Update auffusion_pipeline.py

auffusion_pipeline.py

@@ -469,17 +469,18 @@ class AuffusionPipeline(DiffusionPipeline):
         vocoder: Generator = None,
         requires_safety_checker: bool = False,        
         adapter_list: Optional[List[Callable]] = None,
-        tokenizer_model_max_length: Optional[int] = 77, # 77 is the default value for the CLIPTokenizer(and set for other models)
+        tokenizer_model_max_length: Optional[int] = 77,
     ):
         super().__init__()
-
+    
+        # Store list-based components and non-module fields as attributes
         self.text_encoder_list = text_encoder_list
         self.tokenizer_list = tokenizer_list
-        self.vocoder = vocoder
         self.adapter_list = adapter_list
+        self.vocoder = vocoder  # If it's a torch.nn.Module, you can still register it below
         self.tokenizer_model_max_length = tokenizer_model_max_length
-
-        # Register only actual modules (not lists)
+    
+        # Register torch modules only
         self.register_modules(
             vae=vae,
             unet=unet,
@@ -488,10 +489,19 @@ class AuffusionPipeline(DiffusionPipeline):
             feature_extractor=feature_extractor,
             vocoder=vocoder if vocoder is not None else None,
         )
-
+    
+        # Register config-only (non-module) components — avoids ValueError during .to()
+        self.register_to_config(
+            requires_safety_checker=requires_safety_checker,
+            text_encoder_list=text_encoder_list,
+            tokenizer_list=tokenizer_list,
+            adapter_list=adapter_list,
+            tokenizer_model_max_length=tokenizer_model_max_length,
+        )
+    
+        # Other logic
         self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
         self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
-        self.register_to_config(requires_safety_checker=requires_safety_checker)
 
 
     @classmethod