See what they'll see first.
A saliency model trained on real human eye-tracking. Predicts where attention lands on any design — in seconds, before you ship.
A model that learned to look like us.
Focal is a convolutional saliency network trained on SALICON — tens of thousands of images annotated with where real people actually looked. It reproduces the same attention an eye-tracker would record, in the time it takes to switch tabs.
Trained on real gaze
SALICON pairs images with human fixation maps. The model learns the patterns the eye obeys — contrast, faces, text, edges, center bias.
Built for design speed
A single forward pass produces a full saliency field. Fast enough to scan, adjust, and scan again — without losing your design flow.
Processed and forgotten
Your design is analysed in memory and discarded. Nothing is stored, logged, or used to train future models. Confidential work stays confidential.
What draws the eye
The hotspots that win the first fixations — ranked, scored, located to the pixel.
What gets missed
The cold zones nobody reaches — the CTA below the fold, the price, the disclaimer you were sure they'd read.
How hierarchy holds
The order the eye actually travels versus the order you intended — your hierarchy, graded against reality.
Focal lives inside Figma.
Scan any frame without leaving the canvas. The heatmap overlays in place — fix hierarchy while you design, not after you ship.
Install the plugin