Fix model offload bug when key isn't present (#5030)

* fix model offload bug when key isn't present

* make style

Author: DN6

src/diffusers/pipelines/pipeline_utils.py

@@ -1255,7 +1255,7 @@ def enable_model_cpu_offload(self, gpu_id: int = 0, device: Union[torch.device,
         self._all_hooks = []
         hook = None
         for model_str in self.model_cpu_offload_seq.split("->"):
-            model = all_model_components.pop(model_str)
+            model = all_model_components.pop(model_str, None)
             if not isinstance(model, torch.nn.Module):
                 continue