Image tools

Add a watermark to a photo: text or a logo, dragged wherever you want it or tiled diagonally across the frame, then repeated over a whole folder at once.

An alt text generator that looks at the photo and writes the first draft, using Microsoft's Florence-2.

Remove the background from a photo and keep a transparent PNG, or set the cut-out on a solid color as a JPEG. It finds the subject itself, or you tap or circle the one you want.

Blur, pixelate or black out faces in a photo. A small detector boxes the faces it finds, small ones in a group included, and you box whatever it misses.

AI image upscaler that enlarges a photo 2× or 4×, or works back from the exact print size you type in. Rebuilds detail instead of stretching pixels.

Remove a photobomber, a bin or a stray cable from a photo. Tap it, circle it or paint over it, see how much of the frame it takes, and MI-GAN fills the gap.

Extract text from an image or a scanned PDF, using a neural engine that reads 50 scripts and copes with a page shot at an angle.

An EXIF viewer for JPEGs and PNGs that lists every block a clean copy removes (EXIF, XMP, IPTC, PNG text), keeps GPS on the page, and rewrites nine fields.

Favicon generator: one image in, a package out. Six PNGs, a multi-size favicon.ico, a manifest with your colours, the head tags, and the 16 seen in a real tab.

An image color picker with a magnifier: hover to zoom in on the pixels, click the one you want, and copy its HEX, RGB or HSL code.

Compress a JPEG, PNG or WebP and compare it side by side. Smart picks the quality, Quality takes a slider, Target searches for a size in KB. One file or a folder.

Image converter that writes AVIF, WebP, JPEG, or PNG with the WebAssembly codecs from Squoosh, and reads iPhone HEIC, TIFF, JPEG XL and SVG going in.

Crop an image to 1:1, 16:9, 9:16 or a ratio you type in, with the cut taken from the full-resolution file rather than the preview on screen.

Resize an image by width, percent, a KB budget or a print size in millimetres. The preview and the pixel counts redraw as you type.

Convert an image to SVG with the vtracer engine. Three tracing presets, five manual sliders, and a shape count under the result that tells you how heavy it is.

A passport size photo maker with ten document presets, from the US 2×2 inch to China's 33×48 mm, plus a head-and-eye guide and a 4×6 print sheet at 300 DPI.