ComfyUI: visual node graph for workflows
A visual node graph, extendable with custom nodes, available on Windows, Linux, and macOS.
Verified
Core facts
Read by a script from the official API, not rewritten by a model.
- Repository
- https://github.com/Comfy-Org/ComfyUI
- License
- GPL-3.0
- Languages
- Python
- Maintainer
- Comfy-Org
- Homepage
- https://www.comfy.org/
- Verified
What it is
ComfyUI provides a visual node graph for building and reusing image, video, audio, 3D, and text workflows without code. It is available on Windows, Linux, and macOS. ComfyUI can be extended with custom nodes.
Main features
It provides reusable subgraphs, workflow templates, App Mode, and a local API for integrating workflows into applications.
It loads complete checkpoints or separate diffusion models, VAEs, text encoders, LoRAs, ControlNets, adapters, and upscalers from supported model formats.
Built-in tools cover inpainting, outpainting, reference conditioning, masks and compositing, model merging, upscaling, frame interpolation, segmentation, depth estimation, and media processing.
Workflows can be saved and loaded as JSON, or complete workflows and seeds can be recovered from supported generated media.
It supports saving and loading high bit depth images and videos, with 16 bit PNG images, 32 bit EXR, and 10 bit AVIF among those supported.
Getting started
Comfy Cloud is the official paid cloud version for those who can't afford local hardware.
You can install and start ComfyUI using comfy-cli.
ComfyUI-Manager is an extension that allows you to install, update, and manage custom nodes for ComfyUI.
pip install comfy-cli
comfy install pip install -r manager_requirements.txt python main.py --enable-managerWho it is for
Using a cu130 or above version of pytorch is required on Nvidia 20 series and above. Python 3.13 is very well supported. Python 3.14 works but some custom nodes may have issues.
Intel Arc GPU users can install native PyTorch with torch.xpu support using pip. ComfyUI follows a weekly release cycle targeting Monday, but this regularly changes because of model releases or large changes to the codebase. ComfyUI Core releases a new major stable version roughly every 2 weeks.
Commits outside of the stable release tags may be very unstable and break many custom nodes. Comfy Desktop builds a new release using the latest stable core version. Every 2+ weeks, frontend updates are merged into the core repository.
The new frontend is now the default for ComfyUI. The frontend in the main ComfyUI repository is updated fortnightly. Daily releases are available in the separate frontend repository.
Only parts of the graph that have an output with all the correct inputs will be executed. Only parts of the graph that change from each execution to the next will be executed, and if you submit the same graph twice only the first will be executed. Dragging a generated png on the webpage or loading one gives the full workflow including the seeds that were used to create it.
The default installation includes a fast latent preview method that is low-resolution.
Related tools
Related tools listed on this site.
秒画
SenseTime’s AI image creation product with text-to-image generation, model and LoRA training, image collections, and an inspiration community.
讯飞星辰MaaS
The public primary description positions iFLYTEK Xingchen MaaS as a developer-facing model fine-tuning service, covering data processing, model optimization, evaluation and deployment/hosting. This review did not run those console workflows.
Civitai
Stable Diffusion model-sharing and collaboration platform. This review uses its official repository README, which describes model uploads, browsing, comments and collaborative improvement, and links the Civitai website.
即梦AI
An AI creative platform combining image generation, video generation, and canvas editing, starting from text or images.
PixPix
Image/video creation platform for commerce and creative teams. Its official site describes product-image sets, A+ detail pages, model try-on assets, image/video generation and editing, and an Agent workspace that breaks down creative tasks.
PixTV
AI-video and canvas-creation platform. Its primary description presents text-to-image, image-to-video, character consistency, storyboards and editing; the homepage also shows audio and text-creation entries.
DeepFloyd IF
DeepFloyd IF’s README describes cascaded text-to-image and super-resolution models, with Diffusers and notebook directions and separate code and weight licenses.
Cleanup.pictures
Online inpainting editor that removes selected objects, people, text and defects, with stated workflows for product photos and real-estate imagery.
LiblibAI·哩布哩布AI
A creative community centered on AI image models and workflows, with model sharing, online generation, and training entry points.
RunningHub
An online creative platform that brings together ComfyUI workflows, AI apps, and a canvas for generating and processing images and videos.
LiblibAI
AI image creation platform and model-sharing community whose site lists online drawing tools, downloadable models and online model training.
Genmo
The site says Genmo is developing open video world models; Mochi 1 is its open-source text-to-video model, usable online in the Playground or run locally via the open-source repository or ComfyUI.
Sources
This page is written from the official sources below. Open them to check the original text.
- GitHub READMEhttps://github.com/Comfy-Org/ComfyUIFetched
Verified ·
This page is written by AI from the official sources above and checked automatically. This site has not tested it. Found a mistake? Tell us.