Skip to content
Bluzen Labs
character-embed
All models

bluzen/character-embed

Open
Image Feature Extraction150M paramsPyTorch11k128Updated 14 July 2026

character-embed

Character-identity embedding space for retrieval and dedup across illustration corpora.

This card is generated from the entry's metadata in src/data/hub.js. Write a card field on the entry to replace it with a real one.

How to use it

from transformers import pipeline

pipe = pipeline("image-feature-extraction", model="bluzen/character-embed")

Details

TaskImage Feature Extraction
Size150M params
LibraryPyTorch
LicenceApache-2.0

Limitations

Every model the lab publishes carries the biases of the corpus it came from, and ours is illustration-heavy. Measure before you trust it.