hugpadhugpad

cyberagent / ldm-vq-f16-rgba

Vision70M1000Updated Oct 13, 2025
Hugging Face

Downloads

100

Likes

0

Last updated

Oct 13, 2025

License

apache-2.0

This repository provides a specialized image tokenizer (VQ model) for RGBA images. The model can effectively compress RGBA images into discrete latent codes, which can be used for various downstream tasks such as graphic design completion, as demonstrated in our paper Multimod…

Tasks & library

  • image feature extraction
  • transformers

Tags

  • transformers
  • vqmodel
  • feature-extraction
  • image tokenizer
  • vq model
  • rgba images

Technical specifications

Parameters70M
Librarytransformers
Languagesen
Licenseapache-2.0