Update app.py

app.py

@@ -12,10 +12,10 @@ device = 'cuda' if torch.cuda.is_available() else 'cpu'
 torch.cuda.max_memory_allocated(device=device)
 torch.cuda.empty_cache()
 torch.cuda.max_memory_allocated(device=device)
-pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium", torch_dtype=torch.bfloat16).to(device)
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium", torch_dtype=torch.float16).to(device)
 #pipe.enable_xformers_memory_efficient_attention()
 torch.cuda.empty_cache()
-pipe.enable_model_cpu_offload()
+#pipe.enable_model_cpu_offload()
 #torch.cuda.max_memory_allocated(device=device)
 #refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16").to(device)
 #refiner.enable_xformers_memory_efficient_attention()