(intended to be ultrafast) most of these listed below are realtime or faster, and utilized native legacy hardware.
Intended to make improvements, cleanup, and prepare video.
(they really do compete or outperform AI in many business requirements).
Pre-Process with Waifu2x Anime4k SHADERS .
I get up to 140fps on Legacy AMD 580. New hardware, I will Stack 5 shaders and it still Upscales most video in 1/15x the time it takes to make popcorn.
Apply 3dLUT, HDR, or Gamma Profiles, ProRes BT709 for example. (usually zero process time)
Ravu, NNEDI, DoG, FSRCNN AMD Fidelity Shader or NVIDIA DD (if not proprietary) .dll found easily I did not see anything about license restriction.
Ghost Reduction, Motion Blur Reduction, High Motion Pre-Filters, (yes that is what FlowFrames is for but
it preventsSILKING)
De-Interlace, Denoise, OR x264 nr=400, OR preset Spatial And Temporal (2:2:6:6, 1:1:8:8) , sidenote: (NLMeans=HighMotion is far too slow).
RAW LossLess Export: I'll StaxRip this later... Here: https://github.com/staxrip/staxrip
(Cuts down on the apps need to encode at all). Advanced users will use their own methods anyway. AVSynth, Handbrake, etc...
Please have a look at the App and its Features. Basically there are a plethora export options and Features you might like.
Reason for Request:
I will Pre-Process (AVsynth, FF, Shaders), then use FlowFrame or some NN, then I must Post-Process again (StaxRip).
--> This is a waste.
The reason for this effort is to, improve slightly, then play, without the need for huge processing time or resources.
Example: My netflix series that I Cached pre-flight. Abismal quality that I pay for; So I will enhance, clean, 10-bit encode, and Export.
Now I have smaller files with Satisfactory higher quality, that are: color coded, 1440 60p episodes.
It should Not Take, 1hr per minute or 1.5fps with AI. This is a tragedy for a mere 3090 aficionado.
(hopefully in the future a satisfactory RipUP should take .5x the runtime on an ARM archyPI.)
List of Shaders I use:
glsl Shaders
Anime4K_Clamp_Highlights.glsl;
Anime4K_Restore_CNN_VL.glsl;
Anime4K_Upscale_CNN_x2_UL.gls
/Anime4K_AutoDownscalePre_x4.glsl;
Anime4K_Upscale_CNN_x2_S.glsl
Anime4K_Thin_VeryFast.glsl;
Anime4K_Thin_HQ.glsl
FSRCNN_x2_r2_32-0-
Anime4K_Denoise_Bilateral_Median.gls
Anime4K_Upscale_DTD
Anime4K_Upscale_Denoise_CNN_x2_UL.gls
Anime4K_Deblur_DoG
Anime4K_Deblur_DoG_X2.glsl
FSRCNNX_x2_8-0-4-1_LineArt.gls
nnedi3-nns256-win8x6.hoo
RAVU-lite-ar-r4.hook
nnedi3-nns256-win8x4.hook
ravu-lite-r4.hook;
FSRAMD-FidelityFX-Super-Reso-v1-mpv.glsl;
Pre-Process Features:
(intended to be ultrafast) most of these listed below are realtime or faster, and utilized native legacy hardware. Intended to make improvements, cleanup, and prepare video.
(they really do compete or outperform AI in many business requirements).
I get up to 140fps on Legacy AMD 580. New hardware, I will Stack 5 shaders and it still Upscales most video in 1/15x the time it takes to make popcorn.
Reason for Request:
I will Pre-Process (AVsynth, FF, Shaders), then use FlowFrame or some NN, then I must Post-Process again (StaxRip). --> This is a waste.
The reason for this effort is to, improve slightly, then play, without the need for huge processing time or resources.
Example: My netflix series that I Cached pre-flight. Abismal quality that I pay for; So I will enhance, clean, 10-bit encode, and Export.
Now I have smaller files with Satisfactory higher quality, that are: color coded, 1440 60p episodes. It should Not Take, 1hr per minute or 1.5fps with AI. This is a tragedy for a mere 3090 aficionado. (hopefully in the future a satisfactory RipUP should take .5x the runtime on an ARM archyPI.)
List of Shaders I use: glsl Shaders Anime4K_Clamp_Highlights.glsl; Anime4K_Restore_CNN_VL.glsl; Anime4K_Upscale_CNN_x2_UL.gls /Anime4K_AutoDownscalePre_x4.glsl; Anime4K_Upscale_CNN_x2_S.glsl Anime4K_Thin_VeryFast.glsl; Anime4K_Thin_HQ.glsl FSRCNN_x2_r2_32-0- Anime4K_Denoise_Bilateral_Median.gls Anime4K_Upscale_DTD Anime4K_Upscale_Denoise_CNN_x2_UL.gls Anime4K_Deblur_DoG Anime4K_Deblur_DoG_X2.glsl FSRCNNX_x2_8-0-4-1_LineArt.gls nnedi3-nns256-win8x6.hoo RAVU-lite-ar-r4.hook nnedi3-nns256-win8x4.hook ravu-lite-r4.hook; FSRAMD-FidelityFX-Super-Reso-v1-mpv.glsl;