Update README.md
Browse files
README.md
CHANGED
|
@@ -2,21 +2,21 @@
|
|
| 2 |
license: creativeml-openrail-m
|
| 3 |
---
|
| 4 |
|
| 5 |
-
Prompt with "francat"
|
| 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: 225 concept images + 224 custmized reg images
|
| 11 |
- learning rate 2e-6 for 5500 steps
|
| 12 |
- text encoder rate 15%
|
| 13 |
|
| 14 |
-
Problems
|
| 15 |
|
| 16 |
- The generated images can get blurred easily is often quite dark, especially when anime screenshot is specified.
|
| 17 |
- Cannot get the clothes and the sword properly. This may require tagging the clothes separately.
|
| 18 |
|
| 19 |
-
Example generations (with inpainting)
|
| 20 |
|
| 21 |
|
| 22 |
|
|
|
|
| 2 |
license: creativeml-openrail-m
|
| 3 |
---
|
| 4 |
|
| 5 |
+
Prompt with **"francat"**
|
| 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: 225 concept images + 224 custmized reg images
|
| 11 |
- learning rate 2e-6 for 5500 steps
|
| 12 |
- text encoder rate 15%
|
| 13 |
|
| 14 |
+
**Problems:**
|
| 15 |
|
| 16 |
- The generated images can get blurred easily is often quite dark, especially when anime screenshot is specified.
|
| 17 |
- Cannot get the clothes and the sword properly. This may require tagging the clothes separately.
|
| 18 |
|
| 19 |
+
**Example generations (with inpainting):**
|
| 20 |
|
| 21 |
|
| 22 |
|