Update app.py

app.py

@@ -20,6 +20,10 @@ pipe = FLUXPipelineWithIntermediateOutputs.from_pretrained(
     "black-forest-labs/FLUX.1-schnell", torch_dtype=dtype
 ).to("cuda")
 pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=torch.float16).to("cuda")
+pipe.transformer.to(memory_format=torch.channels_last)
+pipe.transformer = torch.compile(
+    pipe.transformer, mode="max-autotune", fullgraph=True
+)
 torch.cuda.empty_cache()
 
 # Inference function