ComfyUI

How to Use FLUX GGUF Files in ComfyUI

Save VRAM by using quantized model files

Shawn @ Prompting Pixels

What You'll Learn

Learn how to install and configure FLUX GGUF quantized model files in ComfyUI to reduce VRAM usage while maintaining image generation quality.

Video Walkthrough

Prefer watching to reading? Follow along with a step-by-step video guide.

How to Use FLUX GGUF Files in ComfyUI

Flux GGUF files offer an efficient way to generate images within ComfyUI, a popular interface for AI image generation. This guide will walk you through the process of setting up and using Flux GGUF files for optimal results.

  1. Install the ComfyUI GGUF custom node using the ComfyUI manager.
  2. Download Flux model files (dev, schnell) and the T5XXL encoder from Hugging Face.
  3. Place T5XXL GGUF files in the Clip directory (comfyui/models/clip) and Flux1Dev or Schnell GGUF files in the U-Net directory (comfyui/models/unet) within ComfyUI's models folder.

Setting Up ComfyUI:

  1. Search for "GGUF" within ComfyUI workspace and add the UNet Loader GGUF and DualClip Loader GGUF nodes.
  2. Configure the nodes with your chosen Flux and T5 models.
  3. Load the VAE provided by the Flux team at Black Forest Labs.
  4. Set up your sampler settings (e.g., CFG: 1, Sampler: Euler, Steps: 20, Image size: 1024x1024).

Want More AI Image Tutorials?

Get the best AI image tutorials and tool reviews—no spam, just 1 or 2 helpful emails a month.

Continue Learning

More ComfyUI Tutorials

Explore additional tutorials in the ComfyUI category.

View All Tutorials