diff --git a/8.4-generating-images-with-vaes.ipynb b/8.4-generating-images-with-vaes.ipynb
index 1c5a301224..26755fb116 100644
--- a/8.4-generating-images-with-vaes.ipynb
+++ b/8.4-generating-images-with-vaes.ipynb
@@ -184,7 +184,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Here is the code for using `z_mean` and `z_log_var`, the parameters of the statistical distribution assumed to have produced `img_img`, to \n",
+    "Here is the code for using `z_mean` and `z_log_var`, the parameters of the statistical distribution assumed to have produced `input_img`, to \n",
     "generate a latent space point `z`. Here, we wrap some arbitrary code (built on top of Keras backend primitives) into a `Lambda` layer. In \n",
     "Keras, everything needs to be a layer, so code that isn't part of a built-in layer should be wrapped in a `Lambda` (or else, in a custom \n",
     "layer)."