Improve model card: Add pipeline tag, license and link to project page
#1
by
nielsr
HF staff
- opened
README.md
CHANGED
|
@@ -1,10 +1,15 @@
|
|
| 1 |
---
|
| 2 |
library_name: diffusers
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
| 4 |
## EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
|
| 5 |
|
| 6 |
**EQ-VAE** regularizes the latent space of pretrained autoencoders by enforcing equivariance under scaling and rotation transformations.
|
| 7 |
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
#### Model Description
|
| 10 |
This model is a regularized version of [SD-VAE](https://github.com/CompVis/latent-diffusion). We finetune it with EQ-VAE regularization for 5 epochs on OpenImages.
|
|
@@ -27,4 +32,4 @@ Reconstruction performance of eq-vae-ema on Imagenet Validation Set.
|
|
| 27 |
| **PSNR** | 25.95 |
|
| 28 |
| **LPIPS** | 0.141 |
|
| 29 |
| **SSIM** | 0.72 |
|
| 30 |
-
---
|
|
|
|
| 1 |
---
|
| 2 |
library_name: diffusers
|
| 3 |
+
pipeline_tag: image-to-image
|
| 4 |
+
license: mit
|
| 5 |
---
|
| 6 |
+
|
| 7 |
## EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
|
| 8 |
|
| 9 |
**EQ-VAE** regularizes the latent space of pretrained autoencoders by enforcing equivariance under scaling and rotation transformations.
|
| 10 |
|
| 11 |
+
Project page: https://eq-vae.github.io/.
|
| 12 |
+
|
| 13 |
---
|
| 14 |
#### Model Description
|
| 15 |
This model is a regularized version of [SD-VAE](https://github.com/CompVis/latent-diffusion). We finetune it with EQ-VAE regularization for 5 epochs on OpenImages.
|
|
|
|
| 32 |
| **PSNR** | 25.95 |
|
| 33 |
| **LPIPS** | 0.141 |
|
| 34 |
| **SSIM** | 0.72 |
|
| 35 |
+
---
|