Use gpu

app.py

@@ -52,6 +52,10 @@ class Instance:
 
         print("Loaded model")
 
+        if torch.cuda.is_available():
+            pipe.to("cuda")
+            print("Loaded model to GPU")
+
         # # 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()