skills.rest
genmedia-labs
genmedia-labsOFFICIAL
Explore all skills by this author →
GitHub

runcomfy-cli

Runs RunComfy image, video, and audio models from the command line via a single CLI.

12|2|Updated Aug 12, 2026
Search Tags:#api#cli#image generation#command line#video generation#ai models#runcomfy
One-click install
npx skills add https://github.com/genmedia-labs/skills --skill runcomfy-cli-genmedia-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: runcomfy-cli
Source: https://github.com/genmedia-labs/skills/tree/main/runcomfy-cli
Command: npx skills add https://github.com/genmedia-labs/skills --skill runcomfy-cli-genmedia-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Calling hundreds of AI media models (image generation, video generation, lip-sync, face swap, inpainting, LoRA training) normally requires learning each vendor's API. This Skill teaches the agent to install, authenticate, and invoke any RunComfy model through one CLI with a uniform submit-poll-download workflow. ## Core Features & Use Cases - Unified model invocation: Run any model with runcomfy run <vendor>/<model>/<endpoint> --input '<JSON>', with polling, download, and --no-wait async submission. - Scripting support: JSON output mode, batch prompt loops, submit-now-poll-later patterns, and exit-code-based retry logic for timeouts and rate limits. - Auth and discovery: Device-code login, RUNCOMFY_TOKEN for CI, whoami verification, and catalog URLs for discovering model input schemas. - Use Case: Generate a batch of product images by looping over a prompts file, submitting each to a FLUX or GPT Image endpoint, and downloading results into per-run output directories. ## Quick Start Ask the agent to install the RunComfy CLI, log in, and generate an image from a text prompt using a model like openai/gpt-image-2/text-to-image.

Frequently Asked Questions about runcomfy-cli

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

FAQPage Schema
How do I run a RunComfy model from the command line?▼

Install the CLI with npm i -g @runcomfy/cli, authenticate with runcomfy login, then call runcomfy run <vendor>/<model>/<endpoint> --input '<JSON>'. The CLI submits the request, polls until completion, and downloads output files to the current directory or --output-dir.

How do I authenticate the RunComfy CLI in CI or containers?▼

Set the RUNCOMFY_TOKEN environment variable with a token from your RunComfy profile page. This bypasses the browser-based device-code login flow and the local token file entirely, making it suitable for headless environments.

Can I submit RunComfy jobs without waiting for completion?▼

Yes, pass --no-wait to runcomfy run to submit and immediately receive a request_id. Later, check progress from any shell with runcomfy status <request_id>, which is useful for long video generation jobs or parallel batch submissions.

Why does the RunComfy CLI exit with code 75?▼

Exit code 75 indicates a retryable error such as a polling timeout or HTTP 429 rate limit. Wrap the command in a shell retry loop with exponential backoff; other codes like 64 (bad args) or 77 (auth failure) should not be retried.

How do I find the input schema for a RunComfy model?▼

Every model detail page on runcomfy.com has an API tab showing the exact input schema. Browse the full catalog at /models/all or filter by curated collections and capability features like lip-sync or upscale-video.

Related Skills

Explore More Design & Creative Skills→
kvidaikvidai

kvidai-media

Upload user media files to the kvidai CDN via presigned URLs.

Official
Intermediate
refly-airefly-ai
199

video-creator

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

Official
Intermediate
agentspace-soagentspace-so
31

lipsync

Generate lip-synced videos from audio or scripts via RunComfy CLI.

Official
Intermediate
whichguywhichguy

bfl-api

Integrate the Black Forest Labs API for FLUX image generation and editing.

Community
Intermediate