Update README.md

README.md

@@ -17,6 +17,18 @@ The individual character colors, patterns, proportions, and extra refinement was
 ![ReferenceImage](RefImages/3.png)
 (note that these images were cherry-picked, don't be shocked to see some cursed abominations)
 
+# Example negative prompt:
+```
+weirdly colored eyes, weird eyelids, bad art, ((inaccurate)), (missing pupils), weird pupils, inaccurate eyes, weird eyes, bad proportions, more than two ears, (less than two ears), blank eyes, realistic, missing hands, weird, inaccurate pupils, colored eyes, (missing tail), ugly, weird scaling, larger lowerbody, deformed, disfigured, stretched, human, tiled, repeated image, symmetry, unofficial, unofficial artwork
+```
+
+# limitations:
+- Everything was trained from 512x512 images, higher resolution generations will have issues
+- It does not know what the characters look like from behind, and only generate images of them looking forward, left, or right.
+- It struggles to get more dynamic poses, it does good at standing, mediocre with sitting, but laying down and others it struggles.
+- Don't expect high precision control of arm poses
+- Often gets confused with eyes and eyelids
+
 # **(Disclaimer)**
 
 *I am not affiliated with Ludo and do not own the rights to Bluey or its content, this ai was trained off of images from Bluey of which I do not own, and produces images similar to Bluey.