I fine-tuned EVA-02 in a week to build a neural video retrieval engine for what CLIP still won't do [P]

A developer open-sourced a local video retrieval engine built on a fine-tuned EVA-02 model after a 7-day sprint, designed to search large unstructured video portals by visual poses, clothing details, camera angles and motion cadence while ignoring uploader metadata at search time and running in minimal VRAM. The project targets queries the developer says CLIP still handles poorly.

TL;DR: After a manic 7-day sprint, I open-sourced a local video retrieval engine built to search massive unstructured video portals by visual poses, clothing details, camera angles, and motion cadence—ignoring uploader metadata at search time and running in minimal VRAM. GitHub: https://github.com/q