Update app.py

app.py

@@ -9,7 +9,7 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 
 if torch.cuda.is_available():
     torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("sd-community/sdxl-flash", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
+    pipe = DiffusionPipeline.from_pretrained("sd-community/sdxl-flash", torch_dtype=torch.float16, use_safetensors=True)
     pipe.enable_xformers_memory_efficient_attention()
     pipe = pipe.to(device)
 else: