One photograph, placed in a measured reference population of 91,810 posts. The instrument reports where it falls and how much its own ensemble disagrees.
Drop a photo here, or choose one. One person, facing the camera.
Nothing is stored. The image is decoded, scored and discarded; no copy is written to disk and no account is involved.
The live scorer runs on request, on a single machine, and is not running right now. The recording below shows the same path a live upload takes.
Ensemble spread —. This is the range across the three fold checkpoints and the horizontal-flip pair — the disagreement among the models that produced the number, not a confidence interval in the inferential sense.
Predicted engagement for this image posted solo, as the thumbnail, by a standardized account, under this population's revealed preferences — with page reach, follower count, posting history, carousel position and source compression held fixed.
Holding those fixed is the point. Without it, a score mostly measures how many followers an account has. The reference context pins every one of them to the same value for every image, so what varies between two scores is the photograph.
The ensemble band is typically wide — a median of 39 percentile points between the lowest and highest member, measured over 200 held-out images. The band is shown at the same weight as the estimate because it is the same size as the estimate: on most images the honest reading is a third of the scale, not a point.