Can I inference Lenna with 24GB GPUs

[XuYunqiu]

Hi, thanks for sharing the code and model.

I get OOM issue when I use a 24GB GPU. May I ask how much memory does Lenna require in inference?
Is there any guide to dispatch Lenna on multiple GPUs or a quantization solution?

[YizhuoQ]

I got the same issue on RTX 3090. Have you solve this question?