Update README.md
Browse files
README.md
CHANGED
|
@@ -18,3 +18,7 @@ The training for v0.3 was done on a single RTX 3080 10GB GPU using the original
|
|
| 18 |
The only modification to the code was a custom dataloader, a few fixes for torch2/xformers and a custom function that made sure the encoder weights were static (to ensure model compatibility).
|
| 19 |
|
| 20 |
Training took ~20+ hours and was done on two separate datasets. 100 epochs on a filtered subset of the [Wikimedia Foundation Image Dump (November 2005)](https://archive.org/details/wikimedia-image-dump-2005-11) and an extra 200 epochs on the Flickr2K dataset using `transforms.FiveCrop`.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
The only modification to the code was a custom dataloader, a few fixes for torch2/xformers and a custom function that made sure the encoder weights were static (to ensure model compatibility).
|
| 19 |
|
| 20 |
Training took ~20+ hours and was done on two separate datasets. 100 epochs on a filtered subset of the [Wikimedia Foundation Image Dump (November 2005)](https://archive.org/details/wikimedia-image-dump-2005-11) and an extra 200 epochs on the Flickr2K dataset using `transforms.FiveCrop`.
|
| 21 |
+
|
| 22 |
+
(I have two VAE Encode/Upscale Latent nodes in the image below, but the encoder for both is the same so it would be the same even if you used v0.9 as the input on both, I just reused the workflow from the v1.5 test.)
|
| 23 |
+
|
| 24 |
+
|