Search options (Page 45 of 354)

must work... what's in the log?

dlr5668
I solved freezing. You will need to disable black bar detection

nope, this would be too easy...
it just hangs at random times. with black bars detection the chances are higher just because two script initializations instead of one.

I thought you want _faster_, not _better_...

check if SVP 4\utils\clinfo.exe runs successfully, or crashes too
in the latter case clean graphics drivers (via Display Driver Uninstaller) and reinstall them

внезапно, оно именно так и работает
Видеотрансляция -> Web UI
с телефона можно открывать https://www.svp-team.com/cast, оно редиректит на адрес в локалке

> What then does scale=2

the opposite? upscale before, downscale after

if I understand it correctly, scale=0.5 just downscales the whole frame before the "AI" magic, then upscales the result back --> you just get lower resolution intermediate frames
this is why it's "cheating"

> How can I do that ?

switch via profiles menu in runtime

> what really is NVIDIA Optical Flow

NVIDIA's own GPU-only motion estimation algorithm producing motion vectors field for a given two images

> what benefits it would bring

move the most CPU-consuming part of me/mc algorithm to GPU

try this (replace files in SVP 4/plugins)

пока что порядка 10 мин можно на халяву смотреть

fp16 vs. fp32 --> 64 fps vs. 53 fps (704*528 video); 31 fps vs. 28 fps (720p)

upgrade from ver. 1.0.0 (https://www.svp-team.com/forum/viewtopi … 023#p79023)

> python -m pip install --upgrade vsrife

replace SVP 4\script\base.py with the one attached

from SVP's "RIFE AI engine" video profile:
- "Test-Time Augmentation": Enabled - use Pytorch version, Disabled - use Vulkan version
- "AI model": does nothing with Pytorch version; generic/anime model in Vulkan version
- "Math precision": precision in both versions
- "GPU threads": Pytorch: 2 = "scale=1.0", >=4 = "scale=0.5"; Vulkan - GPU threads
- "GPU device": GPU device in both versions