Update README.md

README.md

@@ -17,6 +17,7 @@ Based on my personal experience, preparing a LoRA's dataset properly is more imp
       <img src="imgs/upscale/comp.png"/>
       Now we will crop them into roughly 1k resolution (960x832 in this case) using SD WebUI's Auto-size Crop:
       <img src="imgs/upscale/cut-comp.png"/>
-      See the differences? The image with 4x-upscale has a sharper edges comparing to the one without any upscale, and hence looks more clean and less blurry when getting cropped into 1k resolution.  
-      So what does it translate to LoRA learning? 
+      See the differences? The image with 4x-upscale has a sharper edges comparing to the one without any upscale, and hence looks more clean and less blurry when getting cropped into 1k resolution. <br />
+      So what does it translate to LoRA learning? <br />
+      Inside the LoRA training script, we can see a function called [bucket](https://github.com/bmaltais/kohya_ss/wiki/LoRA-training-parameters#enable-buckets)