| license: mit | |
| base_model: ZhengPeng7/BiRefNet | |
| library_name: mlx | |
| tags: | |
| - mlx | |
| - image-segmentation | |
| - matting | |
| - background-removal | |
| - birefnet | |
| pipeline_tag: image-segmentation | |
| # BiRefNet-fp16 (MLX) | |
| [`mlx-community/BiRefNet-fp16`](https://huggingface.co/mlx-community/BiRefNet-fp16) is an **fp16 MLX** conversion | |
| of [`ZhengPeng7/BiRefNet`](https://huggingface.co/ZhengPeng7/BiRefNet) (MIT) — a Swin-L + ASPP-Deformable | |
| foreground segmentation / matting model at **1024×1024**, producing a single-channel soft-alpha matte | |
| (white = foreground). The fast, general-purpose tier. | |
| **Parity:** IoU **0.9905** vs the PyTorch reference (zero unused keys). fp16 runtime validated for production | |
| matting quality. | |
| ## Use (Swift / MLX) | |
| Loaded by [`mlx-birefnet-swift`](https://github.com/xocialize/mlx-birefnet-swift) — the vendored `BiRefNet` | |
| core plus a conformant MLXEngine `matting` ModelPackage: | |
| ```swift | |
| import BiRefNet | |
| let pipeline = try BiRefNetPipeline.fromPretrained("model.safetensors", dtype: .float16) // inputSize 1024 | |
| let matte = try pipeline(cgImage).maskCGImage() // source-resolution soft-alpha | |
| ``` | |
| Converted from the official PyTorch checkpoint via the package's `birefnet-convert` (PyTorch NCHW → MLX NHWC; | |
| 754 → 687 tensors). Single-file `model.safetensors`. See also the higher-res tier | |
| [`mlx-community/BiRefNet_HR-matting-fp16`](https://huggingface.co/mlx-community/BiRefNet_HR-matting-fp16). | |