nightknocker's picture
Update README.md
67f768f verified
|
raw
history blame
737 Bytes
metadata
license: apache-2.0
new_version: nightknocker/contrastive-u-dae

Contrastive Booru-Image Embedding Model

The model was trained on masked pixiv images, tagged by CL tagger. The caption (prompt) was tokenized by ModernBERT.

Objectives

Image-Caption Similarity Scoring: The model assigns a score to each image based on how closely it is related to its associated caption.

Image Labeling: The image embedding is used to label images by character name.

Updates

This version contains up to 4200 characters extracted from public and private datasets.