cch9897

This may CUDA limit? and RAM to GPU need through CPU and PCIE , it may be very slow. but its not a bad idea, we need someone to try...

There are other ways to reduce VRAM usage, such as using [Tiled Diffusion/Tiled VAE](https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111).