diff --git a/modelscope/pipelines/cv/face_recognition_pipeline.py b/modelscope/pipelines/cv/face_recognition_pipeline.py
index 3779b055..506346df 100644
--- a/modelscope/pipelines/cv/face_recognition_pipeline.py
+++ b/modelscope/pipelines/cv/face_recognition_pipeline.py
@@ -24,12 +24,11 @@ logger = get_logger()
     Tasks.face_recognition, module_name=Pipelines.face_recognition)
 class FaceRecognitionPipeline(Pipeline):
 
-    def __init__(self, model: str, face_detection: Pipeline, **kwargs):
+    def __init__(self, model: str, **kwargs):
         """
         use `model` to create a face recognition pipeline for prediction
         Args:
             model: model id on modelscope hub.
-            face_detecion: pipeline for face detection and face alignment before recognition
         """
 
         # face recong model
@@ -47,7 +46,9 @@ class FaceRecognitionPipeline(Pipeline):
         self.face_model = face_model
         logger.info('face recognition model loaded!')
         # face detect pipeline
-        self.face_detection = face_detection
+        det_model_id = 'damo/cv_resnet_facedetection_scrfd10gkps'
+        self.face_detection = pipeline(
+            Tasks.face_detection, model=det_model_id)
 
     def _choose_face(self,
                      det_result,
diff --git a/tests/pipelines/test_face_recognition.py b/tests/pipelines/test_face_recognition.py
index a41de3e3..ea987a72 100644
--- a/tests/pipelines/test_face_recognition.py
+++ b/tests/pipelines/test_face_recognition.py
@@ -17,20 +17,15 @@ from modelscope.utils.test_utils import test_level
 class FaceRecognitionTest(unittest.TestCase):
 
     def setUp(self) -> None:
-        self.recog_model_id = 'damo/cv_ir101_facerecognition_cfglint'
-        self.det_model_id = 'damo/cv_resnet_facedetection_scrfd10gkps'
+        self.model_id = 'damo/cv_ir101_facerecognition_cfglint'
 
     @unittest.skipUnless(test_level() >= 1, 'skip test in current test level')
     def test_face_compare(self):
         img1 = 'data/test/images/face_recognition_1.png'
         img2 = 'data/test/images/face_recognition_2.png'
 
-        face_detection = pipeline(
-            Tasks.face_detection, model=self.det_model_id)
         face_recognition = pipeline(
-            Tasks.face_recognition,
-            face_detection=face_detection,
-            model=self.recog_model_id)
+            Tasks.face_recognition, model=self.model_id)
         # note that for dataset output, the inference-output is a Generator that can be iterated.
         emb1 = face_recognition(img1)[OutputKeys.IMG_EMBEDDING]
         emb2 = face_recognition(img2)[OutputKeys.IMG_EMBEDDING]