README.md

---
license: mit
base_model: ZhengPeng7/BiRefNet_HR-matting
library_name: mlx
tags:
  - mlx
  - image-segmentation
  - matting
  - background-removal
  - birefnet
pipeline_tag: image-segmentation
---

# BiRefNet_HR-matting-fp16 (MLX)

[`mlx-community/BiRefNet_HR-matting-fp16`](https://huggingface.co/mlx-community/BiRefNet_HR-matting-fp16) is an
**fp16 MLX** conversion of [`ZhengPeng7/BiRefNet_HR-matting`](https://huggingface.co/ZhengPeng7/BiRefNet_HR-matting)
(MIT) — the same Swin-L + ASPP-Deformable architecture run at **2048×2048** for the crispest dense-hair detail.
The high-resolution "best" matting tier (best all-rounder: crispest fine hair while retaining thin structures
like whiskers).

**Parity:** IoU **0.9905** vs the PyTorch reference (loads through the identical converter + model as the
general weights, zero code change). fp16 runtime validated for production matting quality. ~2 s/image at 2048
on Apple Silicon (≈18 GB peak — a pro-tier footprint).

## Use (Swift / MLX)

Loaded by [`mlx-birefnet-swift`](https://github.com/xocialize/mlx-birefnet-swift):

```swift
import BiRefNet
var cfg = BiRefNetConfig.swinLargeDefault; cfg.inputSize = (2048, 2048)
let pipeline = try BiRefNetPipeline.fromPretrained("model.safetensors", dtype: .float16, config: cfg)
let matte = try pipeline(cgImage).maskCGImage()   // source-resolution soft-alpha
```

Converted from the official PyTorch checkpoint via the package's `birefnet-convert`. Single-file
`model.safetensors`. The fast tier is [`mlx-community/BiRefNet-fp16`](https://huggingface.co/mlx-community/BiRefNet-fp16).