Update app.py

app.py

@@ -26,12 +26,12 @@ os.environ["TRANSFORMERS_CACHE"] = cache_path
 os.environ["HF_HUB_CACHE"] = cache_path
 os.environ["HF_HOME"] = cache_path
 
-torch.set_float32_matmul_precision("high")
+torch.set_float32_matmul_precision("medium")
 
-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 = False
+#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 = False
 
 # Load LoRAs from JSON file
 with open('loras.json', 'r') as f:
@@ -71,10 +71,10 @@ pipe.text_encoder.dtype = torch.bfloat16
 pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to("cuda")
 
 
-pipe.transformer.to(memory_format=torch.channels_last)
+#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=False)
+#pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=False)
 #pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=False)
 
 MAX_SEED = 2**32-1