Update README.md

README.md

@@ -50,9 +50,9 @@ LocalDiT achieves comparable image quality to PixArt-α while offering:
 This model is released under the Apache 2.0 License.
 
 # Limitations
-The model primarily works with English text prompts
-Like other text-to-image models, it may struggle with complex spatial relationships, text rendering, and accurate human anatomy
-The model may inherit biases present in the training data
+1. The model primarily works with English text prompts
+2. Like other text-to-image models, it struggle with complex spatial relationships, text rendering, and accurate human/animal anatomy
+3. The model may inherit biases present in the training data
 
 # Citation
 Citation information will be provided at a later date.