---
language: en
license:  apache-2.0
tags:
  - text-to-image
  - diffusion
  - mflux
datasets:
  - custom
---

# FLUX.1-schnell-mflux-v0.6.2-8bit

[![Hugging Face](https://img.shields.io/badge/🤗%20Hugging%20Face-FLUX.1--schnell--mflux--v0.6.2--8bit-blue)](https://huggingface.co/black-forest-labs/FLUX.1-schnell)

![comparison_output](comparison.png)

A 8-bit quantized version of the [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) text-to-image model from Black Forest Labs, implemented using the [mflux](https://github.com/filipstrand/mflux) (version 0.6.2) quantization approach.

## Overview

This repository contains a 8-bit quantized version of the FLUX.1-schnell model, which significantly reduces the memory footprint while maintaining most of the generation quality. The quantization was performed using the mflux methodology (v0.6.2).

### Original Model

FLUX.1-schnell is a lightweight text-to-image diffusion model developed by Black Forest Labs. It's designed to be faster and more efficient than many larger models while still producing high-quality images.

### Benefits of 8-bit Quantization

- **Reduced Memory Usage**: ~50% reduction in memory requirements compared to the original model
- **Faster Loading Times**: Smaller model size means quicker initialization
- **Lower Storage Requirements**: Significantly smaller disk footprint
- **Accessibility**: Can run on consumer hardware with limited VRAM
- **Minimal Quality Loss**: Maintains nearly identical output quality to the original model

## Model Structure

This repository contains the following components:

- `text_encoder/`: CLIP text encoder (8-bit quantized)
- `text_encoder_2/`: Secondary text encoder (8-bit quantized)
- `tokenizer/`: CLIP tokenizer configuration and vocabulary
- `tokenizer_2/`: Secondary tokenizer configuration
- `transformer/`: Main diffusion model components (8-bit quantized)
- `vae/`: Variational autoencoder for image encoding/decoding (8-bit quantized)

## Usage

### Requirements

- Python 
- PyTorch 
- Transformers 
- Diffusers 
- [mflux](https://github.com/filipstrand/mflux) library (for 8-bit model support)

### Installation

```bash
pip install torch diffusers transformers accelerate
uv tool install mflux # check mflux README for more details
```

### Example Usage

```bash
# export path for mflux
% mflux-generate \        
    --path "dhairyashil/FLUX.1-schnell-mflux-v0.6.2-8bit" \        
    --model schnell \                                                                           
    --steps 2 \                                                                                 
    --seed 2 \       
    --height 1920 \
    --width 1024 \
    --prompt "hot chocolate dish"
```

### Comparison Output
The images generated from above prompt for different models are shown at the top.

fp16 and 8-bit results look visibly almost the same, with the 8-bit version maintaining excellent quality while using significantly less memory.

[4-bit model](https://huggingface.co/dhairyashil/FLUX.1-schnell-mflux-v0.6.2-4bit) is also available for comparison, though with more noticeable quality reduction.

## Performance Comparison

| Model Version | Memory Usage | Inference Speed | Quality |
|---------------|--------------|-----------------|--------|
| Original FP16 | ~36 GB      | Base            | Base   |
| 8-bit Quantized | ~18 GB    | Nearly identical | Nearly identical |
| 4-bit Quantized | ~9 GB     | Slightly slower | Moderately reduced |

## Other Highlights

- Very minimal quality degradation compared to the original model
- Nearly identical inference speed
- Rare artifacts that are generally imperceptible in most use cases

## Acknowledgements

- [Black Forest Labs](https://huggingface.co/black-forest-labs) for creating the original FLUX.1-schnell model
- [Filip Strand](https://github.com/filipstrand) for developing the mflux quantization methodology
- The Hugging Face team for their Diffusers and Transformers libraries

## License

This model inherits the license of the original FLUX.1-schnell model. Please refer to the [original model repository](https://huggingface.co/black-forest-labs/FLUX.1-schnell) for licensing information.