Fooocus
Image generation on your own computer that works from a prompt, with very few settings to learn.
Instead of Midjourney, DALL-E

Screenshot from github.com/lllyasviel/Fooocus, taken 2026-10-30, shown to help you recognise the tool. It belongs to its maker. Ask us to remove it.
Fooocus is for people who want to type a sentence and get a picture without learning a hundred dials. It is built on Stable Diffusion XL, aims to feel like Midjourney without the subscription, and handles the settings for you. It runs on your own machine and, after the first launch downloads its default models, works with no connection. The stated minimum is 4 GB of Nvidia graphics memory and 8 GB of system memory, which is light for this category.
Fooocus scores a 5 on lock-in and self-direction, a 4 on power and delivery, a 3 on footprint and a 2 on longevity.
It is free, GPL-3.0 and asks for no account. The project says it is in limited long-term support, with bug fixes only and no newer model designs planned, so it is a finished tool and Longevity is a 2. If you share it over a network with the listen or share options, the interface has no password by default, so leave those off.
- Describe what you want and it picks the settings for you
- Runs on a graphics card with as little as 4 GB of memory
- In limited support, with bug fixes only and no newer model designs planned
What stands out
Do you make Fooocus? 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 fooocus-dark.svg in place of fooocus-light.svg.
For comparison, we also reviewed Adobe Firefly (15/30) and Midjourney (14/30) as a benchmark.