Update README.md
Browse files
README.md
CHANGED
@@ -28,7 +28,7 @@ if len(stable_inversion)>1:
|
|
28 |
|
29 |
it was trained on 1024 images matching the 'genshin_impact' tag on safebooru, epochs 1 and 2 had the model being fed the full captions, epoch 3 had 50% of the tags in the caption, and epoch 4 had 25% of the tags in the caption. Learning rate was 1e-3 and the loss curve looked like this ![](https://pbs.twimg.com/media/FdsdivkWIBQYmZd?format=jpg&name=small)
|
30 |
|
31 |
-
Samples from this finetuned inversion for the prompt "beidou_(genshin_impact)"
|
32 |
![](https://pbs.twimg.com/media/FdsdL7YWIBEXoqG?format=png&name=small)
|
33 |
![](https://pbs.twimg.com/media/FdsdSUdWICIBarc?format=png&name=small)
|
34 |
![](https://pbs.twimg.com/media/Fdsdte5WIAAUALp?format=png&name=small)
|
|
|
28 |
|
29 |
it was trained on 1024 images matching the 'genshin_impact' tag on safebooru, epochs 1 and 2 had the model being fed the full captions, epoch 3 had 50% of the tags in the caption, and epoch 4 had 25% of the tags in the caption. Learning rate was 1e-3 and the loss curve looked like this ![](https://pbs.twimg.com/media/FdsdivkWIBQYmZd?format=jpg&name=small)
|
30 |
|
31 |
+
Samples from this finetuned inversion for the prompt "beidou_(genshin_impact)" using just the 1-4 Stable Diffusion model
|
32 |
![](https://pbs.twimg.com/media/FdsdL7YWIBEXoqG?format=png&name=small)
|
33 |
![](https://pbs.twimg.com/media/FdsdSUdWICIBarc?format=png&name=small)
|
34 |
![](https://pbs.twimg.com/media/Fdsdte5WIAAUALp?format=png&name=small)
|