disable cpu offload and xformers

app.py

@@ -52,12 +52,12 @@ class Instance:
 
         print("Loaded model")
 
-        # This command loads the individual model components on GPU on-demand. So, we don't
-        # need to explicitly call pipe.to("cuda").
-        pipe.enable_model_cpu_offload()
+        # # This command loads the individual model components on GPU on-demand. So, we don't
+        # # need to explicitly call pipe.to("cuda").
+        # pipe.enable_model_cpu_offload()
 
-        # xformers
-        pipe.enable_xformers_memory_efficient_attention()
+        # # xformers
+        # pipe.enable_xformers_memory_efficient_attention()
         return pipe
 
 instance = Instance()