diff --git a/nemo/collections/multimodal/modules/stable_diffusion/encoders/modules.py b/nemo/collections/multimodal/modules/stable_diffusion/encoders/modules.py
index 5d2c2376ebb5..ab33532c3c1f 100644
--- a/nemo/collections/multimodal/modules/stable_diffusion/encoders/modules.py
+++ b/nemo/collections/multimodal/modules/stable_diffusion/encoders/modules.py
@@ -298,7 +298,7 @@ def encode(self, x):
 
 
 class BERTTokenizer(AbstractEncoder):
-    """ Uses a pretrained BERT tokenizer by huggingface. Vocab size: 30522 (?)"""
+    """Uses a pretrained BERT tokenizer by huggingface. Vocab size: 30522 (?)"""
 
     def __init__(self, device="cuda", vq_interface=True, max_length=77):
         super().__init__()
@@ -530,7 +530,10 @@ def __init__(
         print(f"Downloading clip with", arch, version, cache_dir)
         self.device = device
         model, _, _ = open_clip.create_model_and_transforms(
-            arch, device=torch.device("cpu"), pretrained=version, cache_dir=cache_dir,
+            arch,
+            device=torch.device("cpu"),
+            pretrained=version,
+            cache_dir=cache_dir,
         )
         del model.visual
         self.model = model
@@ -669,7 +672,11 @@ def build_tokenizer(self, cfg):
             legacy=legacy,
         )
 
-        _, self.text_transform = get_preprocess_fns(cfg, self.tokenizer, is_train=False,)
+        _, self.text_transform = get_preprocess_fns(
+            cfg,
+            self.tokenizer,
+            is_train=False,
+        )
         self.max_length = cfg.text.get("max_position_embeddings")
 
     def load_model(self, cfg, state_dict):
@@ -764,7 +771,11 @@ def __init__(
         super().__init__()
         assert layer in self.LAYERS
         self.projection_dim = 1280
-        model, _, _ = open_clip.create_model_and_transforms(arch, device=torch.device("cpu"), pretrained=version,)
+        model, _, _ = open_clip.create_model_and_transforms(
+            arch,
+            device=torch.device("cpu"),
+            pretrained=version,
+        )
         del model.visual
         self.model = model