diff --git a/examples/dreambooth/train_dreambooth_sd3.py b/examples/dreambooth/train_dreambooth_sd3.py
index 525a4cc906e9..865696855940 100644
--- a/examples/dreambooth/train_dreambooth_sd3.py
+++ b/examples/dreambooth/train_dreambooth_sd3.py
@@ -902,20 +902,26 @@ def _encode_prompt_with_clip(
     tokenizer,
     prompt: str,
     device=None,
+    text_input_ids=None,
     num_images_per_prompt: int = 1,
 ):
     prompt = [prompt] if isinstance(prompt, str) else prompt
     batch_size = len(prompt)
 
-    text_inputs = tokenizer(
-        prompt,
-        padding="max_length",
-        max_length=77,
-        truncation=True,
-        return_tensors="pt",
-    )
+    if tokenizer is not None:
+        text_inputs = tokenizer(
+            prompt,
+            padding="max_length",
+            max_length=77,
+            truncation=True,
+            return_tensors="pt",
+        )
+
+        text_input_ids = text_inputs.input_ids
+    else:
+        if text_input_ids is None:
+            raise ValueError("text_input_ids must be provided when the tokenizer is not specified")
 
-    text_input_ids = text_inputs.input_ids
     prompt_embeds = text_encoder(text_input_ids.to(device), output_hidden_states=True)
 
     pooled_prompt_embeds = prompt_embeds[0]
@@ -937,6 +943,7 @@ def encode_prompt(
     max_sequence_length,
     device=None,
     num_images_per_prompt: int = 1,
+    text_input_ids_list=None,
 ):
     prompt = [prompt] if isinstance(prompt, str) else prompt
 
@@ -945,13 +952,14 @@ def encode_prompt(
 
     clip_prompt_embeds_list = []
     clip_pooled_prompt_embeds_list = []
-    for tokenizer, text_encoder in zip(clip_tokenizers, clip_text_encoders):
+    for i, (tokenizer, text_encoder) in enumerate(zip(clip_tokenizers, clip_text_encoders)):
         prompt_embeds, pooled_prompt_embeds = _encode_prompt_with_clip(
             text_encoder=text_encoder,
             tokenizer=tokenizer,
             prompt=prompt,
             device=device if device is not None else text_encoder.device,
             num_images_per_prompt=num_images_per_prompt,
+            text_input_ids=text_input_ids_list[i] if text_input_ids_list else None,
         )
         clip_prompt_embeds_list.append(prompt_embeds)
         clip_pooled_prompt_embeds_list.append(pooled_prompt_embeds)