Stable WarpFusion v0.5.14-nightly - raft\flow fixes (Patreon)

(for the ones not afraid of bugs :D)

Hi there! Would be awesome if you could help me test those new tweaks before rolling them to the general public.

The changes include:

- replace RAFT install with a precompiled model
- add flow_lq switch for flow generation
- add preview flow images
- add reverse consistency checking mode
- clean up text descriptions
- remove forward flow maps after consistency checking

Getting rid of that malevolent RAFT install process.

I've converted it to a jit-traced model, and now it's being downloaded from my repo without installing anything for it. Seems to work like a charm on colab, needs testing locally.
Compiled with pytorch v1.12.*, but works for v1.11.*, lower version needs to be tested, but it's not that hard to recompile with a lower pytorch version for compatibility if needed.

Add flow_lq option 

This switches between half and full-precision models. The half one uses 50% less memory, thus letting you use 2x larger images.
This comes at some quality cost, of course, but you can now eyeball the difference and check if it's causing any trouble because you will know where the affected areas are located in the actual frame.

flow_save_img_preview

This saves flow maps as images along with the motion vectors. Not very informative to the human eye, but you can compare quality and investigate the final result artifacts' sources easier now.

add reverse_cc_order

A test feature, allow calculating consistency maps in reverse. Testing it now, not sure it'll help, but still worth testing. reverse_cc_order=True is the default value that replicates older notebooks

remove forward flow maps after consistency checking

Those maps aren't used after consistency checking, so it makes sense to remove those.

Please leave your feedback and video results on our discord-nightly channel -  https://discord.gg/gxXBu6D2