Update app.py

app.py

@@ -23,8 +23,11 @@ pipeline = DiffusionPipeline.from_pretrained(
     use_auth_token=HUGGINGFACE_TOKEN
 )
 pipeline.load_lora_weights(lora_weights_path)
-#pipeline.enable_sequential_cpu_offload()  # Efficient memory usage
-#pipeline.enable_xformers_memory_efficient_attention()  # Enable xformers memory efficient attention
+
+if device == "cuda":
+    pipeline.enable_sequential_cpu_offload()  # Efficient memory usage
+    pipeline.enable_xformers_memory_efficient_attention()  # Enable xformers memory efficient attention
+
 pipeline = pipeline.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max
@@ -138,17 +141,13 @@ with gr.Blocks(css=css) as demo:
                     value=30,
                 )
         
-        gr.Examples(
-            examples=examples,
-            inputs=[prompt],
-            fn=infer, 
-            outputs=[result]
-        )
-
+        for example in examples:
+            gr.Button(example).click(lambda e=example: prompt.set_value(e))
+    
     run_button.click(
         fn=infer,
         inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
         outputs=[result]
     )
 
-demo.queue().launch(share=True)
+demo.queue().launch()