Everything, including the awkward parts

Yes, completely. There is no account, no trial, no credit system, no per-file charge and no watermark on the output. The processing happens on your own device, so there is no server cost to pass on and no reason to meter it. Use it as often as you like.

Drop the file onto the page, or press the button and pick it. The sparkle is located automatically by matching it against the known Gemini logo shape, then removed, and you get a before/after slider to check the result before downloading. It takes a second or two and there is nothing to configure.

Yes. Video is handled frame by frame, so motion and detail survive instead of being blurred over. The mark sits in the same place on every frame, so it is located once and then removed throughout. Frame rate is preserved and the original audio is carried across. A clip takes roughly its own length to process, because it is rebuilt in real time.

The whole clip, frame by frame. The mark sits in the same place on every frame of a Veo 3 or Google Flow export, so it is located once from frames sampled across the video and then removed throughout — which is also why the result is steady instead of flickering, the way a per-frame guess would. Resolution and frame rate are preserved and the audio is carried across. Expect a clip to take roughly its own running time, because the frames are rebuilt as they play.

Yes — Chrome on Android and Safari on iPhone both run it, images and video alike, with nothing to install. Two limits are worth knowing. Phones record video as H.265/HEVC by default and browsers generally cannot decode that, so you may be asked to convert; and a phone has much less memory for holding large frames, so a long 4K clip is the one job better done on a computer.

For images, no: the dimensions, the bit depth and every pixel outside the watermark are untouched, and a PNG is not re-compressed. For video the answer is honest rather than convenient — rebuilding the frames means re-encoding the file, and any re-encode costs a little. Resolution, frame rate and audio are preserved, but the container and bitrate are chosen by your browser. Keep your original if it is a master you will edit further.

Neither. It is a web page: open it and drop a file on it. There is no extension, no desktop app, no sign-up, no email and no credit card. Because the processing happens on your device rather than a server, there is also nothing to meter — no daily limit and no watermark on the output.

Your files, no — never. They are read and rebuilt inside your browser, so there is nothing about them for anyone to collect: not the image, not its name, not its size, not whether a watermark was even found. The page itself is a different question, and the honest answer is that it counts page views and carries Google ads, and those ads set cookies the way ads everywhere do. Neither can see what you process. See the privacy page for exactly what is and is not recorded.

Not during normal use. The file is read with the browser File API, decoded to a canvas, processed by JavaScript on your machine and handed back as a download. Load the page, disconnect from the internet, and watermark removal still works.

There are two exceptions, and neither ever happens on its own. The first: some videos use a codec your browser cannot decode at all — H.265/HEVC above all, which is what most modern phones record. Nothing in the browser can open those files. When that happens you are offered a button to convert that one file on our server; it is re-encoded to H.264, sent straight back, and deleted as the response finishes. If you decline, nothing is transmitted and you are told how to re-encode it yourself. The choice is always explicit — there is no silent fallback.

The second: the chat to PDF tool can fetch a chat share link for you, and a browser is not allowed to read another site's pages, so that link is requested by our server and handed straight back. Nothing is stored. Pasting a conversation instead keeps even that on your device.

No, and you should not trust any tool that says it does. SynthID is Google's invisible watermark, spread statistically across the whole image rather than drawn in one corner. This tool removes the visible sparkle logo only. The invisible provenance signal stays in the file and remains detectable. Anyone claiming "zero traces" is describing the logo, not the provenance data.

Blurring destroys the detail the watermark was sitting on and leaves an obvious smudge that reads as a cover-up. Cropping changes your composition and aspect ratio. Reverse alpha blending is different: because the logo was composited with a known formula, that formula can be solved backwards to recover what was underneath, at the original sharpness.

The watermark was drawn with result = α·logo + (1 − α)·original. Rearranged, that gives original = (result − α·logo) ÷ (1 − α). Given the alpha map for the mark, the pixels underneath fall straight out of the arithmetic. Where alpha approaches 1 the division becomes unstable, so those few core pixels are filled by diffusion from the recovered ring instead.

Images as PNG, JPG, WEBP and AVIF; video as MP4, MOV and WEBM. Sources the detector knows by name include Gemini, Nano Banana, Imagen, Whisk, Veo and Google Flow. Anything else can still be handled in manual mode by brushing over the mark.

Only what your own device can hold in memory. There is no server quota, so the practical ceiling is your RAM and your browser's canvas limits. Long 4K videos are the realistic constraint — those are processed frame by frame and will take roughly as long as the clip itself runs.

Re-encoding uses MediaRecorder, and the container it can write depends on your browser. Chrome and Edge will produce MP4 with H.264 where the codec is available and fall back to WEBM/VP9 otherwise; Safari prefers MP4. The tool picks the best container your browser reports and tells you which one it used before you download.

That depends on you, not on the tool. Removing a watermark from your own generated output for layout or print reasons is ordinary work. Passing AI-generated media off as a real photograph or real footage is not, and in several jurisdictions disclosure is now a legal requirement rather than a courtesy. Google's generative AI terms also have their own say. Check both before you publish.