Fooocus

Image generation with almost every setting hidden. Type a prompt, get a good picture. No longer actively developed.

Self-hosted
Abandoned
Allowed adult content
Open source

At a glance

Where it runs: Self-hostedYou run it on your own machine. Nothing leaves it unless you send it.
Adult content: AllowedAdult content is permitted within the published rules.
Trains on your content: NoYour content is not used to train models.
Status: AbandonedThe maintainers have said they have stopped.
Account needed: No
Licence: GPL-3.0
Cost: Free and open source.
What it keeps: Local only.

What it takes to run

Graphics memory: 4 GB VRAM, 8 GB recommended
System memory: 8 GB, 16 GB recommended
Disk: about 15 GB
Runs on: Linux, Windows

Find what fits your machine on the tools page — pick your hardware from the first menu.

Fooocus took the position that most of the knobs in a Stable Diffusion interface are noise, and hid them behind carefully chosen defaults. For a great many people the results were better than what they were getting by fiddling.

Its author moved on to Forge and other projects, so development has effectively stopped. It still works, and it is still the kindest first thing to install — but it is frozen at the SDXL era and will not learn new models.

Worth knowing before you start

Development has stopped The author moved to other projects. No new model families will be added.
SDXL era only It will not run the model architectures released after it.

What it does

Almost no settings
Good defaults
Style presets
Inpainting

Models it runs

SDXL 1.0

Signs of life

Checked automatically. These are the only figures on this page a machine wrote, and they say when they were taken.

Last answered: Yes, 3 hours ago Its website responded when we asked.
Stars on GitHub: 53,066 8,611 forks.
Last commit: 288 days ago2025-12-01 19:17 UTC
Latest release: v2.5.5
Archived copy: Wayback Machine A snapshot, in case this one stops answering.