Update README.md

README.md

@@ -16,15 +16,15 @@ This model was trained on the Valorant agents splash arts, and some extra arts o
 I thought about including the agents trailers and lore videos, but for the art style is slightly ever so different. I might make an updated version which includes them.
 The model can do portraits and landscape (possibly animal as well?), but not many objects, or at least not cars.
 
+To reference the art style, use the token: valorant style
+
+There is already an existing model that uses textual inversion. This is trained using Dreambooth instead, whether or not this method is better, I will let you judge.
+
 ### Gradio
 
 We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run Valorant_Diffusion:
 [![Open In Spaces](https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565)](https://huggingface.co/spaces/akhaliq/Valorant_Diffusion)
 
-To reference the art style, use the token: valorant style
-
-There is already an existing model that uses textual inversion. This is trained using Dreambooth instead, whether or not this method is better, I will let you judge.
-
 Here are some samples.
 
 **Portraits**