use 4 bit if possible

app.py

@@ -16,9 +16,14 @@ from my_utils.default_values import apply_defaults
 
 import argparse
 
-precision = get_precision()
-transformer = NunchakuFluxTransformer2dModel.from_pretrained(f"nunchaku-tech/nunchaku-flux.1-schnell/svdq-{precision}_r32-flux.1-schnell.safetensors")
-pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", transformer=transformer, torch_dtype=torch.bfloat16).to("cuda")
+try:
+    precision = get_precision()
+    transformer = NunchakuFluxTransformer2dModel.from_pretrained(f"nunchaku-tech/nunchaku-flux.1-schnell/svdq-{precision}_r32-flux.1-schnell.safetensors")
+    pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", transformer=transformer, torch_dtype=torch.bfloat16).to("cuda")
+except Exception as e:
+    print(f"Error loading quantized FluxPipeline: {e}")
+    pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16).to("cuda")
+
 pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=torch.bfloat16).to("cuda")
 
 m_clip = CLIPModel.from_pretrained("multimodalart/clip-vit-base-patch32").to("cuda")