TA-Tok / README.md
nielsr's picture
nielsr HF Staff
Add model card
5306244 verified
|
raw
history blame
294 Bytes
---
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](https://huggingface.co/papers/2506.18898).
Project page: https://tar.csuhan.com