add module.dtype fix to dreambooth script

Author: linoytsaban

examples/dreambooth/train_dreambooth_flux.py

@@ -895,7 +895,10 @@ def _encode_prompt_with_t5(
 
     prompt_embeds = text_encoder(text_input_ids.to(device))[0]
 
-    dtype = text_encoder.dtype
+    if hasattr(text_encoder, "module"):
+        dtype = text_encoder.module.dtype
+    else:
+        dtype = text_encoder.dtype
     prompt_embeds = prompt_embeds.to(dtype=dtype, device=device)
 
     _, seq_len, _ = prompt_embeds.shape
@@ -936,9 +939,13 @@ def _encode_prompt_with_clip(
 
     prompt_embeds = text_encoder(text_input_ids.to(device), output_hidden_states=False)
 
+    if hasattr(text_encoder, "module"):
+        dtype = text_encoder.module.dtype
+    else:
+        dtype = text_encoder.dtype
     # Use pooled output of CLIPTextModel
     prompt_embeds = prompt_embeds.pooler_output
-    prompt_embeds = prompt_embeds.to(dtype=text_encoder.dtype, device=device)
+    prompt_embeds = prompt_embeds.to(dtype=dtype, device=device)
 
     # duplicate text embeddings for each generation per prompt, using mps friendly method
     prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
@@ -958,7 +965,12 @@ def encode_prompt(
 ):
     prompt = [prompt] if isinstance(prompt, str) else prompt
     batch_size = len(prompt)
-    dtype = text_encoders[0].dtype
+
+    if hasattr(text_encoders[0], "module"):
+        dtype = text_encoders[0].module.dtype
+    else:
+        dtype = text_encoders[0].dtype
+
     device = device if device is not None else text_encoders[1].device
     pooled_prompt_embeds = _encode_prompt_with_clip(
         text_encoder=text_encoders[0],