Add option to keep model in VRAM instead of unloading it after each generation

I am running the FP16 version of Flux and the fp16 T5 text encoder on my RTX 2060 laptop with 32 GB RAM. I was surprised to see WebUI forge having faster speeds by multiple magnitudes compared to Comfy (11 minutes vs 2 minutes), so great job on the optimization here, @lllyasviel !

However, running it in FP16 is really tight on my RAM as well so loading parts of the model into VRAM takes quite a bit of time. When I press generation, moving models adds around 1 minute to the generation time.

So it would be really cool to have an option to turn this behavior off. Once loaded, the model should stay in VRAM until I close the program. This way there's be no moving models process between generations and it would speed up the experience up by a lot. Please consider it.

No files, tests, or entry points are named. Trace the model-loading and unloading flow around generation, then identify where a configurable keep-in-VRAM option would fit. Done means models remain in VRAM between generations when enabled and generation still works normally.

Written by the indexing model from the issue text.