Update README.md
Browse files
README.md
CHANGED
|
@@ -48,8 +48,9 @@ for idx, im in enumerate(images):
|
|
| 48 |
|
| 49 |
## Model description
|
| 50 |
|
| 51 |
-
Base model is Stable Diffusion v1.5 and was trained
|
| 52 |
The model is learning to associate Avatar images with the style tokenized as 'avatarart style'.
|
| 53 |
Prior preservation was used during training using the class 'Person' to avoid training bleeding into the representations for that class.
|
| 54 |
Training ran on 2xA6000 GPUs on [Lambda GPU Cloud](https://lambdalabs.com/service/gpu-cloud) for 700 steps, batch size 4 (a couple hours, at a cost of about $4).
|
| 55 |
|
|
|
|
|
|
| 48 |
|
| 49 |
## Model description
|
| 50 |
|
| 51 |
+
Base model is Stable Diffusion v1.5 and was trained using Dreambooth with 60 input images sized 512x512 displaying Avatar character images.
|
| 52 |
The model is learning to associate Avatar images with the style tokenized as 'avatarart style'.
|
| 53 |
Prior preservation was used during training using the class 'Person' to avoid training bleeding into the representations for that class.
|
| 54 |
Training ran on 2xA6000 GPUs on [Lambda GPU Cloud](https://lambdalabs.com/service/gpu-cloud) for 700 steps, batch size 4 (a couple hours, at a cost of about $4).
|
| 55 |
|
| 56 |
+
Author: Eole Cervenka
|