fix lora unscaling in diffusion pipelines

Author: eaidova

optimum/intel/openvino/modeling_diffusion.py

@@ -811,6 +811,9 @@ def forward(self, *args, **kwargs):
     def __call__(self, *args, **kwargs):
         return self.forward(*args, **kwargs)
 
+    def modules(self):
+        return {}
+
 
 class OVModelTextEncoder(OVPipelinePart):
     def forward(