ComfyUI
Build image generation workflows as a graph of nodes.
New to this? What open source means and how to read this page.
Want to run it? Read the ComfyUI guide: install, first clip, model files.
What it is
A modular interface for diffusion models where you connect nodes to build your own generation pipeline. It runs on your own machine.
Good for
People who want control over image generation and are happy to tune workflows and models.
The catch
It is not a one-click Midjourney. You need a capable GPU, and you choose and manage your own models. The learning curve is real.
Facts checked on 12 October 2026. We have not yet run a hands-on test of this tool. When we do, it gets a "Tested" mark here. Approximate US list prices for an individual plan, from third-party price trackers checked on 12 Oct 2026. Monthly billing where it exists. Regions, taxes and promotions change them. Confirm at the vendor before you decide.
More in Images & audio
Speech-to-text you can run yourself.
Replaces: Otter.ai
A free multitrack audio editor.
Replaces: Adobe Audition
A free RAW photo workflow.
Replaces: Adobe Lightroom