Want to deploy VQGAN+CLIP on GPU, having atleast 16GB RAM

Hi there, hope you are fine.

I want to have a permanent(24/7) API, that can host my model with at least 16 GB RAM. I want to ask for pricing, and how much time it would take to develop such solution.

Thanks for any help

cc @jeffboudier can help on this

Thanks for reaching out! I sent you an email with the process to upgrade a Space on GPU.