Update README.md

README.md

@@ -13,7 +13,7 @@ Negative: (realistic, photorealistic), lowres, bad anatomy, bad hands, text, err
 ---
 **Training details:**
 
-Trained with [kanewallmann Dreambooth repository](https://github.com/kanewallmann/Dreambooth-Stable-Diffusion) using tags as captions
+Trained with [kanewallmann Dreambooth repository](https://github.com/kanewallmann/Dreambooth-Stable-Diffusion) using tags as captions  
 The dataset contains 200-400 images for each character and there is also a customized reg set with a few thousands of images
 
 1. I first trained for 25000 steps at lr=1e-6. The result was not very good. (19 characters here)