diff --git a/dalle2_pytorch/dalle2_pytorch.py b/dalle2_pytorch/dalle2_pytorch.py
index dddc206a..81f508bf 100644
--- a/dalle2_pytorch/dalle2_pytorch.py
+++ b/dalle2_pytorch/dalle2_pytorch.py
@@ -1214,7 +1214,7 @@ def sample(self, image_embed, text = None, cond_scale = 1.):
 
         return img
 
-    def forward(self, image, text = None, image_embed = None, unet_number = None):
+    def forward(self, image, text = None, image_embed = None, text_encodings = None, unet_number = None):
         assert not (len(self.unets) > 1 and not exists(unet_number)), f'you must specify which unet you want trained, from a range of 1 to {len(self.unets)}, if you are training cascading DDPM (multiple unets)'
         unet_number = default(unet_number, 1)
         assert 1 <= unet_number <= len(self.unets)
@@ -1233,7 +1233,7 @@ def forward(self, image, text = None, image_embed = None, unet_number = None):
         if not exists(image_embed):
             image_embed = self.get_image_embed(image)
 
-        text_encodings = self.get_text_encodings(text) if exists(text) else None
+        text_encodings = self.get_text_encodings(text) if exists(text) and not exists(text_encodings) else None
 
         lowres_cond_img = image if index > 0 else None
         ddpm_image = resize_image_to(image, target_image_size)
diff --git a/setup.py b/setup.py
index 00bb2323..681eef5d 100644
--- a/setup.py
+++ b/setup.py
@@ -10,7 +10,7 @@
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.0.23',
+  version = '0.0.24',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',