diff --git a/README.md b/README.md
index 1d476d2..3842fd7 100644
--- a/README.md
+++ b/README.md
@@ -7,6 +7,13 @@ It's just for fun, the Unet model does not include attention, normalization, etc
 ![](./images/Screenshot_20230314_225320.png)
 ![](./images/ezgif.com-gif-maker.gif)
 
+## Classifier Guidence DDPM
+ref: Diffusion Models Beat GANs on Image Synthesis (https://arxiv.org/abs/2105.05233)
+- generate "7"
+    - ![](./images/Screenshot_20230322_161942.png)
+- generate "2"
+    - ![](./images/Screenshot_20230322_162114.png)
+
 ## Traning
 
 Before training, please set up the config.ini file:
@@ -36,5 +43,6 @@ To generate 16 pictures, run the following command:
 The pictures will be output to the `./output` directory.
 
 ```
-$ python sample 16
+$ python sample 16                  # unconditional
+$ python sample 16 7                # condiditional, want to generate "7" pictures
 ```
\ No newline at end of file
diff --git a/images/Screenshot_20230322_161942.png b/images/Screenshot_20230322_161942.png
new file mode 100644
index 0000000..62a52e6
Binary files /dev/null and b/images/Screenshot_20230322_161942.png differ
diff --git a/images/Screenshot_20230322_162114.png b/images/Screenshot_20230322_162114.png
new file mode 100644
index 0000000..f6da9c5
Binary files /dev/null and b/images/Screenshot_20230322_162114.png differ