Update app.py

app.py

@@ -14,22 +14,23 @@ auth_token=os.environ["ACCESS_TOKEN"]
 
 scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler", use_auth_token=auth_token)
 
-pipe_merged = StableDiffusionXLPipeline.from_pretrained(
+pipe = StableDiffusionXLPipeline.from_pretrained(
   model_id,
   torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
   scheduler=scheduler, use_auth_token=auth_token)
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
 
-pipe_i2i_merged = StableDiffusionXLImg2ImgPipeline.from_pretrained(
+pipe_i2i = StableDiffusionXLImg2ImgPipeline.from_pretrained(
   model_id,
   torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
   scheduler=scheduler,
   use_auth_token=auth_token
 )
 
-pipe=pipe_merged.to("cuda")
-pipe_i2i=pipe_i2i_merged.to("cuda")
-pipe.enable_xformers_memory_efficient_attention()
-pipe_i2i.enable_xformers_memory_efficient_attention()
+pipe=pipe.to("cuda")
+pipe.enable_model_cpu_offload()
+pipe_i2i=pipe_i2i.to("cuda")
+
 
 def error_str(error, title="Error"):
     return f"""#### {title}
@@ -160,7 +161,7 @@ with gr.Blocks(css=css) as demo:
           with gr.Group():
               
               with gr.Row():
-                prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="[your prompt]").style(container=False)
+                prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="[your prompt]")
                 generate = gr.Button(value="Generate")
 
               image_out = gr.Image(height=1024,width=1024)