ComfyUI

ComfyUI is a node-based, modular visual AI engine for building and running custom image and media generation workflows with full control over every model,…

  • AI
ComfyUI is a node-based, modular visual AI engine for building and running custom image and media generation workflows with full control over every model, parameter, and output.

Platform availability

Available on 2 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox
  • Helm
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

87/100 Excellent

Maintained
100last commit 4 days ago
Popular
100147,339 GitHub stars
Easy to install
352 install platforms, install notes
Light to run
No data
Security check
95no serious findings, CI, tests

Based on 4 of 5 factors.

Availability: platform listings confirmed today, links checked today

GitHub stars
147,339
Open issues
5558
Last commit
2026-11-17
Latest release
v0.45.0
License
GPL-3.0
Activity
declining

Checked 4 days ago - source: GitHub (comfyanonymous/ComfyUI)

Resources & Compatibility

Requirements not published yet.

First-install notes

  • Copy .env and compose files first Copy example.env to .env and compose.example.yml to compose.yml before starting, because Docker Compose (the tool that launches the app) needs these files to know settings, ports, and storage. Without them, ComfyUI may not start or your settings and models may be lost. source
  • Check port, storage, and GPU settings In compose.yml, keep the 8188:8188 port so your browser can reach ComfyUI's web UI, and keep the user, output, and models volume folders so settings, images, and model files are saved. If you have an NVIDIA graphics card, keep the nvidia section so it can use the GPU; if not, remove it to avoid start errors. source
  • Start in foreground for first run Run cd docker && docker compose up, not with -d, so the startup logs stay visible in the terminal. This helps you spot permission, GPU, or model download problems before using ComfyUI. source

Fetched 53 days ago - each note links to its source

Alternatives (5)

  • A1111 Stable Diffusion WEB UI - AUTOMATIC1111's Stable Diffusion web UI provides a powerful, web interface for Stable Diffusion featuring a one-click installer, advanced i…
  • Draw Things - Draw Things provides a comprehensive but still easy-to-use, mobile and desktop solution for AI-based art generation.
  • InvokeAI - InvokeAI is an open-source, self-hosted Stable Diffusion toolkit for generating and editing images from text or existing images.
  • chaiNNer - A flowchart/node-based image processing GUI aimed at making chaining image processing tasks (especially upscaling done by neural networks)…
  • stability matrix - Multi-platform package manager for Stable Diffusion.

Checked 54 days ago - source: AlternativeTo

Common questions

How does ComfyUI reduce VRAM usage for large open-source models?

It can run large open-source models with as little as 4 GB of VRAM and 8 GB of RAM. It uses asynchronous weight streaming to do this.

Which Docker Compose settings should I keep for the web UI, saved files, and GPU?

Keep the 8188:8188 port so the browser can reach the web UI, and keep the user, output, and models volume folders. Keep the nvidia section if you have an NVIDIA card, or remove it to avoid start errors.

How should I start the ComfyUI Docker container for the first time?

Run docker compose up from the docker directory without the -d flag. This keeps startup logs visible so you can spot permission, GPU, or model download problems.

What should I check before putting credentials or private models on a ComfyUI self-hosting template?

Review what the template installs because the templates are community-maintained and not supported by the ComfyUI team. The result is a normal self-hosted ComfyUI with a public URL or an SSH tunnel in front of it.

Answers sourced from context7.com, docs.comfy.org, github.com, github.com

Community

Collected 48 days ago - public community threads