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.
More from Multimodal
- Happy Shrimp launches AI tool to turn one line into a full song — jordiponsdotme · 2026-08-19
- Claude Skill plus Kie generates marketing videos for ~$0.75 each, replacing subscriptions — SimplyAnnisa · 2026-08-19
- AI Generates Breaking Bad in Paper Cut Style Without Keyframes — techhalla · 2026-08-19
- Open-source SRT whiteboard animation skill: hook it to Codex and ship 100 videos a day — huangyun_122 · 2026-08-19
- Image Edit Arena: gpt-image-2 tops 29M-vote leaderboard, nano-banana-pro ranks 8th — arena · 2026-08-19
- Comfy MCP goes local and open-source, letting agents drive your actual ComfyUI install — PurzBeats · 2026-08-19