Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ vae = AutoencoderKL.from_pretrained("lavinal712/transfusion-vae")
|
|
| 19 |
|
| 20 |
## Model
|
| 21 |
|
| 22 |
-
This model was trained for 7 epochs on ImageNet, with training parameters following the original Transfusion paper.
|
| 23 |
|
| 24 |
$$\mathcal{L}_{\mathrm{VAE}} = \mathcal{L}_1 + \mathcal{L}_{\mathrm{LPIPS}} + 0.5\mathcal{L}_{\mathrm{GAN}} + 0.2\mathcal{L}_{\mathrm{ID}} + 0.000001\mathcal{L}_{\mathrm{KL}}$$
|
| 25 |
|
|
|
|
| 19 |
|
| 20 |
## Model
|
| 21 |
|
| 22 |
+
This model was trained for 50 (legacy: 7) epochs on ImageNet, COCO and FFHQ (legacy: ImageNet), with training parameters following the original Transfusion paper.
|
| 23 |
|
| 24 |
$$\mathcal{L}_{\mathrm{VAE}} = \mathcal{L}_1 + \mathcal{L}_{\mathrm{LPIPS}} + 0.5\mathcal{L}_{\mathrm{GAN}} + 0.2\mathcal{L}_{\mathrm{ID}} + 0.000001\mathcal{L}_{\mathrm{KL}}$$
|
| 25 |
|