Image generationGPL-3.0Python

ComfyUI

Node-based interface for diffusion models — images, video and audio.

Stars: 137.6K
Forks: 16.4K
Open issues: 5.2K
Last commit: 2026-10-15

Live from the GitHub API · updated 2026-10-15

What is ComfyUI?

ComfyUI lets you build generation pipelines by wiring nodes together in a graph: load a checkpoint, encode a prompt, sample, decode, upscale. It supports Stable Diffusion 1.5/SDXL/3.5, FLUX, video models such as Wan and HunyuanVideo, and a huge ecosystem of custom nodes. Workflows are saved as JSON (and embedded in output PNGs), so they are easy to share and reproduce.

Key features

Graph/node workflow editor with reusable workflow files
Supports SD1.x, SDXL, SD3.5, FLUX, Wan, HunyuanVideo, LTX-Video and more
Smart memory management — runs large models on GPUs with little VRAM
Only re-executes the parts of a workflow that changed
Thousands of community custom nodes via ComfyUI-Manager

System requirements

Platforms: Windows · macOS · Linux
GPU: NVIDIA (CUDA), AMD (ROCm/DirectML), Intel Arc or Apple Silicon; CPU mode is very slow
VRAM: 4 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models
RAM: 16 GB+
Disk: 10–100 GB depending on how many models you download
Python: 3.12 or 3.13 recommended for manual installs

How to install ComfyUI

Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.

Desktop app (Windows / macOS)

1
Download ComfyUI Desktop from the official site (comfy.org) and run the installer.
2
Pick your GPU type and an install location when prompted; the app sets up Python and PyTorch for you.
3
Load a workflow template and let the app download the required models.

Windows portable (NVIDIA)

1
Download the portable .7z package from the GitHub Releases page.
2
Extract it with 7-Zip.
3
Put checkpoint files in ComfyUI\models\checkpoints.
4
Run run_nvidia_gpu.bat and open the URL it prints (default http://127.0.0.1:8188).

Manual install (Linux / macOS)

Clone the repository.

git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI

2
Create a virtual environment and install PyTorch for your GPU (see pytorch.org), then the requirements.
```
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```
3
Start the server and open http://127.0.0.1:8188.
```
python main.py
```

Strengths

Supports new models first, often on release day
Most flexible and efficient Stable Diffusion/FLUX frontend
Workflows are portable and reproducible

Limitations

Steep learning curve for beginners
Custom nodes vary in quality and can break on updates

ComfyUI alternatives compared

Software	Stars	License	VRAM
ComfyUI Node-based interface for diffusion models — images, video and audio.	137.6K	GPL-3.0	4 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models
Stable Diffusion WebUI Forge A faster, leaner fork of the A1111 WebUI with FLUX support.	13.1K	AGPL-3.0	6 GB+ (FLUX NF4/GGUF variants run on 6–8 GB)
SwarmUI A friendly generate tab on top of ComfyUI, with multi-GPU support.	4.7K	MIT	6 GB+
InvokeAI Professional creative engine with a unified canvas for Stable Diffusion and FLUX.	28.6K	Apache-2.0	4 GB for SD1.5, 8 GB for SDXL, 10 GB+ for FLUX
Fooocus Midjourney-like simplicity for SDXL: type a prompt and press Generate.	53.4K	GPL-3.0	4 GB minimum, 6 GB+ recommended
Stable Diffusion WebUI (AUTOMATIC1111) The classic browser UI for Stable Diffusion with a massive extension ecosystem.	165.1K	AGPL-3.0	4 GB minimum (with --medvram/--lowvram), 8 GB+ recommended

FAQ

Is ComfyUI free?

Yes — ComfyUI is open-source software released under the GPL-3.0 license. Check the license (and any model weight licenses) before commercial use.

Does ComfyUI run on Windows, Mac and Linux?

ComfyUI supports: Windows, macOS, Linux.

What hardware do I need for ComfyUI?

NVIDIA (CUDA), AMD (ROCm/DirectML), Intel Arc or Apple Silicon; CPU mode is very slow. VRAM: 4 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models. RAM: 16 GB+

How do I install ComfyUI?

1. Download ComfyUI Desktop from the official site (comfy.org) and run the installer. 2. Pick your GPU type and an install location when prompted; the app sets up Python and PyTorch for you. 3. Load a workflow template and let the app download the required models.

What are the best ComfyUI alternatives?

Popular alternatives include Stable Diffusion WebUI Forge, SwarmUI, InvokeAI, Fooocus. See the comparison table on this page.

Can I use ComfyUI online without installing it?

If you just want results, AiLoft runs top image models such as GPT Image 2.5 and Nano Banana Pro in the browser — no GPU or setup required.

Skip the install — generate images in your browser

No GPU, drivers or Python needed. Use GPT Image 2.5 and Nano Banana Pro online and compare them side by side.

AI Image Generator

Open-source AI image generators