Home / Images / AI watermark remover

AI watermark remover

Upload an image and select the watermark by hand, pay per run; processing starts automatically once the Alipay payment succeeds, only the selected area is repainted, and the result can be downloaded right away.

Pay per run (¥1 per run), no sign-up, Alipay online payment only. The original image is sent to our backend for AI inference only after payment succeeds; nothing is written to server storage, selection and coordinate mapping happen in your browser, and failed runs are refunded automatically.

More tools in Images

Frequently asked questions about AI watermark remover

How much does this tool cost?
It is charged per use, ¥1 each time. Clicking "Start watermark removal" opens the payment window first; processing starts automatically once the payment succeeds on the Alipay checkout page, so no second click is needed. One payment covers exactly one run, and retrying a failed run needs no new payment.
Can I use it without paying?
No. Removing a watermark needs AI inference and costs compute, so it is charged per use; processing does not start without payment, and your image does not leave the browser before you pay.
What if the checkout page will not open, or nothing happens after payment?
The checkout page is generated by our backend; if it will not open, click "Get a new payment order" to fetch another one and try again. Once the payment succeeds the page starts processing automatically, and you can also click "I have paid" to confirm immediately. If the payment is still not credited after a long wait, keep the order number and contact support.
Are images uploaded to a server?
Yes. Removal needs AI inference, so the original image is sent to our backend only after the payment succeeds; the image is not written to server disk, and the result is sent straight back to the browser to display and download, with nothing retained. If you only pick an image and select areas without paying, the image never leaves the browser.
How are the coordinates of the selected areas computed?
Selections are recorded in the true pixels of the original image, so displaying the preview scaled down on the page does not affect accuracy: exactly the area you select is the area that gets processed.
Can I select several watermarks in one go?
Yes. Drag out several rectangles over the watermarks, up to 8 at a time; drag inside a rectangle to move it, drag a corner or an edge to resize it, and remove one with the × in its upper right corner or the delete entry in the list.
Will the image quality drop after removal?
The result is repainted by the backend AI model; areas outside the selection are not processed, but the repainting and compression detail depend on the model. Compare the download with the original before using it, and keep the original for important material.
What if the result is not good enough? Can I get a refund?
AI repaints the selected areas, and in most cases one run clears the watermark; dense watermarks, busy backgrounds or small images may leave traces, and the actual result is what counts. That is why there is a confirmation above the payment button that has to be ticked first: the fee covers one run, only a model-call failure or an error response gets an automatic refund to the original payment method, and if the result is not good enough you can adjust the selection or the prompt and try once more. Keep a copy of the original for important material.
Is the prompt required? What does it do?
No, it can be left empty and processing still works, in which case only the selected areas are repainted. If you fill it in, it goes to the AI together with the image to describe what the watermark looks like (colour, transparency, text content) or to constrain the repair, for example "semi-transparent white text in the lower right, restore the wood grain behind it". The limit is 1000 characters; anything beyond is cut off as you type, and an empty or whitespace-only prompt counts as no prompt.
How long does AI processing take for one image?
It depends on the image size and the backend queue, commonly between a few seconds and a dozen or so. The page shows the processing status live; on timeout you get a notice and this payment is kept, so you can retry directly without being charged again.
Will processing overwrite the original file?
No. The original stays read-only and the result is saved as a new download you can review before replacing anything; the original file is never touched.
Which image formats are supported?
Input accepts any common format the browser can decode (JPEG, PNG, WebP, GIF, BMP and more); export supports JPEG, WebP and PNG, and each tool offers whichever of those its page lists (code-to-image exports PNG or JPEG, image-to-ASCII exports TXT / PNG / SVG / HTML).
Are images uploaded to a server?
Not for anything except AI watermark removal, AI background removal, AI image generation and AI upscaling. Compression, cropping, collage, image-to-Base64, code-to-image and image-to-ASCII all run locally in the browser, so images never leave your device; the four AI tools need model inference, so the content (the image or the description) is submitted to our backend only after payment succeeds, and the result image is sent straight back to the browser. The source image used by AI image generation and AI upscaling is also uploaded to our site, only so the model can fetch it; the page never shows or hands out an image link, and the result image is still never written to disk.

About Local Toolbox

Local Toolbox gathers the small tools you reach for every day into one place: formatters, encoding converters, date maths, ID card and address parsing, image and QR code handling, password and amount conversion. Open a page and start working — no sign-up, and almost every tool has no usage limit.

Most features compute inside your browser, so your input never leaves your device; the pages are plain static assets, load fast and keep working offline. The IP page asks our backend for your outbound address when it opens and sends none of your input. AI watermark removal, AI background removal, AI image generation and AI upscaling send content to our backend for inference (watermark removal is ¥1 per run; background removal is ¥1 per run; image generation and upscaling are priced by resolution — 2K ¥2, 4K ¥3); AI annotation sends images to a large model that locates the target and returns coordinates (¥0.5 per image, refunded only when every image in the batch fails); AI flowchart, AI mind-map and AI Mermaid chart generation send your text description to a model that builds the diagram (three separate products, charged ¥0.5, ¥0.5 and ¥0.5 per run respectively); and the accounting helper sends the income, expense, social-insurance and balance figures you fill in to generate a report (¥0.5 for the spoken analysis, ¥1 for the report). These features accept Alipay only, upload nothing before payment succeeds, and refund automatically if processing fails.

Links