flux1.dev.8bit.mlx / README.md
mzbac's picture
Upload folder using huggingface_hub
6fa67b9 verified
---
library_name: mlx
tags:
- mlx
- flux
- text-to-image
- quantized
- swift
pipeline_tag: text-to-image
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
# FLUX.1-dev 8-bit Quantized for MLX
This is an 8-bit quantized version of the FLUX.1-dev model optimized for use with MLX and flux.swift. The model size has been reduced from ~24GB to 17GB while maintaining excellent image generation quality.
Quantized using [flux.swift](https://github.com/mzbac/flux.swift), a Swift implementation of FLUX models for Apple Silicon.
## Model Details
- **Quantization**: 8-bit with group size 128
- **Total Size**: 17GB
- **Original Model**: [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev)
- **Framework**: MLX (Metal Performance Shaders)
- **Components**: Transformer, VAE, CLIP text encoder, T5 text encoder
## Usage
This model requires the [flux.swift](https://github.com/mzbac/flux.swift) implementation. Please refer to the repository for installation and usage instructions.
### Quick Start
```bash
# Load and use the quantized model
flux.swift.cli \
--load-quantized-path /path/to/this/model \
--hf-token YOUR_HF_TOKEN \
--prompt "Your prompt here" \
--output output.png
```
### Recommended Parameters
- **Steps**: 10+ (for quality)
- **Guidance Scale**: 7.5
- **Authentication**: Requires Hugging Face token
- **Use Case**: High-quality generation
### Example with Parameters
```bash
flux.swift.cli \
--load-quantized-path /path/to/this/model \
--hf-token YOUR_HF_TOKEN \
--prompt "A futuristic robot in a cyberpunk city" \
--steps 20 \
--guidance 7.5 \
--width 768 \
--height 768 \
--seed 42 \
--output cyberpunk_robot.png
```
## License
This model is a quantized version of FLUX.1-dev, which is licensed under the FLUX.1 [dev] Non-Commercial License. Please review the original license terms:
- Original model: https://huggingface.co/black-forest-labs/FLUX.1-dev
- License: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
- Commercial licensing available at: https://bfl.ai/pricing/licensing
## Performance
- **Memory Usage**: Reduced from ~24GB to 17GB
- **Quality**: Excellent preservation of generation quality
- **Platform**: Optimized for Apple Silicon Macs
## Citation
```bibtex
@misc{flux-dev,
author = {Black Forest Labs},
title = {FLUX.1-dev},
publisher = {Black Forest Labs},
year = {2024},
url = {https://huggingface.co/black-forest-labs/FLUX.1-dev}
}
@software{flux-swift,
author = {mzbac},
title = {flux.swift: Swift implementation of FLUX models},
url = {https://github.com/mzbac/flux.swift},
year = {2024}
}
```