Depth Anything V2 Small

🚀 Depth Estimation with Transformers.js

This project makes the depth-anything/Depth-Anything-V2-Small model compatible with Transformers.js using ONNX weights. It enables depth estimation in a web environment.

🚀 Quick Start

📦 Installation

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

npm i @huggingface/transformers

💻 Usage Examples

Basic Usage

Example: Depth estimation w/ onnx-community/depth-anything-v2-small.

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

// Create depth estimation pipeline
const depth_estimator = await pipeline('depth-estimation', 'onnx-community/depth-anything-v2-small');

// Predict depth of an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg';
const { depth } = await depth_estimator(url);

// Visualize the output
depth.save('depth.png');

📄 License

This project is licensed under the apache-2.0 license.

⚠️ Important 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).