diff --git a/modules/image/face_detection/pyramidbox_lite_server/README.md b/modules/image/face_detection/pyramidbox_lite_server/README.md
index 47417aa7a484efb40ff06ca43d3e592806735cf8..4da44a9fcff9aff91ab364e2df2aed4b1b0c4f97 100644
--- a/modules/image/face_detection/pyramidbox_lite_server/README.md
+++ b/modules/image/face_detection/pyramidbox_lite_server/README.md
@@ -150,6 +150,10 @@
     print(r.json()["results"])
     ```
 
+- ### gradio app 支持
+
+  从 PaddleHub 2.3.1 开始支持使用链接 http://127.0.0.1:8866/gradio/pyramidbox_lite_server 在浏览器中访问 pyramidbox_lite_server 的 Gradio APP。
+
 
 ## 五、更新历史
 
@@ -169,6 +173,10 @@
 
   修复无法导出推理模型的问题
 
+* 1.4.0
+
+  添加 Gradio APP 支持
+
   - ```shell
-    $ hub install pyramidbox_lite_server==1.3.0
+    $ hub install pyramidbox_lite_server==1.4.0
     ```
diff --git a/modules/image/face_detection/pyramidbox_lite_server/README_en.md b/modules/image/face_detection/pyramidbox_lite_server/README_en.md
index 67fa28b3174780c31b34740a8412c240be637c71..8c5cfeb702b1d65b67459fa07e8287d37718348e 100644
--- a/modules/image/face_detection/pyramidbox_lite_server/README_en.md
+++ b/modules/image/face_detection/pyramidbox_lite_server/README_en.md
@@ -150,6 +150,8 @@
     print(r.json()["results"])
     ```
 
+- ### Gradio APP support
+  Starting with PaddleHub 2.3.1, the Gradio APP for pyramidbox_lite_server is supported to be accessed in the browser using the link http://127.0.0.1:8866/gradio/pyramidbox_lite_server.
 
 ## V.Release Note
 
@@ -169,6 +171,10 @@
 
   Fix a bug of save_inference_model
 
+* 1.4.0
+
+  Add Gradio APP support.
+
   - ```shell
-    $ hub install pyramidbox_lite_server==1.3.0
+    $ hub install pyramidbox_lite_server==1.4.0
     ```
diff --git a/modules/image/face_detection/pyramidbox_lite_server/data_feed.py b/modules/image/face_detection/pyramidbox_lite_server/data_feed.py
index a2cb2883fa07fa76749f26bbdf63298520da4fef..b2d51e206eed041be67124fdd2d5432dd999aa95 100644
--- a/modules/image/face_detection/pyramidbox_lite_server/data_feed.py
+++ b/modules/image/face_detection/pyramidbox_lite_server/data_feed.py
@@ -1,4 +1,3 @@
-# coding=utf-8
 import os
 import time
 from collections import OrderedDict
diff --git a/modules/image/face_detection/pyramidbox_lite_server/module.py b/modules/image/face_detection/pyramidbox_lite_server/module.py
index 5fe7c7a57495212dd6901898c8b84b92e9668d49..e16ff8d939f8e502c502842778f530ade8171fc3 100644
--- a/modules/image/face_detection/pyramidbox_lite_server/module.py
+++ b/modules/image/face_detection/pyramidbox_lite_server/module.py
@@ -1,4 +1,3 @@
-# coding=utf-8
 from __future__ import absolute_import
 from __future__ import division
 
@@ -7,13 +6,12 @@ import ast
 import os
 
 import numpy as np
-import paddle
 from paddle.inference import Config
 from paddle.inference import create_predictor
+
 from .data_feed import reader
 from .processor import base64_to_cv2
 from .processor import postprocess
-
 from paddlehub.module.module import moduleinfo
 from paddlehub.module.module import runnable
 from paddlehub.module.module import serving
@@ -24,10 +22,12 @@ from paddlehub.module.module import serving
             author="baidu-vis",
             author_email="",
             summary="PyramidBox-Lite-Server is a high-performance face detection model.",
-            version="1.3.0")
+            version="1.4.0")
 class PyramidBoxLiteServer:
+
     def __init__(self):
-        self.default_pretrained_model_path = os.path.join(self.directory, "pyramidbox_lite_server_face_detection", "model")
+        self.default_pretrained_model_path = os.path.join(self.directory, "pyramidbox_lite_server_face_detection",
+                                                          "model")
         self._set_config()
         self.processor = self
 
@@ -35,8 +35,8 @@ class PyramidBoxLiteServer:
         """
         predictor config setting
         """
-        model = self.default_pretrained_model_path+'.pdmodel'
-        params = self.default_pretrained_model_path+'.pdiparams'
+        model = self.default_pretrained_model_path + '.pdmodel'
+        params = self.default_pretrained_model_path + '.pdiparams'
         cpu_config = Config(model, params)
         cpu_config.disable_glog_info()
         cpu_config.disable_gpu()
@@ -188,3 +188,28 @@ class PyramidBoxLiteServer:
                                           type=ast.literal_eval,
                                           default=0.6,
                                           help="confidence threshold.")
+
+    def create_gradio_app(self):
+        import gradio as gr
+        import tempfile
+        import os
+        from PIL import Image
+
+        def inference(image, shrink, confs_threshold):
+            with tempfile.TemporaryDirectory() as temp_dir:
+                self.face_detection(paths=[image],
+                                    use_gpu=False,
+                                    visualization=True,
+                                    output_dir=temp_dir,
+                                    shrink=shrink,
+                                    confs_threshold=confs_threshold)
+                return Image.open(os.path.join(temp_dir, os.listdir(temp_dir)[0]))
+
+        interface = gr.Interface(inference, [
+            gr.inputs.Image(type="filepath"),
+            gr.Slider(0.0, 1.0, 0.5, step=0.01),
+            gr.Slider(0.0, 1.0, 0.6, step=0.01)
+        ],
+                                 gr.outputs.Image(type="ndarray"),
+                                 title='pyramidbox_lite_server')
+        return interface
diff --git a/modules/image/face_detection/pyramidbox_lite_server/processor.py b/modules/image/face_detection/pyramidbox_lite_server/processor.py
index 2045f51c21be5a437c196ca86a41b6c2cf61d64d..b46b30136827a6ef01ce6198755956ff632a3310 100644
--- a/modules/image/face_detection/pyramidbox_lite_server/processor.py
+++ b/modules/image/face_detection/pyramidbox_lite_server/processor.py
@@ -1,12 +1,11 @@
-# coding=utf-8
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
+import base64
 import os
 import time
 
-import base64
 import cv2
 import numpy as np
 from PIL import Image