LFM2.5-VL-3B Demo: Auto-Maps Skin Regions and Measures

pcuenq · x · 2026-08-19

Demonstrates Liquid AI's LFM2.5-VL-3B model on a visual task: given a generated skin-like image, it mapped 6 regions, drew contours, and measured the L04 area (8.8 x 8.1 mm) before prioritizing what to review first. Ran locally on a Mac Studio.

Original post →

More from Multimodal

Multimodal channel →