Update README.md

README.md

@@ -36,6 +36,10 @@ All model versions are trained using a hand labeled image set of 556 images with
 
 Any model versions with **pploss** in the name were trained with prior preservation loss enabled and used a regularization set of 8000 portrait images comprised of photos/paintings/digitalart of humans in modern day attire.
 
+**1.5 trained model vs 1.4 trained model and hypernetwork presence**
+
+![output Samples](https://huggingface.co/Severian-Void/Starsector-Portraits/resolve/main/images/1.4_vs_1.5_comparrison.png)
+
 **CFG and SAMPLE STEP comparisons between rc_v1 model files**
 
 (prompt: "a starsectorportrait of a person" sampler: euler_a)