Remove AI Watermarks
Strip visible AI watermarks and provenance metadata from images. This demo runs the CPU, lossless commands of the open-source library: identify provenance, remove known visible marks, strip provenance metadata. iPhone HEIC and AVIF are supported alongside PNG / JPEG / WebP.
The invisible SynthID removal path needs a GPU and the diffusion stack, so
it is not in this demo. Run it locally: pip install "remove-ai-watermarks[qwen-zimage]".
Source, docs and issues: github.com/wiltodelta/remove-ai-watermarks (Apache-2.0).
Read every locally-readable provenance signal (C2PA issuer, EXIF/XMP generator, IPTC 'Made with AI', China TC260 AIGC label, xAI signature, SynthID metadata proxy, visible marks) into one verdict.
Detect and remove every registered visible AI-provenance mark in one pass by localize -> fill. Only the mark footprint is touched; the rest of the image is left alone. Sensitivity sets how hard a borderline mark is trusted: auto relaxes only on same-vendor evidence, while strict never relaxes. The fill here is the classical cv2 inpaint; MI-GAN / LaMa run locally.
Inspect or losslessly strip AI / provenance metadata (C2PA, EXIF, XMP, IPTC, PNG chunks, the China TC260 AIGC label). Stripping never touches the pixels: PNG/WebP stay pixel-identical and JPEG keeps its DCT scan bit-for-bit.
Watermarking is a weak trust signal: a mark that is almost always present yet removable can make a cleaned forgery look more trustworthy. Half of this tool is identify, which reads provenance rather than removing it. The point is user autonomy over your own AI generations, not stripping a third party's paid asset. See the repo for the legal limits on removing AI labels.