AI Image Detector
Drop an image to check whether it was generated by ChatGPT, DALL·E, Midjourney, Stable Diffusion, or Adobe Firefly. Runs entirely in your browser.
Your file stays on your device. Detection signals (C2PA, metadata, NPR model) all run in your browser.
How the AI detector decides
Most AI image detectors are guessing games. MediaSens stacks three independent signals so the verdict has something concrete to stand on:
- C2PA Content Credentials. If the generator signed the file (OpenAI, Adobe Firefly, cameras with verified-source modes), the signature names the producer cryptographically. This is the strongest possible signal.
- Embedded generator metadata. Many AI tools leave traces in PNG text chunks, XMP packets, or IPTC fields — “Software: ChatGPT”, “Made by OpenAI”, Stable Diffusion parameter strings, Automatic1111 prompts. MediaSens scans all of these.
- NPR neural detector (CVPR 2024). When metadata has been stripped, a self-hosted ONNX model analyzes noise patterns and frequency signatures to estimate AI-generation probability.
The summary explains which signals fired and weights them honestly. If only the visual model has anything to say, you'll see that called out — not dressed up as certainty.
What the detector can and can't do
Reliable when: the image still has its original metadata, or it came directly from a generator that signs C2PA credentials.
Less reliable when: the file has been screenshotted, re-saved, heavily compressed, or run through filters — all of which strip metadata and distort the visual signal. Treat the NPR score alone as a hint, not proof.
Other things you can check at the same time
- C2PA checker — verify Content Credentials and signing chain in detail
- EXIF viewer — see camera, GPS, timestamps, and software fields
- All MediaSens tools — the full analyzer with reverse image search
Frequently asked questions
- How does the AI image detector work?
- MediaSens combines several signals: C2PA Content Credentials (if the generator signed the file), embedded metadata in PNG text chunks and XMP/IPTC fields that many AI tools quietly leave behind, and an ONNX-based detector (NPR, CVPR 2024) that looks at noise and frequency patterns. The verdict explains which signals fired.
- Is the AI detector free?
- Yes. The detector itself runs in your browser and has no per-image cost. A free account adds plain-language AI summaries (4/month); paid plans remove that cap.
- Do you upload my image?
- No. C2PA verification, EXIF/XMP extraction, and the NPR detector all run client-side in your browser. The file never leaves your device. (The optional AI summary uses extracted text metadata only, not the image bytes.)
- Can it detect ChatGPT / DALL·E / Midjourney / Stable Diffusion images?
- Often, yes. ChatGPT and DALL·E images carry C2PA credentials and 'Made by OpenAI' XMP tags. Midjourney and Stable Diffusion frequently leave generator hints in PNG text chunks. When metadata is stripped, the NPR model gives a probability score based on visual signal patterns.
- What about screenshots of AI images?
- Screenshots usually lose the original metadata, so the verdict will lean on the NPR model alone. Accuracy drops without metadata — treat the score as a hint, not proof.
- Why do two images of the same scene give different results?
- Compression, re-encoding, cropping, and screenshotting all alter the signal patterns the detector relies on. The presence of C2PA or generator metadata is much more reliable than the visual heuristic alone.