flux1.kontext.4bit.mlx

FLUX.1-Kontext 4-bit Quantized for MLX

This is a 4-bit quantized version of the FLUX.1-Kontext-dev model optimized for use with MLX and flux.swift. The model size has been reduced from ~24GB to 9.2GB while maintaining excellent image-to-image generation quality.

Quantized using flux.swift, a Swift implementation of FLUX models for Apple Silicon.

Model Details

• Quantization: 4-bit with group size 64
• Total Size: 9.2GB
• Original Model: black-forest-labs/FLUX.1-Kontext-dev
• Framework: MLX (Metal Performance Shaders)
• Components: Transformer, VAE, CLIP text encoder, T5 text encoder

Usage

This model requires the flux.swift implementation. Please refer to the repository for installation and usage instructions.

Quick Start

# Load and use the quantized model for image-to-image generation
flux.swift.cli \
  --load-quantized-path /path/to/this/model \
  --hf-token YOUR_HF_TOKEN \
  --init-image-path /path/to/input/image.png \
  --prompt "Your transformation prompt here" \
  --output output.png

Recommended Parameters

• Steps: 30
• Guidance Scale: 3.5
• Authentication: Requires Hugging Face token
• Input: Requires --init-image-path for image-to-image generation

Example with Parameters

flux.swift.cli \
  --load-quantized-path /path/to/this/model \
  --hf-token YOUR_HF_TOKEN \
  --init-image-path ./reference.png \
  --prompt "transform this into a watercolor painting with soft pastel tones" \
  --steps 30 \
  --guidance 3.5 \
  --width 512 \
  --height 512 \
  --seed 42 \
  --output watercolor_painting.png

License

This model is a quantized version of FLUX.1-Kontext-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-Kontext-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 9.2GB
• Quality: Excellent preservation of image-to-image generation quality
• Platform: Optimized for Apple Silicon Macs

Citation

@misc{flux-kontext,
  author = {Black Forest Labs},
  title = {FLUX.1-Kontext-dev},
  publisher = {Black Forest Labs},
  year = {2024},
  url = {https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev}
}

@software{flux-swift,
  author = {mzbac},
  title = {flux.swift: Swift implementation of FLUX models},
  url = {https://github.com/mzbac/flux.swift},
  year = {2024}
}