TA-Tok / README.md
nielsr's picture
nielsr HF Staff
Add model card
5306244 verified
|
raw
history blame
294 Bytes
metadata
pipeline_tag: image-to-image
library_name: transformers

This repository contains the model described in Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations.

Project page: https://tar.csuhan.com