Thread

Show HN: AI search for every photo and every frame of video on macOS

151 points · 68 comments · allenleee

yt1998 · 1791122362 · focus · HN ↗
Why chose CLIP to do this. Have you tried small VLMs like Qwen-VL? I believe those models have video encoders can better perform at this scenario.
1. allenleee · 1791133716 · focus · HN ↗
  [dead]

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.