Update README.md
Browse files
README.md
CHANGED
@@ -24,7 +24,7 @@ In this section, I'll outline the steps I typically follow to prepare the datase
|
|
24 |
![Comparison](imgs/upscale/comp.png)
|
25 |
- Now, let's crop them to roughly 1k resolution (960x832 pixels in this case) using SD WebUI's Auto-size Crop:
|
26 |
![Cropped Comparison](imgs/upscale/cut-comp.png)
|
27 |
-
- Notice the difference? The image with 4x upscale has sharper edges compared to the one without any upscale, resulting in a
|
28 |
|
29 |
- So, why is this important for LoRA learning?
|
30 |
Inside the LoRA training script, there's a function called [bucket](https://github.com/bmaltais/kohya_ss/wiki/LoRA-training-parameters#enable-buckets) that automatically crops your image data to a size close to the training resolution specified in the training setup.
|
|
|
24 |
![Comparison](imgs/upscale/comp.png)
|
25 |
- Now, let's crop them to roughly 1k resolution (960x832 pixels in this case) using SD WebUI's Auto-size Crop:
|
26 |
![Cropped Comparison](imgs/upscale/cut-comp.png)
|
27 |
+
- Notice the difference? The image with 4x upscale has sharper edges compared to the one without any upscale, resulting in a clean and less blurry appearance when cropped into 1k resolution.
|
28 |
|
29 |
- So, why is this important for LoRA learning?
|
30 |
Inside the LoRA training script, there's a function called [bucket](https://github.com/bmaltais/kohya_ss/wiki/LoRA-training-parameters#enable-buckets) that automatically crops your image data to a size close to the training resolution specified in the training setup.
|