The tool enlarges an image 2× or 4× using the Real-ESRGAN neural network. Instead of simply stretching pixels, the network reconstructs sharp edges and textures. This is useful for improving the quality of a small photo for printing or a product listing, or for enlarging an AI-generated image or an old picture from the internet. Everything is processed in your browser.
Your photo is not uploaded to a server: the neural network runs on your device. Only the model (from mozgi.io) and libraries (from cdnjs and jsDelivr) are downloaded from the internet. The site collects visit statistics: Cloudflare Web Analytics without cookies, while Yandex Metrica and Google Analytics load only if you've accepted cookies. Learn more in our privacy policy.
After upscaling, the PNG can be large — compress the photo online to WebP. Photo cropping helps you adjust the frame, and for 3D effects there's the online depth map tool.
Regular enlarging simply duplicates pixels, and the image turns blurry. The neural network restores edges and texture, so the result looks sharper.
Yes — choose "Maximum": that model is better at removing JPEG blocks. It won't restore scratches or lost facial detail.
The result would exceed the 16.7 MP limit. Choose 2× or open a smaller source image.
For the first hour you can use it without signing up or subscribing — the hour counts from the first time you open any of the locked mozgi.io tools. After that you need a subscription: it gives full access to all locked tools, prompts and skills. There are no watermarks.