Fooocus
Midjourney-like simplicity for SDXL: type a prompt and press Generate.
- Stars
- 53.4K
- Forks
- 8.6K
- Open issues
- 315
- Last commit
- 2025-12-01
Live from the GitHub API · updated 2026-10-15
What is Fooocus?
Fooocus hides the knobs. It ships a tuned SDXL pipeline with automatic prompt expansion, styles, inpainting, upscaling and image prompts, so beginners get good images without learning samplers or CFG. The project is now in limited long-term support (bug fixes only) and focuses on SDXL.
Key features
- One-box prompting with GPT-2–based prompt expansion
- Style presets, image prompt and face swap via references
- Inpaint/outpaint and 1.5×/2× upscale “Vary” tools
- Offline and private after the first model download
System requirements
- Platforms
- Windows · Linux · macOS
- GPU
- NVIDIA recommended; AMD and Apple Silicon supported (slower)
- VRAM
- 4 GB minimum, 6 GB+ recommended
- RAM
- 8 GB minimum, 16 GB recommended
- Disk
- ~15 GB for default models
How to install Fooocus
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Windows
- 1Download the .7z package from the README and extract it with 7-Zip.
- 2Run run.bat. The first launch downloads the SDXL models automatically.
Linux / macOS
- 1Clone and create a virtual environment.
git clone https://github.com/lllyasviel/Fooocus.git cd Fooocus python3 -m venv fooocus_env source fooocus_env/bin/activate - 2Install requirements and launch.
pip install -r requirements_versions.txt python entry_with_update.py - 3On Apple Silicon, add --disable-offload-from-vram for better speed.
Strengths
- Easiest local SDXL setup
- Great defaults
- Works offline
Limitations
- SDXL only; no FLUX or newer models
- Limited long-term support — no new features
Fooocus alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| Fooocus Midjourney-like simplicity for SDXL: type a prompt and press Generate. | 53.4K | GPL-3.0 | 4 GB minimum, 6 GB+ recommended | |
| InvokeAI Professional creative engine with a unified canvas for Stable Diffusion and FLUX. | 28.6K | Apache-2.0 | 4 GB for SD1.5, 8 GB for SDXL, 10 GB+ for FLUX | |
| ComfyUI Node-based interface for diffusion models — images, video and audio. | 137.6K | GPL-3.0 | 4 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models | |
| Stable Diffusion WebUI Forge A faster, leaner fork of the A1111 WebUI with FLUX support. | 13.1K | AGPL-3.0 | 6 GB+ (FLUX NF4/GGUF variants run on 6–8 GB) | |
| DiffusionBee The simplest way to run Stable Diffusion on a Mac. | 13.6K | AGPL-3.0 | — | |
| Stable Diffusion WebUI (AUTOMATIC1111) The classic browser UI for Stable Diffusion with a massive extension ecosystem. | 165.1K | AGPL-3.0 | 4 GB minimum (with --medvram/--lowvram), 8 GB+ recommended |
Related models
FAQ
Is Fooocus free?
Yes — Fooocus is open-source software released under the GPL-3.0 license. Check the license (and any model weight licenses) before commercial use.
Does Fooocus run on Windows, Mac and Linux?
Fooocus supports: Windows, Linux, macOS.
What hardware do I need for Fooocus?
NVIDIA recommended; AMD and Apple Silicon supported (slower). VRAM: 4 GB minimum, 6 GB+ recommended. RAM: 8 GB minimum, 16 GB recommended
How do I install Fooocus?
1. Download the .7z package from the README and extract it with 7-Zip. 2. Run run.bat. The first launch downloads the SDXL models automatically.
What are the best Fooocus alternatives?
Popular alternatives include InvokeAI, ComfyUI, Stable Diffusion WebUI Forge, DiffusionBee. See the comparison table on this page.
Can I use Fooocus online without installing it?
If you just want results, AiLoft runs top image models such as GPT Image 2.5 and Nano Banana Pro in the browser — no GPU or setup required.
Skip the install — generate images in your browser
No GPU, drivers or Python needed. Use GPT Image 2.5 and Nano Banana Pro online and compare them side by side.