immich-team's picture
Create README.md
3ec6422
|
raw
history blame
469 Bytes
metadata
tags:
  - immich
  - clip
  - multilingual

Model Description

This repo contains ONNX exports for the multilingual CLIP model M-CLIP/XLM-Roberta-Large-Vit-B-16Plus. It separates the visual and textual encoders into separate models for the purpose of generating image and text embeddings.

This repo is specifically intended for use with Immich, a self-hosted photo library.