diff --git a/examples/text_to_image/train_text_to_image_lora.py b/examples/text_to_image/train_text_to_image_lora.py
index b56e0dca536c..a3c5bef73a95 100644
--- a/examples/text_to_image/train_text_to_image_lora.py
+++ b/examples/text_to_image/train_text_to_image_lora.py
@@ -415,7 +415,12 @@ def main():
     unet = UNet2DConditionModel.from_pretrained(
         args.pretrained_model_name_or_path, subfolder="unet", revision=args.revision
     )
-
+    # freeze parameters of models to save more memory
+    unet.requires_grad_(False)
+    vae.requires_grad_(False)
+    
+    text_encoder.requires_grad_(False)
+    
     # For mixed precision training we cast the text_encoder and vae weights to half-precision
     # as these models are only used for inference, keeping weights in full precision is not required.
     weight_dtype = torch.float32