diff --git a/readme.md b/readme.md
index 2320218..80f4ed5 100644
--- a/readme.md
+++ b/readme.md
@@ -33,18 +33,19 @@ SCEPTER offers 3 core components:
 ### Edit Tuners
 
 Simply provide 10 image pairs, SCEPTER will tune an edit tuner for your own Image-to-Image tasks, like `de-text`, `segmentation`, etc.
-Try our official few-shot datasets: [De-Text](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fdetext.zip), [Image2Hed](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fhed_pair.zip), [image2depth](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fimage2depth.zip), [depth2image](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fdepth2image.zip)
+Try our official few-shot datasets: [De-Text](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fdetext.zip), [Image2Hed](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fhed_pair.zip), [image2depth](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fimage2depth.zip), [depth2image](https://www.modelscope.cn/api/v1/models/iic/scepter/repo?Revision=master&FilePath=datasets%2Fdepth2image.zip).
 <table>
   <tr>
-    <td align="center"><strong>De-Text</strong><br><img src="asset/images/edit_tuner/text.jpg" width="300"><img src="asset/images/edit_tuner/detext.jpeg" width="300"><br>Prompt: <strong>"Remove the texts"</strong> (Left: input Right: output)</td>
-    <td align="center"><strong>Image2Hed</strong><br><img src="asset/images/edit_tuner/cat_512.jpg" width="300"><img src="asset/images/edit_tuner/hed.jpeg" width="300"><br>Prompt: <strong>"Convert to an edge map"</strong> (Left: input Right: output)</td>
+    <td align="center"><strong>De-Text</strong><br><img src="asset/images/edit_tuner/text.jpg" width="230"><img src="asset/images/edit_tuner/detext.jpeg" width="230"><br>Prompt: <strong>"Remove the texts"</strong> </td>
+    <td align="center"><strong>Image2Hed</strong><br><img src="asset/images/edit_tuner/cat_512.jpg" width="230"><img src="asset/images/edit_tuner/hed.jpeg" width="230"><br>Prompt: <strong>"Convert to an edge map"</strong> </td>
   </tr>
   <tr>
-    <td align="center"><strong>Image2Depth</strong><br><img src="asset/images/edit_tuner/house.jpg" width="300"><img src="asset/images/edit_tuner/image2depth.jpeg" width="300"><br>Prompt: <strong>"Calculate the depth map"</strong> (Left: input Right: output)</td>
-    <td align="center"><strong>Depth2Image</strong><br><img src="asset/images/edit_tuner/depth.jpg" width="300"><img src="asset/images/edit_tuner/depth2image.jpeg" width="300"><br>Prompt: <strong>"Convert depth map into color image"</strong> (Left: input Right: output)</td>
+    <td align="center"><strong>Image2Depth</strong><br><img src="asset/images/edit_tuner/house.jpg" width="230"><img src="asset/images/edit_tuner/image2depth.jpeg" width="230"><br>Prompt: <strong>"Calculate the depth map"</strong> </td>
+    <td align="center"><strong>Depth2Image</strong><br><img src="asset/images/edit_tuner/depth.jpg" width="230"><img src="asset/images/edit_tuner/depth2image.jpeg" width="230"><br>Prompt: <strong>"Convert depth map into color image"</strong> </td>
   </tr>
 </table>
 
+Note: Left image is input and right image is output.
 
 ## 🛠️ Installation