# How to Install Flux in ComfyUI in 2026: fp8 and GGUF Workflow Guide

> Published 2026-07-01 · https://www.promptzone.com/tara_suzuki/how-to-install-flux-in-comfyui-in-2026-fp8-and-gguf-workflow-guide-3ni1

---
title: How to Install Flux in ComfyUI in 2026: fp8 and GGUF Workflow Guide
published: true
description: Install Flux in ComfyUI in 2026 — where each model file goes, fp8 vs GGUF, the ComfyUI-GGUF node, and how to load a working Flux workflow step by step.
tags: ai, imagegen, flux, comfyui
---

**Short answer (2026):** Installing Flux in ComfyUI is four steps: (1) install the **ComfyUI-GGUF** custom node if you're low on VRAM, (2) drop the model files into the right folders (`diffusion_models`/`unet`, `text_encoders`, `vae`), (3) set **fp8** in the *Load Diffusion Model* node (or use a **GGUF** loader for quantized models), and (4) load a ready-made Flux workflow from the ComfyUI Manager and queue a test.

- **High VRAM (16GB+):** fp8 `.safetensors` + the standard diffusion loader
- **Low VRAM (6–8GB):** GGUF quant + ComfyUI-GGUF node
- **Don't skip:** the T5 + CLIP text encoders and the VAE

## What you need to download

Flux is not one file — it's four components:

| Component | Folder | Notes |
|-----------|--------|-------|
| Diffusion model (Flux.1-dev) | `models/diffusion_models/` (or `unet/`) | fp8 `.safetensors` **or** a GGUF quant |
| T5 text encoder | `models/text_encoders/` | Use the **quantized GGUF T5** on low VRAM (fp16 is ~9GB) |
| CLIP-L encoder | `models/text_encoders/` | `clip_l.safetensors` |
| VAE | `models/vae/` | `ae.safetensors` |

For 8GB systems, look for fp8 versions (e.g., huggingface.co/Kijai/flux-fp8) or a GGUF quant.

## Path A — fp8 (simplest, for 16GB+ GPUs)

1. Put the fp8 `flux1-dev` `.safetensors` in `models/diffusion_models/`.
2. Add the T5, CLIP-L, and VAE to their folders above.
3. In ComfyUI, load the **default Flux workflow** (Manager → Workflow browser, or drag in a known-good JSON).
4. In the **Load Diffusion Model** node, set `weight_dtype = fp8_e4m3fn`. **Set fp8 here, in the node — not on the command line.** ComfyUI's `--fp8_e4m3fn-unet` flag is often ignored by Flux's loader.
5. Queue a prompt.

## Path B — GGUF (for 6–8GB GPUs)

1. Install **ComfyUI-GGUF**: Custom Nodes Manager → search "GGUF" → install → restart. (Or `git clone https://github.com/city96/ComfyUI-GGUF` into `custom_nodes`.)
2. Download a GGUF model (Q4_K_S is the 8GB sweet spot) into `models/unet/`.
3. Download the **quantized GGUF T5** into `models/text_encoders/` — not the fp16 one.
4. Load a **GGUF workflow** from the Manager's workflow browser; it uses the **Unet Loader (GGUF)** node instead of the standard loader.
5. Launch ComfyUI with `--lowvram` and queue a prompt.

Full low-VRAM detail (quant levels, the T5 trap, memory flags) is in our [Flux on 8GB VRAM guide](https://promptzone.com/rebecca_patel_bba79f92/how-to-run-flux-on-8gb-vram-in-2026-the-gguf-low-vram-guide-46k8). Once it's running, level up your results with the [best Flux LoRAs for realism](https://promptzone.com/rebecca_patel_bba79f92/best-flux-loras-in-2026-for-realism-and-how-to-stack-them-1mck).

## Verify it works

Queue a generation with a simple prompt. If an image appears in the preview node with no red error nodes, Flux is installed correctly. Red nodes almost always mean a missing file in one of the four folders above — recheck the T5, CLIP, and VAE first.

## Frequently asked questions

### Where do Flux model files go in ComfyUI?
The diffusion model goes in `models/diffusion_models/` (or `unet/` for GGUF), the T5 and CLIP-L encoders in `models/text_encoders/`, and the VAE in `models/vae/`.

### fp8 or GGUF for Flux — which should I use?
Use fp8 `.safetensors` if you have 16GB+ VRAM (simplest). Use GGUF with the ComfyUI-GGUF node if you're on 6–8GB — it compresses the model to fit.

### Why is my Flux workflow showing red error nodes?
Almost always a missing file. Confirm the diffusion model, T5 encoder, CLIP-L, and VAE are all present in their correct folders — the text encoders and VAE are the most commonly forgotten.

### Do I need to set fp8 on the command line?
No — set `weight_dtype = fp8_e4m3fn` inside the Load Diffusion Model node. The `--fp8_e4m3fn-unet` CLI flag is frequently ignored by Flux's loader.

## Conclusion

Flux in ComfyUI comes down to putting four files in four folders and choosing fp8 (high VRAM) or GGUF (low VRAM). Load a prebuilt workflow from the Manager rather than wiring from scratch, and you'll be generating in minutes. Got a favorite Flux workflow? Share it below.

## Sources
- [Serverman — How to Install Flux in ComfyUI](https://www.serverman.co.uk/ai/comfyui/how-to-install-flux-comfyui/)
- [ComfyUI Wiki — Flux.1 ComfyUI Guide](https://comfyui-wiki.com/en/tutorial/advanced/image/flux/flux-1-dev-t2i)
- [city96/ComfyUI-GGUF (GitHub)](https://github.com/city96/ComfyUI-GGUF)