skills.rest
Chia1104
Chia1104COMMUNITY
Explore all skills by this author →
Website𝕏@chia7423GitHub

comfyui

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

1|Updated Aug 11, 2026
Search Tags:#workflow automation#image generation#Flux#diffusion models#video generation#comfyui#Stable Diffusion
One-click install
npx skills add https://github.com/Chia1104/agent-air --skill comfyui-chia1104
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/Chia1104/agent-air/tree/main/skills/hermes/creative/comfyui
Command: npx skills add https://github.com/Chia1104/agent-air --skill comfyui-chia1104

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Running ComfyUI workflows programmatically requires juggling installation, hardware checks, model and custom-node dependencies, API-format workflow JSON, and execution monitoring — this Skill automates that entire pipeline for local servers and Comfy Cloud. ## Core Features & Use Cases - Guided Setup: Hardware probing (GPU/VRAM/disk) recommends local install vs Comfy Cloud, then an automated script installs comfy-cli, ComfyUI, and launches the server. - Workflow Execution: Inject parameters (prompt, seed, steps, denoise), upload input images for img2img/inpainting, submit jobs, monitor progress over WebSocket, and download outputs safely. - Dependency Management: Inspect any workflow to list controllable parameters and missing nodes/models, then auto-install custom nodes via comfy-cli. - Use Case: Ask the agent to generate eight variations of an SDXL image with random seeds — it validates the workflow, checks dependencies, runs a parallel batch, and returns the output file paths. ## Quick Start Ask the agent to generate an image of a sunset over mountains using the SDXL example workflow, and it will check the server, inject your prompt, run the job, and return the saved image.

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, passing parameters via --args as a JSON object. 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. The hardware_check.py script probes your machine and recommends local versus Comfy Cloud.

Can I use ComfyUI without a GPU?▼

Yes, through Comfy Cloud, which hosts workflows on RTX 6000 Pro GPUs with common models preinstalled. Set the COMFY_CLOUD_API_KEY environment variable and pass --host https://cloud.comfy.org; note the free tier cannot run workflows via the API.

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

This error means a required custom node package is not installed on the server. Run check_deps.py to identify the missing package and its install command, or auto_fix_deps.py to install it via comfy node install automatically.

How do I convert a ComfyUI workflow to API format?▼

Open the workflow in the ComfyUI web UI and use Workflow → Export (API) in newer versions or Save (API Format) in older ones. Editor-format files with top-level nodes and links arrays are not directly executable and must be re-exported.

How do I generate multiple image variations with different seeds?▼

Use run_batch.py with --count for the number of variations and --randomize-seed for fresh seeds per run. The --parallel flag controls concurrent jobs up to your local capacity or Comfy Cloud tier limit.

Related Skills

Explore More Design & Creative Skills→
ShinyGuaShinyGua

inpainting-regions

Compiles a Visual Intent Object into a ComfyUI SDXL inpainting prompt JSON.

Community
Intermediate
refly-airefly-ai
199

video-creator

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

Official
Intermediate
jadeclijadecli
1

refine

Refine dispatch prompts and agent-selection criteria through iterative scoring cycles.

Official
Intermediate
taracodlabstaracodlabs
799

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion via HuggingFace Diffusers or Inference API.

Official
Intermediate