minor summar updates

README.md

@@ -12,17 +12,21 @@ language:
 ---
 # CommonCanvas-S-NC
 
+**Version Number:** 0.1
+
 ## Summary
 CommonCanvas is a family of latent diffusion models capable of generating images from a given text prompt. 
 Different models in the family are different sizes, and trained on different subsets of the CommonCatalog Dataset (See Data Card), a large dataset of Creative Commons licensed images with synthetic captions produced using a pre-trained BLIP-2 captioning model.
 CommonCanvas-S-NC is the small (S) model based off the Stable Diffusion 2 architecture, and trained on the non-commercial (NC) subset of CommonCatalog.
 
+The goal of this purpose is to produce a high-quality text-to-image model, but to do so using an easily accessible dataset of known provenance. 
+The exact training recipe of the model can be found in the paper hosted at this link. https://arxiv.org/abs/2310.16825
+
+
+### Training Overview
 **Input:** CommonCatalog Text Captions  
 **Output:** CommonCatalog Images  
 **Architecture:** Stable Diffusion 2  
-**Version Number:** 0.1
-
-The goal of this purpose is to produce a model that is competitive with Stable Diffusion 2, but to do so using an easily accessible dataset of known provenance. Doing so makes replicating the model significantly easier and provides proper attribution to all the creative commons work used to train the model. The exact training recipe of the model can be found in the paper hosted at this link. https://arxiv.org/abs/2310.16825
 
 ## Performance Limitations