Update README.md
Browse files
README.md
CHANGED
@@ -2,27 +2,26 @@
|
|
2 |
license: creativeml-openrail-m
|
3 |
---
|
4 |
|
5 |
-
Prompt with "sarasa"
|
6 |
|
7 |
-
Training details
|
8 |
|
9 |
- Trained with [TheLastBen's fast-DreamBooth notebook](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb)
|
10 |
- data set: 111 concept images after data augmentation + a number of cusomized reg images (cannot remember)
|
11 |
- learning rate 2e-6 for 5000 steps
|
12 |
- text encoder rate 15%
|
13 |
|
14 |
-
Problems
|
15 |
|
16 |
- The generated images can get blurred easily; this may be due to the use of anime screenshot
|
17 |
- Some cropping does not include face and this is not properly tagged, and therefore it may generate such images
|
18 |
- The pendant is never properly generated
|
19 |
|
20 |
-
Example generations (with inpainting)
|
21 |
|
22 |
![00136-1864644566-hat](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00136-1864644566-hat.png)
|
|
|
23 |
![00143-3043336834-skirt](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00143-3043336834-skirt.png)
|
24 |
![00155-1282216333-pink](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00155-1282216333-pink.png)
|
25 |
-
![00156-4275417758-beautiful](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00156-4275417758-beautiful.png)
|
26 |
-
![00159-3155561993-(sarasa](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00159-3155561993-(sarasa.png)
|
27 |
![00186-4241773092-sarasa](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00186-4241773092-sarasa.png)
|
28 |
|
|
|
2 |
license: creativeml-openrail-m
|
3 |
---
|
4 |
|
5 |
+
Prompt with **"sarasa"**
|
6 |
|
7 |
+
**Training details:**
|
8 |
|
9 |
- Trained with [TheLastBen's fast-DreamBooth notebook](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb)
|
10 |
- data set: 111 concept images after data augmentation + a number of cusomized reg images (cannot remember)
|
11 |
- learning rate 2e-6 for 5000 steps
|
12 |
- text encoder rate 15%
|
13 |
|
14 |
+
**Problems:**
|
15 |
|
16 |
- The generated images can get blurred easily; this may be due to the use of anime screenshot
|
17 |
- Some cropping does not include face and this is not properly tagged, and therefore it may generate such images
|
18 |
- The pendant is never properly generated
|
19 |
|
20 |
+
**Example generations (with inpainting):**
|
21 |
|
22 |
![00136-1864644566-hat](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00136-1864644566-hat.png)
|
23 |
+
![00159-3155561993-(sarasa](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00159-3155561993-(sarasa.png)
|
24 |
![00143-3043336834-skirt](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00143-3043336834-skirt.png)
|
25 |
![00155-1282216333-pink](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00155-1282216333-pink.png)
|
|
|
|
|
26 |
![00186-4241773092-sarasa](https://huggingface.co/alea31415/sarasa-shinmai-renkinjutsushi/resolve/main/00186-4241773092-sarasa.png)
|
27 |
|