AI Image Detector

About this tool

Check whether an image carries C2PA Content Credentials, read EXIF/XMP, and scan pixels for invisible spread-spectrum watermarks in your browser. If the file looks AI-marked, you can strip that watermark locally and re-run the scan. When Sightengine keys are configured, you can optionally send a copy for a pixel-based AI-generated score. A valid trusted signature is evidence of origin; a missing manifest or a forensic score is not proof.

What you can do

• C2PA / Content Credentials — Parse the signed manifest locally with the Content Authenticity SDK: signer, claim generator, actions, and IPTC digital source type when present.
• Invisible watermark scan — A local residual/FFT check looks for sparse spread-spectrum carriers (SynthID-style and similar). It is not Google’s private decoder.
• Local watermark strip — If the file is read as AI-marked, re-encode in the browser to disrupt pixel watermarks, drop C2PA/EXIF, then re-analyze the new JPEG.
• EXIF and XMP — Show camera make/model, software, timestamps, and GPS if the file still has them. Tags are easy to strip or forge.
• Optional Sightengine pixel check — If SIGHTENGINE_API_USER and SIGHTENGINE_API_SECRET are set, request a genai confidence score and per-generator hints. Off by default when keys are missing.

Related tools

• Image Compressor
• Favicon / Icon Generator
• File Converter

Frequently asked questions

Is this a reliable AI image detector?

No single detector is a proof. A valid C2PA signature from a trusted issuer (for example OpenAI, Google, Adobe, or a camera vendor) is the strongest origin signal. Missing Content Credentials are common and prove nothing. The local watermark scan and Sightengine’s pixel score are statistical hints and can fail on screenshots, heavy JPEG compression, collages, and new generators.

Are my images uploaded?

C2PA, EXIF, the invisible-watermark scan, and watermark stripping run in your browser on the original file bytes. Nothing is uploaded for those steps. If you enable the optional Sightengine pixel check and the server has API credentials, a copy of the image is sent to Sightengine’s API for that request only and is not stored by Roy's Tools.

What is C2PA / Content Credentials?

C2PA is a tamper-evident provenance standard. When present and valid, it records who signed the file, whether it was generated or captured, and whether the pixels still match the signature. Re-saving, cropping in some apps, or taking a screenshot usually removes it.

Can I remove a SynthID or other AI watermark here?

If analysis reads the file as AI-marked, a Remove invisible watermark button runs locally: geometric disruption, residual-peak attenuation, resample, and JPEG re-encode. The detector then runs again on the new file. This targets pixel-space spread-spectrum marks and strips C2PA/EXIF. It cannot guarantee a vendor’s private decoder will fail, and it does not make an AI image into a photograph.

Do I need a Sightengine API key?

Not for C2PA, EXIF, or the local watermark scan/strip. Pixel scoring uses SIGHTENGINE_API_USER and SIGHTENGINE_API_SECRET on the server (for example Railway). The free Sightengine plan is quota-capped. If those variables are unset, the tool still works locally and labels the pixel panel as unavailable.

Why did a known AI image show no credentials?

Many generators never embed C2PA, and platforms strip metadata. Use the original download from the generator when you can. A screenshot of ChatGPT or Midjourney is usually unsigned and harder for both provenance and pixel models.

Can EXIF prove a photo is real?

No. Camera make, model, and GPS are useful context but are trivial to edit. This viewer reports what the file contains, not whether those tags are truthful.