Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- ILSVRC/imagenet-1k
|
| 5 |
+
tags:
|
| 6 |
+
- diffusion
|
| 7 |
+
- mamba-transformer
|
| 8 |
+
- class2image
|
| 9 |
+
- imagenet1k-256
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<div align="center">
|
| 13 |
+
<h1>Official PyTorch models of "DiMSUM: Diffusion Mamba - A Scalable and Unified
|
| 14 |
+
Spatial-Frequency Method for Image Generation" <a href="https://arxiv.org/abs/2411.04168"> (NeurIPS'24)</a></h1>
|
| 15 |
+
</div>
|
| 16 |
+
|
| 17 |
+
<div align="center">
|
| 18 |
+
<a href="https://hao-pt.github.io/" target="_blank">Hao Phung</a><sup>*13†</sup>   <b>·</b>  
|
| 19 |
+
<a href="https://quandao10.github.io/" target="_blank">Quan Dao</a><sup>*12†</sup>   <b>·</b>  
|
| 20 |
+
<a href="https://termanteus.com/" target="_blank">Trung Dao</a><sup>1</sup>
|
| 21 |
+
<br> <br>
|
| 22 |
+
<a href="https://viethoang1512.github.io/" target="_blank">Hoang Phan</a><sup>4</sup>   <b>·</b>  
|
| 23 |
+
<a href="https://people.cs.rutgers.edu/~dnm/" target="_blank"> Dimitris N. Metaxas</a><sup>2</sup>   <b>·</b>  
|
| 24 |
+
<a href="https://sites.google.com/site/anhttranusc/" target="_blank">Anh Tran</a><sup>1</sup>
|
| 25 |
+
<br> <br>
|
| 26 |
+
<sup>1</sup>VinAI Research  
|
| 27 |
+
<sup>2</sup>Rutgers University  
|
| 28 |
+
<sup>3</sup>Cornell University  
|
| 29 |
+
<sup>4</sup>New York University
|
| 30 |
+
<br> <br>
|
| 31 |
+
<a href="https://vinairesearch.github.io/DiMSUM/">[Page]</a>   
|
| 32 |
+
<a href="https://arxiv.org/abs/2411.04168">[Paper]</a>   
|
| 33 |
+
<br> <br>
|
| 34 |
+
<emp><sup>*</sup>Equal contribution</emp>  
|
| 35 |
+
<emp><sup>†</sup>Work done while at VinAI Research</emp>
|
| 36 |
+
</div>
|
| 37 |
+
|
| 38 |
+
Our codebase is hosted at https://github.com/VinAIResearch/DiMSUM.git. Please refer to [sample.py]()
|
| 39 |
+
|
| 40 |
+
To use DiMSUM pre trained model:
|
| 41 |
+
```python
|
| 42 |
+
from dimsum.model_dims import DiM
|
| 43 |
+
|
| 44 |
+
model = DiM.from_pretrained("haopt/dimsum-L2-imagenet256")
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
**Please CITE** our paper and give us a :star: whenever this repository is used to help produce published results or incorporated into other software.
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@inproceedings{phung2024dimsum,
|
| 51 |
+
title={DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation},
|
| 52 |
+
author={Phung, Hao and Dao, Quan and Dao, Trung and Phan, Hoang and Metaxas, Dimitris and Tran, Anh},
|
| 53 |
+
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
|
| 54 |
+
year= {2024},
|
| 55 |
+
}
|
| 56 |
+
```
|