Production lane
The current image lane is aidetect-v16-image-384-v1+owenslab+siglip-probe-routed-v11+dualview-orig-v1. It returns warning signals, never proof or authenticity claims.
AI image detector
Inspect images.
Keep the context.
Submit a JPEG or PNG and review a warning label, raw score, active model and processing source. The result does not prove who created the image.
Open the free checkerScope before score.
Every result is a warning signal. The evidence and limitations below define what this route can and cannot support.
Input boundary
The public checker accepts JPEG or PNG up to 4 MB and 25 million decoded pixels.
Evidence level
78.1% of 653 AI images from acceptance-v4, scored through the deployed pipeline drew a strong warning. This is a bounded, source-asserted slice, not an overall accuracy claim and not independent validation.
Do not infer more than the lane measured.
- Art, screenshots, compression and unseen generators can fail.
- A low score does not establish that an image is human-made or authentic.
- Model and training-data rights remain a commercial diligence item.