Jia-Liu/big-lama-coreml

LaMa (Large Mask Inpainting) - Core ML Format

LaMa model converted to Apple Core ML format for macOS GPU-accelerated inference.

📖 Original Model

• Source Repository: https://github.com/advimman/lama
• License: Apache 2.0
• Paper: Resolution-robust Large Mask Inpainting with Fourier Convolutions
• Project Page: https://advimman.github.io/lama-project/
• Authors: Roman Suvorov, Elizaveta Logacheva, Anton Mashikhin, et al.

🔄 Conversion Details

This model was converted using the CoreMLaMa project by @mallman.

• Original Model: big-lama.pt (196MB)
• Original Download: https://github.com/Sanster/models/releases/download/add_big_lama/big-lama.pt
• Conversion Tool: CoreMLaMa
• Precision: FP32
• Compute Units: CPU + GPU
• Output Format: Core ML Package (.mlpackage)

Conversion Steps

# Clone CoreMLaMa
git clone https://github.com/mallman/CoreMLaMa
cd CoreMLaMa

# Create environment
conda create -n coremlama python=3.10
conda activate coremlama

# Install dependencies
pip install -r requirements.txt
pip install iopaint

# Run conversion
python convert_lama.py

📥 Usage

Load the model in a macOS application using Core ML:

import CoreML
import Vision

let config = MLModelConfiguration()
config.computeUnits = .cpuAndGPU

let model = try LaMa(configuration: config)

📊 Model Inputs/Outputs

Inputs:

• image: 3-channel RGB image, 800×800 pixels
• mask: 1-channel grayscale mask, 800×800 pixels

Output:

• output: Inpainted 3-channel RGB image, 800×800 pixels

⚖️ License & Attribution

This repository contains a format conversion of the original LaMa model. All rights and credit belong to the original authors.

• Original License: Apache 2.0
• Conversion: Format-only, no weight modifications
• Conversion Tool Credit: CoreMLaMa by @mallman

📚 Citation

If you use this model, please cite the original paper:

@inproceedings{suvorov2022resolution,
  title={Resolution-robust Large Mask Inpainting with Fourier Convolutions},
  author={Suvorov, Roman and Logacheva, Elizaveta and Mashikhin, Anton and others},
  booktitle={WACV},
  year={2022}
}