metadata
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.
- Project Page: https://rae-dit.github.io/scale-rae/
- GitHub Repository: 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.
The implementation supports GPU inference and TPU training. To generate images with pre-trained models:
python cli.py t2i --prompt "Can you generate a photo of a cat on a windowsill?"
Citation
@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}
}