runcomfy-cli

Official

Run any RunComfy model from the terminal.

Authorruncomfy-com
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It removes the friction of installing, authenticating, and operating RunComfy model endpoints by giving you a single command-line workflow for submitting requests, polling status, and downloading outputs.

Core Features & Use Cases

  • One-binary model execution: Run text-to-image, image-to-video, edits, lip-sync, face swap, upscaling, and more through a consistent interface.
  • Auth + request lifecycle: Install the verified CLI, sign in once, then submit jobs with input JSON, poll for completion, and download results.
  • Operational reliability patterns: Supports streaming-friendly JSON output, no-wait submission with later status checks, and documented retryable exit codes for resilience.

Quick Start

Run a text-to-image request by telling the agent: runcomfy run openai/gpt-image-2/text-to-image --input '{"prompt":"a small purple cat at sunset, photorealistic"}'.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: runcomfy-cli
Download link: https://github.com/runcomfy-com/skills/archive/main.zip#runcomfy-cli

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.