A newer version of this model is available:
nightknocker/contrastive-u-dae
Contrastive Booru-Image Embedding Model
The model was trained on 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 color and character name.
Updates
The 1.2 and 1.3 versions focused on the heads, clothes, and colors of the most common anime characters.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support