Instructions to use mlx-community/NAFNet-REDS-width64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/NAFNet-REDS-width64 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir NAFNet-REDS-width64 mlx-community/NAFNet-REDS-width64
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
metadata
license: mit
library_name: mlx
pipeline_tag: image-to-image
tags:
- mlx
- image-restoration
- deblurring
- denoising
- nafnet
base_model: megvii-research/NAFNet
NAFNet width64 (MLX) — Image deblurring
Apple MLX port of NAFNet (Simple Baselines for Image Restoration, ECCV 2022). Runs on Apple Silicon via MLX.
This checkpoint: REDS (Image deblurring). width64.
Usage
from nafnet_mlx import NAFNetConfig
from nafnet_mlx.pipeline import load_model, restore_to_file
m = load_model("model.safetensors", NAFNetConfig.reds_width64())
restore_to_file(m, "input.png", "output.png")
Validation
Faithful NHWC port (SimpleGate, Simplified Channel Attention, channel-axis LayerNorm2d, UNet + PixelShuffle). PT-vs-MLX full-model parity on a real image ~1e-6. Uses NAFNetLocal (TLC) local pooling.
License & attribution
MIT. Derived from megvii-research/NAFNet (MIT). See NOTICE.