Update README.md

README.md

@@ -207,6 +207,14 @@ For higher quality outcomes, prepend prompts with:
 (masterpiece, best quality, very aesthetic, ultra detailed), intricate details,
 ```
 
+### Tag Ordering
+
+For optimal results, it's recommended to follow the structured prompt template because we train the model like this:
+
+```
+1girl/1boy, character name, from what series, everything else in any order.
+```
+
 ### Multi Aspect Resolution
 
 This model supports generating images at the following dimensions: