Fooocus by Codagentic

👉 Click Here to Install Fooocus 👈

Fooocus is a powerful offline image generation software based on Stable Diffusion XL (SDXL), enhanced and maintained by Mustafa Shoukat at Codagentic. This version delivers Midjourney-like quality with full offline, open-source, and free capabilities.

⚠️ Beware of fake websites claiming to be Fooocus. The only official source is this GitHub page. We do not own domains such as fooocus.com, fooocus.ai, etc.

---

🚦 Project Status

Limited Long-Term Support (LTS) – Only critical bug fixes. No new features or major updates unless a community consensus emerges around new generation standards.

For newer models like Flux, try:

• WebUI Forge
• ComfyUI / SwarmUI
• Community Forks

---

✨ Features

Midjourney Feature	Fooocus Equivalent
Text-to-image with minimal prompt tuning	GPT-2 based prompt processor
V1–V4 Variations	Upscale / Variation / Vary Subtle / Strong
U1–U4 Upscaling	Upscale to 1.5x or 2x
Inpaint / Pan	Built-in inpainting models
Image Prompt	Enhanced algorithmic support
--style	Style configuration in Advanced
--no	Negative prompts
--ar	Aspect ratio setting
Prompt weights	(word:1.5) format
Describe image	Use Describe tool
ControlNet	Advanced image prompt control
InsightFace	FaceSwap with tools

More in Advanced Features

---

📥 Download & Install

🔹 Windows (NVIDIA)

1. Download Fooocus 2.5.0 (7z)
2. Extract the archive.
3. Run run.bat.
4. Wait for model downloads.

🛠 Requires 4GB VRAM (NVIDIA) and 8GB RAM

Optional Presets:

• run.bat – Default
• run_anime.bat – Anime
• run_realistic.bat – Realistic

🔹 Google Colab

Run in the cloud:

Example:

!python entry_with_update.py --share --always-high-vram --preset anime

🔹 Linux (Anaconda)

git clone https://github.com/lllyasviel/Fooocus.git
cd Fooocus
conda env create -f environment.yaml
conda activate fooocus
pip install -r requirements_versions.txt
python entry_with_update.py

🔹 Linux (Python venv)

git clone https://github.com/lllyasviel/Fooocus.git
cd Fooocus
python3 -m venv fooocus_env
source fooocus_env/bin/activate
pip install -r requirements_versions.txt
python entry_with_update.py

🔹 AMD GPU (Windows/Linux)

pip uninstall torch torchvision torchaudio
pip install torch-directml  # Windows
# OR
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.6  # Linux

python entry_with_update.py --directml --preset anime

⚠️ AMD support is experimental.

---

🛠 Troubleshooting

• Corrupted models → Re-download model files
• RuntimeError: CPUAllocator → Enable swap memory
• Slow generation? → Try NVIDIA driver v531

More: Troubleshooting Guide

---

📸 Screenshots

---

👨‍💻 Maintained By

Mustafa Shoukat | Founder at Codagentic

Name	Email	LinkedIn	GitHub	Kaggle	LeetCode	WhatsApp
Mustafa Shoukat	mustafashoukat.ai@gmail.com