Update README.md
Browse files
README.md
CHANGED
@@ -13,5 +13,5 @@ Based on my personal experience, preparing a LoRA's dataset properly is more imp
|
|
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
|
17 |
<img src="https://huggingface.co/fallenl/My_2cents_on_LoRa_training/blob/main/imgs/upscale/comp.png"/>
|
|
|
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 907x823 pixels, the other with 3624x3288 pixels using simple 4x-upscale from SD WebUI.
|
17 |
<img src="https://huggingface.co/fallenl/My_2cents_on_LoRa_training/blob/main/imgs/upscale/comp.png"/>
|