gpu

main.py

@@ -9,6 +9,7 @@ from fastapi.responses import StreamingResponse
 base = DiffusionPipeline.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
+
 base.to("cuda")
 # base.enable_model_cpu_offload()
 base.enable_attention_slicing()