Lumethic
Check If a Photo Is AI-Generated
Upload an image and we read its Content Credentials, the signed record that tools like DALL·E, Adobe Firefly and licensed Midjourney workflows attach to generated images. The check is free, runs in your browser, and your file is not uploaded anywhere.
Drag & drop a photo here, or click to select
JPEG, PNG, WebP, AVIF, HEIC, TIFF, SVG, DNG and ARW are supported
Choose a photoYour photo is analyzed entirely in your browser, it is never uploaded.
No signed photo to hand? Try an example
Inspect a prepared image to see what the report looks like.
What this checker can and cannot tell you
What it can tell you
- Whether the image carries C2PA Content Credentials, and if so, which tool created or edited it, including recorded AI generation.
- Whether the credentials are intact or the file was modified after signing.
- Which camera or software produced the credential, when, and what edits were recorded.
What no tool can tell you
If an image has no credentials, no tool can prove whether it is real or AI-generated. Pixel-based AI detectors guess from statistical patterns. They regularly flag real photos as AI and let AI images pass as real.
This is not a limitation of this particular checker, it is the current state of the art. Detection accuracy drops with every new model generation, while a cryptographic record stays verifiable.
Read why AI detectors produce false positivesDo you need to show that your own photo is real?
Photographers who are asked for evidence, for example by a contest, a client or an editor, do not need a detector. Verify your camera's RAW file against the exported JPEG and you get a verification report you can share.
How the check works
Drop in an image
JPEG, PNG, WebP or AVIF. The file is analyzed locally in your browser with the open-source C2PA SDK. It never leaves your device.
We read the credentials
The checker parses the C2PA manifest: who created the image, with what tool, whether AI generation was recorded, and whether the signature still matches the pixels.
You see the result
You see what the image's provenance record says, and a clear note when there is no record to read. There is no probability score.
Why this checker does not guess
Most AI image detectors run a classifier over the pixels and output a confidence score. Independent tests show that these classifiers err in both directions: heavily edited or scanned real photos get flagged as AI, while images from current generators often pass. A wrong answer with a confident percentage attached is worse than no answer.
The C2PA standard works the other way around. It records provenance when the image is created and protects the record cryptographically. The large AI generators now attach Content Credentials to their output, and several camera makers sign images in hardware. Reading that record yields facts rather than estimates. See which cameras support C2PA Content Credentials
Provenance instead of detection
Detection tries to judge from the pixels whether an image looks generated, and that judgement gets harder with every model generation. Provenance asks whether there is a verifiable record of where the image came from, which can be answered definitively. The transparency rules of the EU AI Act and the policies of the large photo contests rely on provenance for the same reason.
Provenance vs. AI detection, explained in depthFrequently asked questions
This checker reads C2PA Content Credentials. The absence of credentials does not mean an image is AI-generated, and their presence reflects what the signing tool recorded. The analysis runs entirely in your browser.