siglip2_decoder / README.md
nielsr's picture
nielsr HF Staff
Add model card and metadata
ebaffa9 verified
|
raw
history blame
1.7 kB
---
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).
The implementation supports GPU inference and TPU training. To generate images with pre-trained models:
```bash
python cli.py t2i --prompt "Can you generate a photo of a cat on a windowsill?"
```
## 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}
}
```