
How do I run a ComfyUI workflow from the command line?▼

Use run_workflow.py with an API-format workflow JSON and a parameter dictionary, for example passing prompt, seed, and steps via --args. The script submits the job to the server, monitors execution, and downloads outputs to your chosen directory.

What hardware do I need to run ComfyUI locally?▼

Local ComfyUI needs an NVIDIA GPU with at least 6 GB VRAM (8 GB for SDXL, 12 GB or more for Flux and video), an AMD GPU with ROCm on Linux, or an Apple Silicon Mac with 16 GB unified memory. Machines without a capable GPU should use Comfy Cloud instead.

Can I use Comfy Cloud instead of installing ComfyUI locally?▼

Yes, Comfy Cloud runs workflows on hosted GPUs with an API key set via the COMFY_CLOUD_API_KEY environment variable. Note that the free tier cannot execute workflows through the API; a paid subscription is required for prompt submission and output download.

Why does my ComfyUI workflow fail with class_type not found?▼

This error means a required custom node is not installed on the server. Run check_deps.py against the workflow to identify missing nodes and their packages, then install them with comfy node install or let auto_fix_deps.py handle it.

What is the difference between editor format and API format workflows?▼

API format workflows have top-level node IDs each containing a class_type field and are directly executable via the REST API. Editor format has top-level nodes and links arrays and must be re-exported from the ComfyUI web UI using Export (API) before scripts can run it.

How do I run img2img or inpainting with ComfyUI?▼

Pass --input-image to run_workflow.py to upload a local image and inject its server filename into the workflow's image parameter. For inpainting, supply both an image and a mask, where white mask pixels mark regions to regenerate.

Related Skills

Explore More Design & Creative Skills→
dawsonblockdawsonblock

cli-anything-comfyui

Manage ComfyUI workflow queues and download generated images via REST API.

Community
Intermediate
refly-airefly-ai
199

video-creator

Generates short AI-powered videos and scripts for social media platforms.

Official
Intermediate
Bakery88Bakery88

ComfyUI Workflow Builder

Assemble and validate ComfyUI workflows using MCP tools.

Community
Advanced
fgarofalo56fgarofalo56
6

localai

Run local AI models via a self-hosted OpenAI-compatible API.

Community
Advanced