Update app.py

app.py

@@ -42,7 +42,7 @@ pipe.unload_lora_weights()
 
 # Memory optimizations
 pipe.transformer.to(memory_format=torch.channels_last)
-pipe.enable_attention_slicing()
+pipe.enable_xformers_memory_efficient_attention()
 
 # CUDA Graph setup
 static_inputs = None
@@ -159,7 +159,7 @@ with gr.Blocks() as demo:
         gr.Markdown("<span style='color: red;'>Note: Sometimes it stucks or stops generating images (I don't know why). In that situation just refresh the site.</span>")
 
         with gr.Row():
-            with gr.Column(scale=2.5):
+            with gr.Column(scale=2): # Changed scale to 2
                 result = gr.Image(label="Generated Image", show_label=False, interactive=False)
             with gr.Column(scale=1):
                 prompt = gr.Text(
@@ -192,7 +192,8 @@ with gr.Blocks() as demo:
                 fn=generate_image,
                 inputs=[prompt],
                 outputs=[result, seed, latency],
-                cache_examples="lazy" 
+                cache_examples=True, # Changed cache_examples
+                cache_mode="lazy" # Added cache_mode
             )
 
     enhanceBtn.click(
@@ -252,4 +253,4 @@ with gr.Blocks() as demo:
         )
 
 # Launch the app
-demo.queue(max_size=5, concurrency_count=1).launch()
+demo.queue(max_size=5).launch() # Removed concurrency_count