Update app.py

app.py

@@ -85,7 +85,7 @@ def inference(prompt,canny_image,number,seed ):
     pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
     # 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()
+    #pipe.enable_model_cpu_offload()
     # xformers
     pipe.enable_xformers_memory_efficient_attention()
     # Generator seed,