diff --git a/README.md b/README.md
index d19c969..dbbe4cc 100644
--- a/README.md
+++ b/README.md
@@ -79,13 +79,11 @@ It uses the pre-trained model specified by model name to generate an image embed
 
 **Parameters:**
 
-***data:*** *Union[List[towhee._types.Image], towhee._types.Image]*
+***data:*** *towhee._types.Image*
 
-The decoded image data in numpy.ndarray. It allows both single input and a list for batch input.
+The decoded image data in towhee Image (a subset of numpy.ndarray).
 
 
-**Returns:** *Union[List[numpy.ndarray], numpy.ndarray]*
+**Returns:** *numpy.ndarray*
 
-If only 1 image input, then output is an image embedding in shape of (feature_dim,).
-If a list of images as input, then output is a same-length list of numpy.ndarray,
-each of which represents an image embedding in shape of (feature_dim,).
+ An image embedding generated by model, in shape of (feature_dim,).