---
license: mit
library_name: transformers
pipeline_tag: image-to-image
---

# Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders (Scale-RAE)

This repository contains artifacts related to the paper [Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders](https://huggingface.co/papers/2601.16208).

- **Project Page:** [https://rae-dit.github.io/scale-rae/](https://rae-dit.github.io/scale-rae/)
- **GitHub Repository:** [https://github.com/ZitengWangNYU/Scale-RAE](https://github.com/ZitengWangNYU/Scale-RAE)

## Introduction
Representation Autoencoders (RAEs) provide a simplified and powerful alternative to VAEs for large-scale text-to-image generation. Scale-RAE demonstrates that training diffusion models in high-dimensional semantic latent spaces (using encoders like SigLIP-2) leads to faster convergence, better generation quality, and improved stability compared to state-of-the-art VAE-based foundations.

## Usage
For detailed instructions on installation, training, and inference, please visit the [official GitHub repository](https://github.com/ZitengWangNYU/Scale-RAE).

**This decoder is also directly compatitable with original RAE [codebase](https://github.com/bytetriper/RAE).** Try it out by simply swapping the encoder with google/siglip2-so400m-patch14-224!

## Citation
```bibtex
@article{scale-rae-2026,
  title={Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders},
  author={Shengbang Tong and Boyang Zheng and Ziteng Wang and Bingda Tang and Nanye Ma and Ellis Brown and Jihan Yang and Rob Fergus and Yann LeCun and Saining Xie},
  journal={arXiv preprint arXiv:2601.16208},
  year={2026}
}
```