RMBG-2-CoreML

VincentGOURBIN/RMBG-2-CoreML

RMBG-2-CoreML is a image segmentation model from VincentGOURBIN. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for coreml. The card lists the license as cc-by-nc-4.0.

CoreML conversion of BRIA AI's RMBG-2.0 background removal model, optimized for Apple Neural Engine (ANE).

Downloads · 30 days

134

16% of all-time downloads

All-time downloads

858

Public

Repo size

728 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin722 MB · 99%

At a glance

Task: Image Segmentation
Library: coreml
License: cc-by-nc-4.0
Model type: RMBG-2-CoreML
Access: Public
Created: Feb 4, 2026
Updated: Feb 5, 2026
SHA: 0da071b5

Base models

briaai/RMBG-2.0

Model card

From the Hugging Face model README

RMBG-2 CoreML - Background Removal Model

CoreML conversion of BRIA AI's RMBG-2.0 background removal model, optimized for Apple Neural Engine (ANE).

Model Description

This is a native ML Program format CoreML model converted from RMBG-2.0 (BiRefNet architecture) for high-quality background removal on Apple devices.

Key Features

Native CoreML ML Program format - Full ANE compatibility
INT8 weight quantization - Reduced model size (233MB vs 461MB)
No custom layers - Uses only native CoreML operations
1024x1024 input resolution - High-quality segmentation
Fast inference - ~3-5 seconds on Apple Silicon

Usage

With RMBG2Swift Package

import RMBG2Swift

// Simple one-liner
let rmbg = try await RMBG2()
let result = try await rmbg.removeBackground(from: image)

// Access the result
let outputImage = result.image  // Image with transparent background
let mask = result.mask          // Grayscale segmentation mask

Swift Package: github.com/VincentGourbin/RMBG2Swift

Manual Integration

import CoreML

// Load the model
let config = MLModelConfiguration()
config.computeUnits = .all  // Enable ANE

let model = try await MLModel.load(contentsOf: modelURL, configuration: config)

// Prepare input (1024x1024, NCHW format with ImageNet normalization)
let input = MLDictionaryFeatureProvider(dictionary: ["input": inputArray])

// Run inference
let output = try model.prediction(from: input)

// Get mask from output_3 (full resolution)
let mask = output.featureValue(for: "output_3")?.multiArrayValue

Model Details

Property	Value
Architecture	BiRefNet
Input Size	1024 x 1024
Input Format	RGB, NCHW [1, 3, 1024, 1024]
Normalization	ImageNet (mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
Output	4 scales (output_0 to output_3), use output_3 for full resolution
Format	ML Program (.mlpackage)
Weight Quantization	INT8 (symmetric linear)
Model Size	~233 MB
Minimum OS	macOS 13+ / iOS 16+
Compute Units	All (CPU, GPU, ANE)

Performance

Tested on Apple Silicon:

Device	Compute Units	Inference Time
M1 Pro	.all (ANE)	~5s
M1 Pro	.cpuAndGPU	~3s

Note: ANE performance varies by device. The INT8 quantization improves memory efficiency and model size while maintaining quality.

Files

Two model versions are available:

File	Size	Description
`RMBG-2-native.mlpackage/`	461 MB	Original FP32 model
`RMBG-2-native-int8.mlpackage/`	233 MB	INT8 quantized model (recommended)

Recommended: Use the INT8 version for better memory efficiency and smaller download size with equivalent quality.

License

Creative Commons Attribution-NonCommercial 4.0 (CC BY-NC 4.0)

Free for non-commercial use: Research, personal projects, education
Commercial use requires a separate license from BRIA AI

For commercial licensing, contact: bria.ai/contact-us

Attribution

This CoreML conversion is based on the RMBG-2.0 model by BRIA AI:

Original Model: briaai/RMBG-2.0
Architecture: BiRefNet
Creator: BRIA AI