ComfyUI
A node-based tool for building image, video and 3D generation workflows that run on your own machine.
Instead of Hosted AI image tools and Adobe Firefly
Screenshot from www.comfy.org, taken 2026-10-23, shown to help you recognise the tool. It belongs to its maker. Ask us to remove it.
ComfyUI is a GPL-3.0 project from Comfy Org that lets you build image, video, audio and 3D generation workflows as a visual graph of nodes. Its core runs fully offline and downloads nothing unless you ask, and optional paid partner API nodes can be switched off. Comfy also sells a paid cloud version for people without suitable hardware.
It is the opposite of a locked AI studio: you choose the models, see every step and keep the workflow as a file. It needs a capable computer, setup takes effort, and each model you load comes with its own licence and its own questions about training data, which the score does not cover.
- Builds image, video and 3D workflows as a visual graph of nodes
- The core runs fully offline and you choose the models
- Needs a capable computer and some setup effort
What stands out
Do you make ComfyUI? Get the badge for your site
This badge reports a dated review. It is not a certification and it costs nothing. Link it to this page and leave the numbers alone: the image always shows the current score.
For dark backgrounds, use comfyui-dark.svg in place of comfyui-light.svg.
For comparison, we also reviewed Adobe Creative Cloud (12/30) as a benchmark.
Other tools for “draw, design and edit”
- KritaA full painting and illustration studio that costs nothing.
InkscapeA vector graphics editor for logos, illustrations and diagrams, built on the open SVG format.
GIMPA long-running image editor for retouching, compositing and creating pictures.
BlenderA complete 3D creation suite for modelling, animation, rendering and more.- darktableA non-destructive RAW photo editor and library for photographers.
- PenpotAn open-source design and prototyping tool for interfaces, built on web standards.