Is this video AI-generated?
Drop an mp4, webm, mov, or m4v. We sample 12 evenly-spaced frames in your browser and compute noise consistency, lighting plausibility, and frame-to-frame motion. Plus ELA + noise residual on a key reference frame. Nothing is uploaded.
MVP detector. Optical flow, face-landmark drift, and lip-sync analysis land next.
Frames first, then time
Each frame is its own little image-detection problem. We run noise residual on every sampled frame and ELA on the key frame — then compare across time to catch what a single still misses.
Motion is the hardest fake
Generators have to keep style, lighting, and identity stable across thousands of frames. They often slip. The motion plot shows where.
Want to learn more?
Read How AI Video Forensics Work for the full method walkthrough.