Update README.md

README.md

@@ -23,7 +23,23 @@ This model was trained for 7 epochs on ImageNet, with training parameters follow
 
 $$\mathcal{L}_{\mathrm{VAE}} = \mathcal{L}_1 + \mathcal{L}_{\mathrm{LPIPS}} + 0.5\mathcal{L}_{\mathrm{GAN}} + 0.2\mathcal{L}_{\mathrm{ID}} + 0.000001\mathcal{L}_{\mathrm{KL}}$$
 
-## Evaluation 
+## Evaluation
+
+ImageNet 2012 (256x256, val, 50000 images)
+
+| Model           | rFID  | PSNR   | SSIM  | LPIPS |
+|-----------------|-------|--------|-------|-------|
+| Transfusion-VAE | 0.408 | 28.723 | 0.845 | 0.081 |
+| SD-VAE          | 0.692 | 26.910 | 0.772 | 0.130 |
+
+COCO 2017 (256x256, val, 5000 images)
+
+| Model           | rFID  | PSNR   | SSIM  | LPIPS |
+|-----------------|-------|--------|-------|-------|
+| Transfusion-VAE | 2.749 | 28.556 | 0.855 | 0.078 |
+| SD-VAE          | 4.246 | 26.622 | 0.784 | 0.127 |
+
+## Evaluation (legacy)
 
 ImageNet 2012 (256x256, val, 50000 images)
 
@@ -34,6 +50,6 @@ ImageNet 2012 (256x256, val, 50000 images)
 
 Paper: [Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model](https://arxiv.org/abs/2408.11039)
 
-Dataset: [ImageNet](https://image-net.org/)
+Dataset: [ImageNet](https://image-net.org/), [COCO](https://cocodataset.org/), [FFHQ](https://github.com/NVlabs/ffhq-dataset)
 
 Base Code: [lavinal712/AutoencoderKL](https://github.com/lavinal712/AutoencoderKL)