How does AI object removal work?

The tool uses the LaMa (Large Mask Inpainting) AI model. You paint a mask over the area you want removed, and the model fills it in based on the surrounding context, generating plausible textures and patterns.

Why do I need to select a 512x512 region first?

The LaMa model processes images at a fixed 512x512 pixel resolution. The region selector lets you choose which part of a larger image to edit. After processing, the result is composited back onto the original at full resolution.

How large is the AI model download?

The LaMa model is approximately 208 MB. It downloads once and is cached in your browser for instant future use. Processing takes 5-15 seconds depending on your device.

Does the tool upload my images to a server?

No. The entire process runs locally in your browser using WebAssembly. Your images never leave your device.

Remove
Object
from
Photo

Paint over unwanted objects in a photo and let AI fill in the background.

Upload Image

JPG, PNG, or WebP. Select a region, paint over the object to remove, and let AI fill the background.

Learn more

How does AI know what to put behind the object you removed?

Was this useful?

Background Remover

Remove image backgrounds and download a transparent PNG — works on any image.

Remove Gemini Watermark

Remove the Gemini sparkle watermark from AI-generated images. Batch processing, lossless, instant.

Depth Map Generator

Generate a depth map from any image using AI. Download grayscale or colorized depth maps, and explore a 3D parallax preview.

Image to Text (OCR)

Extract readable text from image files inside your browser.

Color Picker

Pick colors visually, sync HEX/RGB/HSL values, and extract dominant palettes from uploaded images.

Image Converter

Convert any image to JPG, PNG, WebP, GIF, BMP, TIFF, or AVIF. Accepts all major image formats as input.

RemoveObjectfromPhoto