Downloads · 30 days
0
contrastive-pixiv-embedding
nightknocker/contrastive-pixiv-embedding
contrastive-pixiv-embedding 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 model was trained on pixiv images, tagged by CL tagger. The caption (prompt) was tokenized by ModernBERT.
Access
Public
Updated Oct 7, 2025
Parameters
161M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors642 MB · 100%
At a glance
- Task
- Image Feature Extraction
- License
- apache-2.0
- Access
- Public
- Created
- Oct 1, 2025
- Updated
- Oct 7, 2025
- SHA
- 5df3cedc
Model card
From the Hugging Face model README
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.
- Task
- Image Feature Extraction
- License
- apache-2.0
- Created
- Oct 1, 2025
- Updated
- Oct 7, 2025