diff --git a/lessons/X-Extras/X1-MultiModal/Clip.ipynb b/lessons/X-Extras/X1-MultiModal/Clip.ipynb
index 8da9c6b1..397fe18e 100644
--- a/lessons/X-Extras/X1-MultiModal/Clip.ipynb
+++ b/lessons/X-Extras/X1-MultiModal/Clip.ipynb
@@ -21,8 +21,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#import sys\n",
-    "#!{sys.executable} -m pip install git+https://github.com/openai/CLIP.git"
+    "import sys\n",
+    "!{sys.executable} -m pip install git+https://github.com/openai/CLIP.git"
    ]
   },
   {
diff --git a/lessons/X-Extras/X1-MultiModal/README.md b/lessons/X-Extras/X1-MultiModal/README.md
index aa8b6801..3b81a155 100644
--- a/lessons/X-Extras/X1-MultiModal/README.md
+++ b/lessons/X-Extras/X1-MultiModal/README.md
@@ -50,7 +50,7 @@ To generate an image corresponding to a text prompt, we start with some random e
 
 A great library that implements VQGAN+CLIP is [Pixray](http://github.com/pixray/pixray)
 
-![Picture produced by Pixray](a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png) |  ![Picture produced by pixray](a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png)
+![Picture produced by Pixray](images/a_closeup_watercolor_portrait_of_young_male_teacher_of_literature_with_a_book.png) |  ![Picture produced by pixray](images/a_closeup_oil_portrait_of_young_female_teacher_of_computer_science_with_a_computer.png)
 ----|----
 Picture generated from prompt *a closeup watercolor portrait of young male teacher of literature with a book* | Picture generated from prompt *a closeup oil portrait of young female teacher of computer science with a computer*