Downloads · 30 days
0
contrastive-u-dae
nightknocker/contrastive-u-dae
contrastive-u-dae is a image feature extraction model from nightknocker. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
The ViT-B model was replaced by another Encoder.
Access
Public
Updated Oct 13, 2025
Parameters
81.6M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors326 MB · 100%
At a glance
- Task
- Image Feature Extraction
- License
- apache-2.0
- Access
- Public
- Created
- Oct 13, 2025
- Updated
- Oct 13, 2025
- SHA
- 82143b8e
Model card
From the Hugging Face model README
Contrastive Booru-Image Embedding Model
The ViT-B model was replaced by another Encoder.
The images were tagged by the 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 4000 female characters extracted from public and private datasets.
- Task
- Image Feature Extraction
- License
- apache-2.0
- Created
- Oct 13, 2025
- Updated
- Oct 13, 2025