Update app.py

app.py

@@ -28,6 +28,11 @@ os.environ["HF_HOME"] = cache_path
 
 torch.set_float32_matmul_precision("high")
 
+torch._inductor.config.conv_1x1_as_mm = True
+torch._inductor.config.coordinate_descent_tuning = True
+torch._inductor.config.epilogue_fusion = False
+torch._inductor.config.coordinate_descent_check_all_directions = True
+
 # Load LoRAs from JSON file
 with open('loras.json', 'r') as f:
     loras = json.load(f)
@@ -64,6 +69,12 @@ pipe.text_encoder = clip_model.text_model
 pipe.tokenizer_max_length = maxtokens
 pipe.text_encoder.dtype = torch.bfloat16
 
+pipe.transformer.to(memory_format=torch.channels_last)
+pipe.vae.to(memory_format=torch.channels_last)
+
+pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=True)
+pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)
+
 MAX_SEED = 2**32-1
 
 class calculateDuration: