Add model card for SANA 1.5

This PR adds a model card, ensuring the model can be found at https://huggingface.co/models?pipeline_tag=text-to-image.
It also adds a link to https://huggingface.co/papers/2501.18427, as well as to the Github repo.

README.md

@@ -1,7 +1,15 @@
+---
+pipeline_tag: text-to-image
+---
+
 # Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
 
 [[paper](https://arxiv.org/abs/2410.10733)] [[GitHub](https://github.com/mit-han-lab/efficientvit)]
 
+This repository contains the model of the paper [SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer](https://huggingface.co/papers/2501.18427).
+
+Project page: https://hanlab.mit.edu/projects/sana/
+
 ![demo](assets/dc_ae_demo.gif)
 <p align="center">
 <b> Figure 1: We address the reconstruction accuracy drop of high spatial-compression autoencoders.
@@ -111,3 +119,17 @@ If DC-AE is useful or relevant to your research, please kindly recognize our con
   year={2024}
 }
 ```
+
+The work on SANA 1.5 can be cited as follows:
+
+```
+@misc{xie2025sana,
+      title={SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer},
+      author={Enze Xie and Junyu Chen and Han Cai and Junsong Chen and Haotian Tang and Yao Lu and Song Han},
+      year={2025},
+      eprint={2501.18427},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2501.18427},
+}
+```