comfy-cli
Install, manage, and run ComfyUI instances. Use when setting up ComfyUI, launching servers, installing/updating/debugging custom nodes, downloading models from CivitAI/HuggingFace, managing workspaces, running API workflows, or troubleshooting node conflicts with bisect.
Best use case
comfy-cli is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Install, manage, and run ComfyUI instances. Use when setting up ComfyUI, launching servers, installing/updating/debugging custom nodes, downloading models from CivitAI/HuggingFace, managing workspaces, running API workflows, or troubleshooting node conflicts with bisect.
Teams using comfy-cli should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/comfy-cli/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How comfy-cli Compares
| Feature / Agent | comfy-cli | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Install, manage, and run ComfyUI instances. Use when setting up ComfyUI, launching servers, installing/updating/debugging custom nodes, downloading models from CivitAI/HuggingFace, managing workspaces, running API workflows, or troubleshooting node conflicts with bisect.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# comfy-cli CLI tool for managing ComfyUI installations, custom nodes, and models. ## Quick start ```bash comfy install # Install ComfyUI + ComfyUI-Manager comfy launch # Start ComfyUI server comfy node install ComfyUI-Impact-Pack # Install a custom node comfy model download --url "https://civitai.com/api/download/models/12345" ``` ## Installation ```bash comfy install # Interactive GPU selection comfy install --nvidia # NVIDIA GPU comfy install --amd # AMD GPU (Linux ROCm) comfy install --m-series # Apple Silicon comfy install --cpu # CPU only comfy install --restore # Restore deps for existing install comfy install --pr 1234 # Install specific PR comfy install --version latest # Latest stable release comfy install --version 0.2.0 # Specific version ``` GPU options: `--nvidia`, `--amd`, `--intel-arc`, `--m-series`, `--cpu` CUDA versions (NVIDIA): `--cuda 12.9`, `--cuda 12.6`, `--cuda 12.4`, `--cuda 12.1`, `--cuda 11.8` Other flags: `--skip-manager`, `--skip-torch-or-directml`, `--skip-requirement`, `--fast-deps` ## Launch ```bash comfy launch # Foreground mode comfy launch --background # Background mode comfy launch -- --listen 0.0.0.0 # Pass args to ComfyUI comfy stop # Stop background instance comfy launch --frontend-pr 1234 # Test frontend PR ``` ## Workspace selection Global flags (mutually exclusive): ```bash comfy --workspace /path/to/ComfyUI ... # Explicit path comfy --recent ... # Last used instance comfy --here ... # Current directory comfy which # Show selected instance comfy set-default /path/to/ComfyUI # Set default ``` ## Custom nodes ```bash comfy node show # List installed nodes comfy node simple-show # Compact list comfy node install <name> # Install from registry comfy node install <name> --fast-deps # Fast dependency install comfy node reinstall <name> # Reinstall node comfy node uninstall <name> # Remove node comfy node update all # Update all nodes comfy node disable <name> # Disable node comfy node enable <name> # Enable node comfy node fix <name> # Fix node dependencies ``` Snapshots: ```bash comfy node save-snapshot # Save current state comfy node save-snapshot --output snapshot.json comfy node restore-snapshot snapshot.json comfy node restore-dependencies # Restore deps from nodes ``` Debugging: ```bash comfy node bisect # Binary search for broken node comfy node deps-in-workflow workflow.json # Extract deps from workflow comfy node install-deps --workflow workflow.json # Install workflow deps ``` Publishing: ```bash comfy node init # Init scaffolding comfy node scaffold # Create project via cookiecutter comfy node validate # Validate before publishing comfy node pack # Package node comfy node publish # Publish to registry ``` ## Models ```bash comfy model list # List available models comfy model download --url <url> # Download from URL comfy model remove <name> # Remove model ``` Sources: CivitAI, Hugging Face, direct URLs Tokens for gated models: - `--civitai-token` or config `civitai_api_token` - `--hf-token` or config `hf_api_token` ## Run workflows ```bash comfy run --workflow workflow_api.json comfy run --workflow workflow.json --wait --verbose comfy run --workflow workflow.json --host 192.168.1.10 --port 8188 ``` Requires running ComfyUI instance. ## ComfyUI-Manager ```bash comfy manager disable-gui # Hide manager in UI comfy manager enable-gui # Show manager in UI comfy manager clear # Clear startup actions ``` ## Update ```bash comfy update all # Update ComfyUI + nodes comfy update comfy # Update ComfyUI only ``` ## Other commands ```bash comfy env # Show config and paths comfy --version # Print CLI version comfy pr-cache list # List cached PR builds comfy pr-cache clean # Clear expired caches comfy standalone # Create standalone Python bundle comfy tracking enable|disable # Manage analytics comfy feedback # Submit feedback ``` ## Config Location: - Linux: `~/.config/comfy-cli/config.ini` - macOS: `~/Library/Application Support/comfy-cli/config.ini` - Windows: `%APPDATA%\Local\comfy-cli\config.ini` Keys: `default_workspace`, `default_launch_extras`, `civitai_api_token`, `hf_api_token` ## Tips - `--skip-prompt` for non-interactive mode (CI/scripts) - Background mode tracks PID for clean `comfy stop` - Snapshots preserve exact node versions for reproducibility - `comfy node bisect` binary-searches to find which node broke your setup - PR cache avoids rebuilding frontend PRs you've tested before
Related Skills
portfolio-watcher
Monitor stock/crypto holdings, get price alerts, track portfolio performance
portainer
Control Docker containers and stacks via Portainer API. List containers, start/stop/restart, view logs, and redeploy stacks from git.
portable-tools
Build cross-device tools without hardcoding paths or account names
polymarket
Trade prediction markets on Polymarket. Analyze odds, place bets, track positions, automate alerts, and maximize returns from event outcomes. Covers sports, politics, entertainment, and more.
polymarket-traiding-bot
No description provided.
polymarket-analysis
Analyze Polymarket prediction markets for trading edges. Pair Cost arbitrage, whale tracking, sentiment analysis, momentum signals, user profile tracking. No execution.
polymarket-agent
Autonomous prediction market agent - analyzes markets, researches news, and identifies trading opportunities
polymarket-5
Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data.
polymarket-4
Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data.
polymarket-3
Query Polymarket prediction market odds and events via CLI. Search for markets, get current prices, list events by category. Supports sports betting (NFL, NBA, soccer/EPL, Champions League), politics, crypto, elections, geopolitics. Real money markets = more accurate than polls. No API key required. Use when asked about odds, probabilities, predictions, or "what are the chances of X".
polymarket-2
Query Polymarket prediction markets - check odds, trending markets, search events, track prices.
pollinations
Pollinations.ai API for AI generation - text, images, videos, audio, and analysis. Use when user requests AI-powered generation (text completion, images, videos, audio, vision/analysis, transcription) or mentions Pollinations. Supports 25+ models (OpenAI, Claude, Gemini, Flux, Veo, etc.) with OpenAI-compatible chat endpoint and specialized generation endpoints.