ComfyUI: Open Source AI Interaction & Interfaces

What is ComfyUI?

ComfyUI is a GPL-3.0 licensed Python and PyTorch node-graph application, local API, and backend for running diffusion models across image, video, audio, 3D, and text workflows, built for visual professionals who want control over every model, parameter, and output, and for developers who embed those workflows into production pipelines.

What it is

ComfyUI lives in the Python and PyTorch ecosystem and is filed under AI & Machine Learning / AI Interaction & Interfaces. It presents diffusion model generation as a visual node graph: nodes are wired together to build and reuse workflows for images, videos, 3D models, audio, and text. The same graph can be driven from a local API, so what a user assembles visually can also be called from an application. The project tags itself ai, comfy, comfyui, python, pytorch, and stable-diffusion, and its homepage is comfy.org.

The concrete problem it solves is the assembly of diffusion pipelines. Instead of writing code to chain model loaders, samplers, and post-processing stages, a user wires those stages into a reusable graph. Reusable subgraphs and workflow templates remove the need to rebuild common pipelines, and App Mode exposes a finished graph behind a simple UI, so the sophisticated workflow stays hidden from the person operating it. For production integration, local API endpoints let applications call the same graph. One graph definition therefore serves both the builder and the operator, which replaces hand-written scripts for each pipeline.

Key capabilities

A visual node graph for building and reusing image, video, audio, 3D, and text workflows without code.
Reusable subgraphs, workflow templates, and App Mode, which expose complex workflows through a simple UI.
A local API for integrating workflows into applications and production pipelines.
Efficient local execution through asynchronous queueing, partial graph re-execution, smart VRAM and RAM management, model offloading, and support for quantized models.
Broad native model support, including Stable Diffusion 1.5, SDXL, SD3.5, Flux.1, Flux.2, Qwen Image, Z-Image, Hunyuan Image 2.1, HiDream, Lumina Image 2.0, Chroma, Anima, LongCat Image, Ideogram 4, Krea 2, MageFlow, Microsoft Lens, PixelDiT, Kandinsky 5, and Ernie Image.
Partner nodes that open access to closed-source models such as Nano Banana, Seedance, and Hunyuan3D.
Installation on Windows, Linux, and macOS, with manual install supporting NVIDIA, AMD, Intel, Apple Silicon, and Ascend GPUs.

Who uses it and how

Visual professionals and creatives who need control over every model, parameter, and output.
Development teams embedding generation into production pipelines through the local API endpoints.
Users without local hardware, who run the official paid Comfy Cloud version.
New users on Windows and macOS, who take the desktop application as the easiest entry point.
Self-hosters on any operating system or GPU type, who use the manual install path.

Getting started

ComfyUI ships as a desktop application for Windows and macOS, as a manual install covering all operating systems and GPU types, and as the paid Comfy Cloud service at comfy.org/cloud. The desktop application is described as the easiest way to begin.

How it compares

No list of paid products that this project replaces is supplied in the facts, and no similar tools are named there either. On the available facts, ComfyUI stands alone in this registry.

When to use it — and when not to

Local use requires a machine with one of the supported GPUs, and the only managed alternative is the paid Comfy Cloud, so a self-hoster runs and maintains the installation directly. The licence is GPL-3.0, a copyleft licence, which is worth checking before embedding the code in a proprietary product. The repository carries a large open tracker of 4,894 issues, so a user should expect an active project rather than a quiet, frozen one.

project readme (upstream, from github) — read inline

ComfyUI

The most powerful and modular AI engine for content creation.

ComfyUI is the AI creation engine for visual professionals who demand control over every model, every parameter, and every output. Its powerful and modular node graph interface empowers creatives to generate images, videos, 3D models, audio, and more...

ComfyUI natively supports the latest open-source state of the art models.
Partner nodes provide access to the best closed source models such as Nano Banana, Seedance, Hunyuan3D, etc.
It is available on Windows, Linux, and macOS, locally with our desktop application, our portable install or on our cloud.
The most sophisticated workflows can be exposed through a simple UI thanks to App Mode.
It integrates seamlessly into production pipelines with our API endpoints.

Get Started

Local

Desktop Application

The easiest way to get started.
Available on Windows & macOS.

Manual Install

Supports all operating systems and GPU types (NVIDIA, AMD, Intel, Apple Silicon, Ascend).

