Commit
•
2ed0c0d
1
Parent(s):
db276de
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ license: creativeml-openrail-m
|
|
| 6 |
|
| 7 |
Each model was trained on a notable Japanese AI artist's works using dreambooth, with 30 of their works gained mainly from twitter (except for aibanousagi, which I could find only 23).
|
| 8 |
|
| 9 |
-
It tooks 1000 steps to train each model, at a learning rate of 5-e6.
|
| 10 |
|
| 11 |
Some are good at backgrounds, while others can generate a semi-realistic style as seen in many SD 1.5 anime/waifu models (and some might be a bit overfitted).
|
| 12 |
|
|
|
|
| 6 |
|
| 7 |
Each model was trained on a notable Japanese AI artist's works using dreambooth, with 30 of their works gained mainly from twitter (except for aibanousagi, which I could find only 23).
|
| 8 |
|
| 9 |
+
It tooks 1000 steps to train each model, at a learning rate of 5-e6. I have shared the notebook [here](https://huggingface.co/Phantom-Artist/phantom-diffusion/blob/main/DreamBooth_Stable_Diffusion_works_with_SD_2.ipynb) in case you want to try out additional training.
|
| 10 |
|
| 11 |
Some are good at backgrounds, while others can generate a semi-realistic style as seen in many SD 1.5 anime/waifu models (and some might be a bit overfitted).
|
| 12 |
|