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.
Related event: 3B Vision Model Runs Locally to Map Skin Regions and Measure Lesions(3 posts)→
More from Multimodal
- ImageNet should retire: DiT method rankings negatively correlate between ImageNet and text-to-image — YouJiacheng · 2026-10-16
- Open-source anatomy-reveal skill turns Claude into an exploded-view motion design studio — msharmas · 2026-10-16
- Flux 3 Klein vs Flux 2 Klein hands-on: the new base model 'barely usable' for T2I — Both-Rub5248 · 2026-10-16
- USTC paper uses speculative sampling to cut latency in interactive video generation — ustc · 2026-10-16
- 800,000 Gaussian splats run in WebGPU; Casado sees near-infinite scaling — generativist · 2026-10-16
- Nano Banana 2.1 image generation now live in Perplexity Computer for all users — ChrisUniverse · 2026-10-16