Cloud

Comfy Cloud

Our official paid cloud version for those who can't afford local hardware.

Examples

See what ComfyUI can do with the newer template workflows or old example workflows.

Features

A visual node graph for building and reusing image, video, audio, 3D, and text workflows without code.
Reusable subgraphs, workflow templates, App Mode, and a local API for integrating workflows into applications.
Efficient local execution with asynchronous queueing, partial graph re-execution, smart VRAM and RAM management, model offloading, and support for quantized models.
Broad native model support. This is a representative list; browse the workflow library for maintained, ready-to-run templates.
- Image generation: Stable Diffusion 1.5, SDXL, SD3.5, Flux.1, Flux.2, Qwen Image, Z-Image, Hunyuan Image 2.1, HiDream, Lumina Image 2.0, Chroma, Anima, LongCat Image, Ideogram 4, Krea 2, MageFlow, Microsoft Lens, PixelDiT, Kandinsky 5, and Ernie Image.
- Image editing: Flux Kontext, Flux.2 Klein, Qwen Image Edit, HiDream E1.1 and O1, OmniGen2, Boogu, JoyImage Edit, MageFlow Edit, and LongCat Image Edit.
- Video generation: Wan 2.1 and 2.2, LTX-Video 2 and 2.3, HunyuanVideo 1.5, Kandinsky 5 Video, CogVideoX, Cosmos Predict2, Bernini-R, SCAIL 2, and Mochi.
- Audio and video generation: MiniMax H3 and LTX-AV.
- Audio generation: ACE-Step 1.5, Stable Audio 3, MiniMax Music 3 and Yue 2.
- 3D and vision: Hunyuan3D 2.1, TripoSplat, SeedVR2, SUPIR, Depth Anything 3, MoGe, SAM 3 and 3.1, RT-DETRv4, and BiRefNet.
- Text generation: Gemma 3 and 4, Qwen3, Qwen3.5, and Qwen3-VL, including multimodal inputs.
Load complete checkpoints or separate diffusion models, VAEs, text encoders, LoRAs, ControlNets, adapters, and upscalers from supported model formats.
Built-in tools for inpainting, outpainting, reference conditioning, masks and compositing, model merging, upscaling, frame interpolation, segmentation, depth estimation, and media processing.
Save and load workflows as JSON, or recover complete workflows and seeds from supported generated media.
Runs fully offline: core does not download anything unless you request it. Use --disable-api-nodes to disable the optional paid Comfy API nodes and force all built-in functionality to stay offline.
Extend ComfyUI with custom nodes
Configure additional model locations with extra_model_paths.yaml.
Support for saving and loading high bit depth images and videos: 16 bit PNG images, 32 bit EXR, 10 bit AVIF are supported and more.
Support for saving and loading HDR videos and images in various formats.

Release Process

ComfyUI follows a weekly release cycle targeting Monday but this regularly changes because of model releases or large changes to the codebase. There are three interconnected repositories:

ComfyUI Core
- Releases a new major stable version (e.g., v0.7.0) roughly every 2 weeks.
- Starting from v0.4.0 patch versions will be used for fixes backported onto the current stable release.
- Minor versions will be used for releases off the master branch.
- Patch versions may still be used for releases on the master branch in cases where a backport would not make sense.
- Commits outside of the stable release tags may be very unstable and break many custom nodes.
- Serves as the foundation for the desktop release
Comfy Desktop
- Builds a new release using the latest stable core version
ComfyUI Frontend
- Every 2+ weeks frontend updates are merged into the core repository
- Features are frozen for the upcoming core release
- Development continues for the next release cycle

Shortcuts

Keybind	Explanation
`Ctrl` + `Enter`	Queue up current graph for generation
`Ctrl` + `Shift` + `Enter`	Queue up current graph as first for generation
`Ctrl` + `Alt` + `Enter`	Cancel current generation
`Ctrl` + `Z`/`Ctrl` + `Y`	Undo/Redo
`Ctrl` + `S`	Save workflow
`Ctrl` + `O`	Load workflow
`Ctrl` + `A`	Select all nodes

Frequently asked questions

Is ComfyUI free to use?

ComfyUI is open source under the GPL-3.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does ComfyUI do?

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

What is ComfyUI written in?

ComfyUI is primarily written in Python. Its source is publicly available at https://github.com/Comfy-Org/ComfyUI, and it has 133,792 GitHub stars.