Self-host ComfyUI
v0.45.0Modular AI engine for visual content with node graph
- Stars
- 147 014
- RAM
- 8GB
- Port
- 8188 (Web UI and API server)
What is ComfyUI?
ComfyUI is a self-hosted AI engine for visual content creation built around a visual node graph interface. It generates various media types using modern diffusion models. The software runs locally on Windows, Linux, and macOS with support for NVIDIA, AMD, Intel, Apple Silicon, and Ascend hardware. Key capabilities include asynchronous queueing, intelligent VRAM and RAM handling, model offloading, quantized model support, custom nodes, workflow templates, App Mode, and a local API for integration. Users can install it via a desktop app, portable builds, or manual Python setup.
Should you self-host ComfyUI?
ComfyUI scores 92/100 on selfhost.directory (how scoring works) and ranks #2 of 123 in AI. It has 147 014 GitHub stars, +10 054 in the last 30 days.
It shipped 29 stable releases in the past year. The latest, v0.45.0, came out on 10 November 2026. New versions land roughly every 6 days.
Setup is moderate: expect some configuration beyond a single command. It is GPL-3.0-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is openclaw (93/100, 394 525 stars). It scores higher overall, so compare the two before you pick. See ComfyUI vs openclaw side by side.
Features
- App Mode
- Broad native model support
- Built-in media processing tools
- Custom nodes extension system
- Dynamic prompts
- Efficient local execution
- High bit depth image/video support
- Local API for integration
- Model format flexibility
- Multi-modal generation
- Node-based workflow editor
- Offline Mode
- Reusable subgraphs and workflow templates
- Textual inversion/embeddings support
- Workflow save/load as JSON
Models ComfyUI runs
Popular open-weight models with ComfyUI support, with VRAM needs and licence at a glance.
More in AI
comfyui-mcpLocal-first agent for ComfyUI generating images, video, audio via MCP server and Claude Code plugin. Works with Claude, ChatGPT, Gemini, or local LLMs.
CompreFaceOpen-source face recognition system you can self-host. Provides REST API for detection, verification, recognition, age/gender/mask/pose analysis.
confab-webSelf-hosted, open-source platform for archiving and analyzing AI coding sessions with cost tracking, AI recaps, and team sharing.
ConnapseConnapse is a self-hosted, open-source knowledge backend giving AI agents persistent, searchable memory via hybrid search, MCP server, and storage connectors.
ContextMCPSelf-hosted MCP server powered by Probe that lets AI assistants search any GitHub repository or local documentation via npx, Docker, or pre-built npm packages.
coolify-mcpOpen-source MCP server exposing 46 tools so AI assistants can deploy, diagnose and operate a self-hosted Coolify PaaS, with human confirmation on destructive actions.
Copilot_ProxySelf-hosted proxy that converts GitHub Copilot API into OpenAI, Anthropic, and Gemini compatible endpoints with a WebUI for multi-account management and token handling.
Crawl4AICrawl4AI converts websites into LLM-ready Markdown for RAG and AI agents. Self-host via pip/Docker or use the cloud API. Open-source Apache-2.0.
crwfastCRW is a self-hosted, open-source web scraping and search API in Rust with Firecrawl-compatible endpoints and native MCP server for AI agents.
daily-briefSelf-hosted AI daily news aggregator with 26+ sources, 21 financial tickers with technical indicators, and 6 swappable LLM backends.
DarkMoonDarkMoon is an autonomous AI penetration testing platform with 50 specialist agents that runs on your infrastructure using local LLMs behind a Privacy Gateway.
dbhubDBHub is a minimal, token-efficient MCP server connecting AI assistants to PostgreSQL, MySQL, SQL Server, Oracle, MariaDB, and SQLite with built-in guardrails.
0 comments