Swin2sr Lightweight X2 64

🚀 Xenova/swin2SR-lightweight-x2-64

This project adapts the model from https://huggingface.co/caidas/swin2SR-lightweight-x2-64 with ONNX weights to be compatible with Transformers.js, enabling image upscaling in the web environment.

🚀 Quick Start

This model is based on the caidas/swin2SR-lightweight-x2-64 base model and uses the transformers.js library. It provides ONNX weights to be compatible with Transformers.js.

📦 Installation

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @xenova/transformers

💻 Usage Examples

Basic Usage

Example: Upscale an image with Xenova/swin2SR-lightweight-x2-64.

import { pipeline } from '@xenova/transformers';

// Create image-to-image pipeline
const upscaler = await pipeline('image-to-image', 'Xenova/swin2SR-lightweight-x2-64', {
    // quantized: false, // Uncomment this line to use the quantized version
});

// Upscale an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/butterfly.jpg';
const output = await upscaler(url);
// RawImage {
//   data: Uint8Array(786432) [ ... ],
//   width: 512,
//   height: 512,
//   channels: 3
// }

// (Optional) Save the upscaled image
output.save('upscaled.png');

📚 Documentation

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).