Every few months I see new mind blowing NeRF results, but I wonder if there is a usable project that I could try it myself. Be it open source project, or commercial product.

Also I'm not quite sure what time scales are we talking about, with turning bunch of images to nerf model, and then using that model to generate novel views.. hours on powerful gpu? minutes on cpu?

Trains a nerf in a couple of seconds.

I went on a trip to Italy last year and took a video while walking around Michelangelo’s David. Even with that relatively poor image quality this let me turn it into a pretty high quality nerf.