Update README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,16 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
-
# This is **NOT A GUIDE** for LoRA training, and
|
5 |
|
6 |
# This serves as a onging project that I share some of the personal opinions or interesting findings where I learned or discovered during my journey in LoRA training.
|
7 |
|
8 |
-
To start with, LoRA training could be easy and quick with
|
|
|
9 |
|
10 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
+
# This is **NOT A GUIDE** for LoRA training, and please NEVER treat it as.
|
5 |
|
6 |
# This serves as a onging project that I share some of the personal opinions or interesting findings where I learned or discovered during my journey in LoRA training.
|
7 |
|
8 |
+
To start with, LoRA training could be easy and quick with simple dataset preparation and training setup; but surely that's not what I'm satisfied with.
|
9 |
+
Based on my personal experience, preparing a LoRA's dataset properly is more important than using complicated and fancy training techniques. Just like cooking, you can't make any tasty dishes using materials without good quality.
|
10 |
|
11 |
+
- ### Dataset preparation
|
12 |
+
I'll disscuss several steps that I usually do when I prepare the dataset for a LoRA in order, and I'll skip the "How to Get Image Data" part since there're too many tools/methods available for you to use.
|
13 |
+
1. After getting all image data needed for a LoRA, remove all none-static image files (.mp4, .wav, .gif, etc). Then change all none-.png format images into .png.
|
14 |
+
2. Spend some time going through the images to see if there're any duplicated images and remove them. This will happen a lot if the dataset is large.
|
15 |
+
3. Upscale all low-resolution images to at least 2k resolution. But why? Let's see an example:
|
16 |
+
We have two identical png images, one with 907*823 pixels, the other with 3624*3288 pixels using simple 4x-upscale from SD WebUI.
|