Update app.py

Adding pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
To test speed.

app.py

@@ -11,15 +11,19 @@ if torch.cuda.is_available():
     pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
     pipe.enable_xformers_memory_efficient_attention()
     pipe = pipe.to(device)
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
     torch.cuda.empty_cache()
     refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16")
     refiner.enable_xformers_memory_efficient_attention()
     refiner.enable_sequential_cpu_offload()
+    refiner.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
 else: 
     pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", use_safetensors=True)
     pipe = pipe.to(device)
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
     refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True)
     refiner = refiner.to(device)
+    refiner.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
 
 n_steps = 40
 high_noise_frac = 0.8