diff --git a/data/test/images/face_liveness_xc.png b/data/test/images/face_liveness_xc.png
new file mode 100644
index 00000000..54777f9e
--- /dev/null
+++ b/data/test/images/face_liveness_xc.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abad2347748bf312ab0dbce48fdc643a703d94970e1b181cf19b9be6312db8c
+size 3145728
diff --git a/modelscope/metainfo.py b/modelscope/metainfo.py
index 21cd7cb6..3fca7856 100644
--- a/modelscope/metainfo.py
+++ b/modelscope/metainfo.py
@@ -236,6 +236,7 @@ class Pipelines(object):
     face_detection = 'resnet-face-detection-scrfd10gkps'
     face_liveness_ir = 'manual-face-liveness-flir'
     face_liveness_rgb = 'manual-face-liveness-flir'
+    face_liveness_xc = 'manual-face-liveness-flxc'
     card_detection = 'resnet-card-detection-scrfd34gkps'
     ulfd_face_detection = 'manual-face-detection-ulfd'
     tinymog_face_detection = 'manual-face-detection-tinymog'
diff --git a/modelscope/pipelines/cv/face_liveness_xc_pipeline.py b/modelscope/pipelines/cv/face_liveness_xc_pipeline.py
new file mode 100644
index 00000000..dbe19be1
--- /dev/null
+++ b/modelscope/pipelines/cv/face_liveness_xc_pipeline.py
@@ -0,0 +1,87 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+import os.path as osp
+from typing import Any, Dict
+
+import cv2
+import numpy as np
+import onnxruntime
+import PIL
+import torch
+import torch.nn.functional as F
+
+from modelscope.metainfo import Pipelines
+from modelscope.models.cv.face_recognition.align_face import align_face
+from modelscope.models.cv.facial_landmark_confidence import \
+    FacialLandmarkConfidence
+from modelscope.outputs import OutputKeys
+from modelscope.pipelines import pipeline
+from modelscope.pipelines.base import Input, Pipeline
+from modelscope.pipelines.builder import PIPELINES
+from modelscope.preprocessors import LoadImage
+from modelscope.utils.constant import ModelFile, Tasks
+from modelscope.utils.logger import get_logger
+from . import FaceProcessingBasePipeline
+
+logger = get_logger()
+
+
+@PIPELINES.register_module(
+    Tasks.face_liveness, module_name=Pipelines.face_liveness_xc)
+class FaceLivenessXcPipeline(FaceProcessingBasePipeline):
+
+    def __init__(self, model: str, **kwargs):
+        """
+        FaceLivenessXcPipeline can judge the input face is a real or fake face.
+        use `model` to create a face lievness ir pipeline for prediction
+        Args:
+            model: model id on modelscope hub.
+        ```python
+        >>> from modelscope.pipelines import pipeline
+        >>> fl_xc = pipeline('face_liveness', 'damo/cv_manual_face-liveness_flxc')
+        >>> fl_xc("https://modelscope.oss-cn-beijing.aliyuncs.com/test/images/face_liveness_xc.png")
+        {'scores': [0.03821974992752075], 'boxes': [[12.569677352905273, 6.428711891174316,
+            94.17887115478516, 106.74441528320312]]}
+        ```
+        """
+        super().__init__(model=model, **kwargs)
+        onnx_path = osp.join(model, ModelFile.ONNX_MODEL_FILE)
+        logger.info(f'loading model from {onnx_path}')
+        self.sess, self.input_node_name, self.out_node_name = self.load_onnx_model(
+            onnx_path)
+        logger.info('load model done')
+
+    def load_onnx_model(self, onnx_path):
+        sess = onnxruntime.InferenceSession(onnx_path)
+        out_node_name = []
+        input_node_name = []
+        for node in sess.get_outputs():
+            out_node_name.append(node.name)
+
+        for node in sess.get_inputs():
+            input_node_name.append(node.name)
+
+        return sess, input_node_name, out_node_name
+
+    def preprocess(self, input: Input) -> Dict[str, Any]:
+        result = super().preprocess(input)
+        img = result['img']
+        img = (img - 127.5) * 0.0078125
+        img = np.expand_dims(img, 0).copy()
+        input_tensor = np.concatenate([img, img, img, img], axis=3)
+        input_tensor = np.transpose(
+            input_tensor, axes=(0, 3, 1, 2)).astype(np.float32)
+        result['input_tensor'] = input_tensor
+        return result
+
+    def forward(self, input: Dict[str, Any]) -> Dict[str, Any]:
+        input_feed = {}
+        input_feed[
+            self.input_node_name[0]] = input['input_tensor'].cpu().numpy()
+        result = self.sess.run(self.out_node_name, input_feed=input_feed)
+        scores = [result[0][0][0].tolist()]
+
+        boxes = input['bbox'].cpu().numpy()[np.newaxis, :].tolist()
+        return {OutputKeys.SCORES: scores, OutputKeys.BOXES: boxes}
+
+    def postprocess(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
+        return inputs
diff --git a/tests/pipelines/test_face_liveness_xc.py b/tests/pipelines/test_face_liveness_xc.py
new file mode 100644
index 00000000..91b46e01
--- /dev/null
+++ b/tests/pipelines/test_face_liveness_xc.py
@@ -0,0 +1,38 @@
+# Copyright (c) Alibaba, Inc. and its affiliates.
+import os.path as osp
+import unittest
+
+import cv2
+
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+from modelscope.utils.cv.image_utils import draw_face_detection_no_lm_result
+from modelscope.utils.test_utils import test_level
+
+
+class FaceLivenessXcTest(unittest.TestCase):
+
+    def setUp(self) -> None:
+        self.model_id = 'damo/cv_manual_face-liveness_flxc'
+        self.img_path = 'data/test/images/face_liveness_rgb.png'
+
+    def show_result(self, img_path, detection_result):
+        img = draw_face_detection_no_lm_result(img_path, detection_result)
+        cv2.imwrite('result.png', img)
+        print(f'output written to {osp.abspath("result.png")}')
+
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
+    def test_run_modelhub(self):
+        face_detection = pipeline(Tasks.face_liveness, model=self.model_id)
+        result = face_detection(self.img_path)
+        self.show_result(self.img_path, result)
+
+    @unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
+    def test_run_default_model(self):
+        face_detection = pipeline(Tasks.face_liveness)
+        result = face_detection(self.img_path)
+        self.show_result(self.img_path, result)
+
+
+if __name__ == '__main__':
+    unittest.main()