Overview

Using ComfyUI as a Developer

ComfyUI is a modular GenAI inference engine that can be run as a server, accessed via API, extended with custom nodes, and managed from the command line. Most API work follows two steps: get ComfyUI running somewhere, then run workflows against it from your application.

Quick Start

The fastest way to try the API is to run a workflow against Comfy Cloud. There is nothing to deploy: the SDKs point at Comfy Cloud by default, so all you need is a workflow and an API key.

1. Get a workflow

   Browse ComfyUI Workflows for community workflows, or build your own in the editor. Save it in API format as workflow_api.json.

2. Install an SDK

   Python

   pip install comfy-sdk
   
3. Run it

   Python

   from comfy_sdk import Comfy
   
   client = Comfy(api_key="comfyui-...")  # Comfy Cloud is the default target
   
   wf = client.workflows.from_file("workflow_api.json")
   
   job = client.run(wf)
   for output in job.get_outputs("9"):
       output.to_file(output.name)
   

   "9" is the ID of the output node in your workflow file. See the SDK guide for inputs, progress events, and error handling.

4. Deploy your own ComfyUI

   When you need your own models and custom nodes behind the endpoint, deploy your environment with the Serverless API. The same SDK code works against it; only the base URL changes.

Deploy ComfyUI

Learn how to deploy and scale ComfyUI, on the Developer Platform or your own infrastructure.

Deployment Overview

Compare Serverless API, Comfy Cloud, and self-hosting, and pick the right target.

See also: Serverless API · Comfy Cloud · Self-Hosting Options

Run Workflows

Learn how to run workflows using our SDKs and the v2 HTTP API. They work against our serverless API endpoints and your own ComfyUI instance.

Running Workflows

See which client works with which deployment, starting with the Python and TypeScript SDKs.

See also: Comfy SDKs · API Proxy for Self-Hosted · Comfy API v2 Reference

Agent Tools / MCP

Connect AI agents to ComfyUI via the Model Context Protocol (MCP). Start with the hosted Cloud MCP, or use Local MCP and Comfy CLI for other setups.

MCP Overview

Compare Cloud MCP, Local MCP, and Comfy CLI, and find the right setup for your AI agent integration.

See also: Comfy MCP for cloud and local connections

More

Self-Hosted Server API

The raw REST and WebSocket API of the ComfyUI server: routes, messages, and startup flags.

Comfy CLI

Install, update, and manage ComfyUI from the terminal.

Custom Nodes

Extend ComfyUI with Python backends and JavaScript UI extensions.

Registry

Package and publish custom nodes through the Comfy Registry.