A web-based creative engine for generating and editing images with Stable Diffusion and other AI models, featuring a unified canvas and node-based workflows.
lllyasviel/Fooocus
Offline, open-source image generator built on Stable Diffusion XL that lets you focus on prompts instead of manual parameter tuning.
Open-source alternative to:Midjourney
- Stars
- 53,602
- Forks
- 8,660
- Open issues
- 315
- Last commit
- 11 months ago
What is it?
Fooocus is a Gradio-based image generation application that runs locally and offline. It aims to offer the ease of online services like Midjourney, so users mainly write prompts and supply images rather than tuning sampler and model settings. Installation is simplified to a few clicks, and the project lists a minimum of 4GB Nvidia VRAM and 8GB system memory.
The app covers text-to-image, image-to-image style variation, upscaling, inpainting and outpainting, image prompts with face swap, and image description. Prompt expansion is built in through a GPT-2 based engine, and styles, aspect ratios and LoRAs can be chosen from the interface. Presets such as the default, anime and realistic editions switch between different default models.
The project is now in limited long-term support with bug fixes only, and it is built on SDXL rather than newer architectures such as Flux. Windows, Linux, Mac (MPS), AMD (DirectML/ROCm beta) and CPU-only setups are documented, and Docker and Colab are also supported.
Key features
- 01Text-to-image generation with prompt expansion and style presets
- 02Image-to-image variation, upscaling and image prompts with face swap
- 03Inpainting and outpainting in all four directions
- 04Preset editions for general, anime and realistic styles
- 05Optional HTTP listener, share link and basic authentication via auth.json
- 06Wildcards and inline LoRA syntax in prompts
Use cases
- Quickly producing SDXL-quality artwork without learning node-based workflows
- Generating illustrations or photo-style images on a local GPU without cloud fees
- Editing parts of an existing image through inpainting or extending its borders
- Hosting a private image generation UI for a small group on a local network
Quick start
- 1
Download the Windows package from the official releases link
- 2
Uncompress the file and run run.bat
- 3
On Linux, clone the repository
git clone https://github.com/lllyasviel/Fooocus.git - 4
Install requirements and launch with the launcher
pip install -r requirements_versions.txt && python entry_with_update.py
Things to know
- Minimum requirement is a 4GB Nvidia GPU and 8GB RAM, and it relies on Windows virtual swap on low-memory systems.
- The project is in limited long-term support with bug fixes only and no plans to adopt newer model architectures like Flux.
- AMD GPU support is in beta and not intensively tested.
- Licensed under GPL-3.0, a copyleft license.
Topics
FAQ
- What is Fooocus?
- Offline, open-source image generator built on Stable Diffusion XL that lets you focus on prompts instead of manual parameter tuning. Fooocus is a Gradio-based image generation application that runs locally and offline. It aims to offer the ease of online services like Midjourney, so users mainly write prompts and supply images rather than tuning sampler and model settings. Installation is simplified to a few clicks, and the project lists a minimum of 4GB Nvidia VRAM and 8GB system memory.
- Is Fooocus free to use? What license does it have?
- Fooocus is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is Fooocus still maintained?
- No commits for 6+ months. The last commit to Fooocus was on Dec 1, 2025.
- What can I use Fooocus for?
- Quickly producing SDXL-quality artwork without learning node-based workflows Generating illustrations or photo-style images on a local GPU without cloud fees Editing parts of an existing image through inpainting or extending its borders Hosting a private image generation UI for a small group on a local network
- How do I install Fooocus?
- Download the Windows package from the official releases link Uncompress the file and run run.bat On Linux, clone the repository: git clone https://github.com/lllyasviel/Fooocus.git Install requirements and launch with the launcher: pip install -r requirements_versions.txt && python entry_with_update.py
- Where can I get Fooocus?
- The source code and installation instructions are on GitHub: https://github.com/lllyasviel/Fooocus
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source Stable Diffusion-based tool for generating character-consistent comic images and long-range image-to-video sequences.
A Gradio-based web UI for running Stable Diffusion and newer image/video models, continuing the Forge fork with added model support and optimizations.
Training, generation and utility scripts for Stable Diffusion and other image generation models, covering LoRA and fine-tuning.
A node-graph GUI, API and backend for running diffusion models locally to generate images, video, audio and 3D content.
Open-source native unified multimodal models from SenseNova that handle image understanding, text-to-image generation, and image editing in one architecture.