Update README.md
Browse files
README.md
CHANGED
|
@@ -48,6 +48,8 @@ Spatial-Frequency Method for Image Generation" <a href="https://arxiv.org/abs/24
|
|
| 48 |
<emp><sup>†</sup>Work done while at VinAI Research</emp>
|
| 49 |
</div>
|
| 50 |
|
|
|
|
|
|
|
| 51 |
Our codebase is hosted at https://github.com/VinAIResearch/DiMSUM.git.
|
| 52 |
|
| 53 |
To use DiMSUM pre trained model:
|
|
|
|
| 48 |
<emp><sup>†</sup>Work done while at VinAI Research</emp>
|
| 49 |
</div>
|
| 50 |
|
| 51 |
+
## Model details
|
| 52 |
+
Our model is a hydrid Mamba-Transformer architecture for class-to-image generation. This method is trained with flow matching objective. The model has 460M parameters and achieves an FID score of 2.11 on ImageNet-1K 256 dataset.
|
| 53 |
Our codebase is hosted at https://github.com/VinAIResearch/DiMSUM.git.
|
| 54 |
|
| 55 |
To use DiMSUM pre trained model:
|