Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model:
|
| 4 |
+
- ostris/vae-kl-f8-d16
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
Another take on upscaler using AsymmetricAutoencoderKL, in this case I did re-use decoder of ostris/vae-kl-f8-d16 as decoder and trained just encoder.
|
| 8 |
+
|
| 9 |
+
Oversharpening was reduced by usage of sobel in loss calculation. I guess that without high resolution image used as reference, it might look more blury than previous one.
|