CLIP-powered image search: 25,000 images in under 50ms, running locally in your browser
jason_mayes · x · 2026-09-22
xenovacom demos a fast image search built not on the newest multimodal model, but CLIP — a zero-shot multimodal classifier released nearly 6 years ago:
- 25,000 images searched in under 50ms, with no image labeling required.
- Runs locally in the browser on WebGPU via Transformers.js, with a live demo to try.
A nice reminder that classic models still crush lightweight local semantic image retrieval.
More from Multimodal
- MiniMax H3 Turns a Mac Desktop Into Oggy-Style Cartoon Chaos — Full Prompt Included — SimplyAnnisa · 2026-09-22
- Striking human-motion visualizations made with Sentinel — Kyrannio · 2026-09-22
- New Pika impresses early users as the video startup returns to form — Kyrannio · 2026-09-22
- Tencent's Hunyuan Image 3.5 lands on OnSolo: 5 refs, 2K output, 1 credit — Div_pradeep · 2026-09-22
- Museum statue meme generated with AI — prompt included — umesh_ai · 2026-09-22
- Princeton's VideoGen-Agent Adds 19 Points via Agentic RL Tool Use for Video — princetonu · 2026-09-22