1. What is Image Upscaler?

Image Upscaler is a simple extension that enables you to upscale an image within your browser. It uses two different techniques to upscale the input image. The first (and default) method is using the HTML5 Canvas API to upscale the image up to 10 times the original size. The Canvas API has a built-in interpolation method for smoothing the final pixels within the image file. The final result is somehow satisfactory but lacks some details and may not be sharp enough. The other method used artificial intelligence to upscale the input image. This method is still in the experimental stage and currently can upscale an image up to a maximum of 4 times the original size. The final result is better than the previous method and has more details and sharpness. However, it has a much slower process. For the AI method, it is recommended to use small images as the upscaling process with artificial intelligence is computationally expensive. To make it easier, you can enable the patch option to divide the input image into patches before upscaling, but the final result will have the patchs borderline. To get more info about this addon please read the below FAQ items.

2. How can I work with this add-on?

As mentioned above, please drag and drop an input image file in the interface (top-left area). This extension supports a wide variety of input image file formats such as png, jpg, webp, tiff, etc. Once the image is inserted into the app, please adjust the upscaling level. Without artificial intelligence, you can upscale up to 10 times the original size, but with artificial intelligence, the maximum value is 4 times. If the AI method is chosen, you can specify a precision level. The default option is - thick - which is the best level. There is also an option to split the original image into patches before upscaling with AI. If this option is selected, you can upscale larger images as well. Without this option only upscaling small images is recommended. The final option for the AI upscaler is the patch size, which is set to 16 pixels by default. As mentioned before the default method uses HTML5 canvas API to upscale images. On the other hand, the AI method uses TensorFlow and UpscalerJS open-source projects to upscale the input image. This method is still a work in progress and might have some bugs. The AI method tries to upscale the input image with maximum details and precision using a modern artificial intelligence engine. Because the AI process is computationally expensive and uses a lot of memory, it might slow down your browser when the upscaling process is running.

3. How can I download the source code for Image Upscaler?

To download the source code for this extension from Chrome Web Store, it is recommended to use Extension Source Downloader. With this addon, you can download the source code as a ZIP or CRX format to your machine. If you want to download the source code from the Firefox addons store, please open the firefox download link (if available) in the Firefox browser and then right-click on the - Add to Firefox - button and select - Save Link As... - item. Choose the destination folder on your machine and then save the file in XPI format. You can then rename the XPI format to a RAR or ZIP file. Some extensions may have a GitHub repo address, which you can use to download the source code as well. But, it may not be the latest version of the addon. Therefore, downloading the source code from the official web stores is the best option as it always gives you the latest version of the addon.

4. How does Image Upscaler addon work?

Image Upscaler uses two different methods for the upscaling process. The first method does not need any third-party libraries and uses only the native HTML5 Canvas API. The second method uses an artificial intelligence technique and needs two third-party libraries called TensorFlow and UpscalerJS. If the input image is large please use the first and default method only. But if you have a small image and need to upscale it with more details and sharpness, you can use the second method. If the input image is large and you want to use the AI method anyways, please enable the patch option to prevent the browser from freezing or crashing.

5. What is new in version 0.1.1+?

Image Upscaler version 0.1.1+ uses two different AI methods for upscaling images. The first AI is client-side and uses TensorFlow & UpscalerJS libraries mentioned above. The new server-side AI uses ClipDrop API for upsacling images. This API is deveped by Stability AI and uses the Stable Diffusion project for upscaling. This project is an image synthesis engine with latent diffusion models. Please read the above GitHub page to get more info about this new AI option.

6. What is TensorFlow?

TensorFlow is an open-source machine learning framework developed by Google. It is widely used for various applications, including computer vision, natural language processing, and other machine-learning tasks. TensorFlow uses data flow graphs to build models that can be trained and deployed on various platforms such as desktops, servers, and mobile devices. It provides a variety of APIs for building and training models, including high-level APIs for beginners and low-level APIs for more experienced users. TensorFlow also supports a wide range of languages such as Python, C++, Java, and Go, making it accessible to a broad range of developers. Its popularity and ease of use have made it one of the most popular machine-learning frameworks available today. To get more info about this library please visit this page.

7. What is UpscalerJS?

UpscalerJS is an open-source JavaScript library that can be used to upscale images using machine learning algorithms. The library is based on super-resolution technology and can increase the resolution of an image without losing its quality. UpscalerJS uses deep learning models to upscale the image and produces a high-resolution image that looks more detailed and sharp. It supports various image formats such as PNG, JPEG, GIF, etc., and can be used on both client-side and server-side applications. To get more info about this library please visit this page.

8. How do I turn the extension OFF?

When app UI is closed, this addon is completely OFF and has no usage (RAM/CPU) on your system at all. Alternatively, if you want to completely turn off the addon, please head to the extensions tab in your browser and then click on the disable button from there.

9. How can I reload the app UI?

When you open the app UI, you will see a reload button on the top right corner of the screen. Please press this button to reload the UI. Also, note that reloading the UI will terminate all active operations and reset the optimization process.

10. How can I download the upscaled image?

As mentioned above, once the upscaling process is done, the upscaled image will be rendered in the top-right area. Simply click on the - download button - to download the upscaled image. Please note that the image will be downloaded to the default download location on your machine.

11. How can I change the download location for the optimized image?

To change the download location, please head to the settings tab in your browser and then find the download section. Within this section, you can adjust the download path. This will globally change the download location for all your downloads in the browser.

12. What input file format(s) does this addon accept?

This addon accepts most common image file formats including PNG, BMP, JPG, WEBP, TIFF, etc.

13. Do I need an internet connection to work with this addon?

No, this addon does not need any internet connection to work with. Simply open the UI and start vectorizing an image. Moreover, it works on all modern browsers and platforms.

14. Where can I find the privacy policy for Image Upscaler?

Please read the privacy policy for this extension here.