GPT Watermarker

C2PA Detector

Privately scan an image for familiar C2PA Content Credentials marker strings in your browser. This quick check does not parse manifests or verify AI and edit provenance.

C2PA

Detect Content Credentials

Look for common C2PA / Content Credentials marker strings in an image.

C2PA Detector: Check Images for Content Credentials

C2PA Content Credentials are signed provenance manifests that can record how media was made and edited. This browser tool performs a quick private search for familiar C2PA, JUMBF and Content Credentials marker strings. It does not parse a manifest, validate its signature or return a definitive provenance verdict.

If credentials are present and you need a clean file, the detector routes you to the remover that strips them.

What C2PA / Content Credentials Are

A signed manifest in the file header naming the model and timestamping the generation.

C2PA (the Coalition for Content Provenance and Authenticity) defines a tamper-evident manifest — often branded "Content Credentials" — embedded in JPEG, PNG and other files. It can name the generating model, timestamp the creation, and chain edits together. For AI images it's the clearest machine-readable proof of origin, which is exactly why so many platforms scan for it on upload. This detector looks for the C2PA, JUMBF and Content Credentials markers in the file bytes and reports what it finds.

Where C2PA Comes From

AI generators, editing software, and increasingly the camera in your phone.

C2PA can appear on images from AI generators, editing software and supported cameras. A conforming parser and verifier can inspect a manifest and its signature; a marker-string scan like this one cannot establish that the manifest is valid or absent. C2PA is also separate from pixel-domain watermarks that may survive metadata stripping.

Detect, Then Remove the Credentials

One pass from finding the manifest to downloading a file without it.

When Content Credentials are found, the "Remove" button routes to the remover, which rewrites the file to drop the C2PA manifest and other provenance metadata while leaving the visible image untouched. If your image is from Gemini or ChatGPT, note that stripping C2PA alone won't remove SynthID — use the SynthID detector and remover for the pixel-level layer.

C2PA & Content Credentials FAQs

Straight answers on what each workflow removes, how files are handled, and what result you should expect.

How do I check if an image has C2PA / Content Credentials?

Upload it here for a private local scan of common C2PA and Content Credentials marker strings. It is a screening hint, not a definitive answer or signature verification.

Which tools add C2PA to images?

Google Gemini, OpenAI ChatGPT and DALL·E, xAI Grok, Adobe Firefly and Photoshop, plus a growing number of cameras and apps. Platforms like Adobe, LinkedIn and TikTok read it on upload.

Is removing C2PA the same as removing SynthID?

No. C2PA is metadata in the header and is removed by re-writing the file. SynthID is a separate signal in the pixels that survives a metadata strip — for Gemini and ChatGPT images you need the SynthID remover too.

Does detecting C2PA upload my file?

No. The scan runs entirely in your browser. Removal is a separate, optional step.

How do I remove Content Credentials?

Click through to the relevant remover. The Grok metadata-only flow strips supported provenance metadata without re-encoding image pixels; other hidden-watermark flows may also process the pixels.
    C2PA Detector — Check Images for Content Credentials