How to Run FLUX Locally on Windows, Mac, and Linux

FLUX is a cutting-edge AI image generator that creates detailed and imaginative visuals from text prompts. Running FLUX locally on your system brings significant advantages such as faster processing, enhanced privacy, and unrestricted usage. In this guide, we’ll show you how to set up FLUX on Windows, Mac, and Linux to harness its full potential.

Why Run FLUX Locally?

Running FLUX locally offers many benefits over web-based platforms:

• Faster Processing: Generate images without relying on the internet.
• Increased Privacy: Keep your data and prompts local to your machine.
• No Restrictions: Unrestricted access to FLUX's capabilities.

Now, let’s dive into the methods of setting up FLUX on different operating systems.

Method 1: Using ComfyUI to Run FLUX Locally

ComfyUI is a powerful, user-friendly graphical interface ideal for those who prefer avoiding command-line operations. Follow these steps to get started with ComfyUI:

Step 1: Install ComfyUI

Visit the ComfyUI GitHub releases page.

Download the latest version for your OS.

Extract the downloaded archive to a location of your choice.

Step 2: Download FLUX Models

Visit the FLUX HuggingFace repository and download the following files:

• flux_schnell.safetensors (main model)
• ae.safetensors (VAE file)

Download the following encoders from the FLUX text encoders repository:

• t5xxl_fp16.safetensors (for systems with 32GB+ RAM)
• t5xxl_fp8_e4m3fn.safetensors (for systems with less than 32GB RAM)
• clip_l.safetensors

Step 3: Place Files in ComfyUI Folders

Move flux_schnell.safetensors to ComfyUI/models/checkpoints/.

Move ae.safetensors to ComfyUI/models/vae/.

Place t5xxl_fp16.safetensors or t5xxl_fp8_e4m3fn.safetensors and clip_l.safetensors in ComfyUI/models/clip/.

Step 4: Run ComfyUI

Open a terminal or command prompt.

Navigate to the ComfyUI folder.

Run the command:

• Windows: python_embeded\\\\python.exe -m ComfyUI
• Mac/Linux: python3 main.py

Open a web browser and go to http://localhost:8188.

Step 5: Set Up FLUX Workflow

In ComfyUI, right-click and add these nodes:

• CLIP Text Encode (T5XXL)
• CLIP Text Encode (CLIP L)
• Flux Guidance
• Empty Latent Image
• VAE Decode

Connect the nodes as follows:

• CLIP Text Encode (T5XXL) output to Flux Guidance "t5_emb" input.
• CLIP Text Encode (CLIP L) output to Flux Guidance "clip_emb" input.
• Empty Latent Image output to Flux Guidance "latent" input.
• Flux Guidance output to VAE Decode input.

Step 6: Generate Images

Enter your text prompt in both CLIP Text Encode nodes.

Click “Queue Prompt” to generate an image.

Method 2: Using Stable Diffusion WebUI

Stable Diffusion WebUI is another popular interface for running FLUX models. Here’s how you can use it:

Step 1: Install Stable Diffusion WebUI

Clone the Stable Diffusion WebUI repository.

Navigate to the cloned directory: