Supercharge Your Image Processing: Revolutionary AI Tools Powered by WebGPU

Bytefer - Nov 4 - - Dev Community

As a web engineer passionate about emerging technologies, particularly AI, I've been exploring Microsoft's onnxruntime-web library. Using this powerful tool, I developed BatchTool - an online AI-powered image processing platform.

ONNX Runtime Web is a Javascript library for running ONNX models on browsers and on Node.js. ONNX Runtime Web has adopted WebAssembly and WebGL technologies for providing an optimized ONNX model inference runtime for both CPUs and GPUs.

Currently, BatchTool offers two main features:

  1. Batch Background Removal
  2. Batch Objects/Watermarks Removal

Batch Background Removal - BatchTool

Key Features of BatchTool

  • Privacy-First: Uses local AI models - no server uploads required
  • AI-Powered: Leverages artificial intelligence to simplify complex tasks
  • High Performance: WebGPU acceleration enables processing each image in milliseconds
  • Efficient Batch Processing: Process multiple files with a single click
  • User-Friendly: Simple, intuitive interface with zero learning curve
  • Cross-Platform: Works in your browser - no installation needed

Batch Background Removal

Model Download

Remove Backgrounds runs on your browser and does not need to be uploaded to a server. Simply download the corresponding model on first use. After that, the model file will be cached in the browser cache and you can use it directly the next time you use it.

Displayed on the following screen: WebGPU ✅ indicates that the current device supports WebGPU acceleration.

Batch Background Removal WebGPU - BatchTool

Select Images

After selecting the images to be processed, Batch Tool will automatically detect the current running environment and enable WebGPU acceleration mode if the current environment supports WebGPU acceleration, otherwise it will automatically switch to CPU mode.

Batch Background Removal Result - BatchTool

Once the image background has been removed, click on the Compare Images icon to see the effect of the removed background.

Image from: https://pixabay.com/

Compare Images - BatchTool

Next, you can click on the batch download button to batch download all the images that have been processed.

Batch Download - BatchTool

Batch Objects/Watermarks Removal

Model Download

As with the removal of the background, the objects removal is run on the browser and does not need to be uploaded to the server. It is only necessary to download the corresponding model on the first use. After that, the model file will be cached in the browser cache and can be used directly the next time you use it.

Scenario 1

In this scene, you can select multiple images at once, and then perform an object erase operation on each image one by one.

Batch Objects Removal Scene 1 - BatchTool

After completing the erasure, you can either download the repaired single image immediately, or wait until all the images have been adjusted and then download them all at once.

Scenario 2

This scenario is suitable for batch erasing watermarks in the same area on multiple images of the same size. The steps are also very simple, just four small steps.

1.Select multiple pictures to be processed;
2.Enable Batch Erase Same Area Watermark mode;

Batch Erase Mode - BatchTool

3.Select the first picture and draw the watermark area with the brush;
4.Click the Repair button (eraser icon) on the ribbon.

Batch Erase Auto Mode - BatchTool

After that, the program will be automatically executed, when a picture processing is completed, it will display the completed logo on the right thumbnail, as shown in the following figure:

Batch Erase Mode Result - BatchTool

Scenario 2 is very suitable for batch removal of fixed area watermarks, which greatly improves work efficiency. If your computer supports WebGPU acceleration, the processing speed will be very fast, with an average of just a few hundred milliseconds for a single image.

I invite you to try out BatchTool's image processing capabilities! If you encounter any issues while using the tool, please don't hesitate to leave a comment.

. . .