Search options (Page 1 of 16)

dawkinscm wrote:

Drakko01 wrote:

Exactly right, it kinda like the new 4.25_heavy, but reintroduce some artifacts the most models has for especific scene that 4.25 was fixed already, I hope see a combination of the two in the next model

Are you seeing any difference between the old v4.25_heavy and the new smaller one? Have you guys tried the new 4.25_heavy with SC disabled?

I only have the smaller 4.25?heavy 82.6MB, glad to look into the differences of the old  4.25h if you provide a link for download the file.

I like very much the smoothness of heavy version, most of the time , but with miss the interpolation in some scene at the point that can't used instead of 4.25. If this " errors" where fix maintaining the overall smoothness or fine a way to eliminate/minimize  I will be glad to use 4.25h as main.

I give you three examples that what i'm saying for you to test. Comments are appreciated.

Avengers at 1:53:23 after Hulk jumps of the 3° building

Avengers Endgame at 2:19:12 after Drax stab Cull Obsidian , and Pepper(Rescue Armor) fly across the screen

Spiderman No way home at 38:00 when spiderman drop hanging of the bridge after the car fell. And 38:20 after Doc OP take the nanotech and camera pans 360 around him.

Am not saying that 4.25 make this scenes perfect, but managed in a way much less disrupted.

Blackfyre wrote:

Having said that, artefact masking is not as good as the original 4.25 that was released as a beta.

I am glad that was released as a beta, because that older one still remains the best quality version IMO and better than 4.18 too.

Exactly right, it kinda like the new 4.25_heavy, but reintroduce some artifacts the most models has for especific scene that 4.25 was fixed already, I hope see a combination of the two in the next model

Blackfyre wrote:

rife_v4.25_heavy - 153 MB
Not sure if something needs to be updated for it to work properly.

Try these for heavy?

dawkinscm wrote:

Rife v2.5 lite is now available for anyone who is interested.

aka 4.25 lite

Chainik wrote:

BTW: if you just replace vsmlrt.py with the latest git, then it will use V1 models instead of V2

Yes, cause in december 2023 the dev updated the signature of the RIFE method:
https://gyazo.com/bde7edb2b4deb80294dbbaf71b757cc2
but he didn't add it as last element of the method so please fix it by updating helpers.py to send video_player True or False as 10th parameter:

return RIFE(clip,multi,1.0,None,None,None,model_num,backend,ensemble,False,implementation)
or
return RIFE(clip,multi,1.0,None,None,None,model_num,backend,ensemble,True,implementation)
(not sure which one is best for SVP)

Chainik wrote:

I'd say this's because of color space converted back and forth, noticeable in a very high contrast areas only.
Probably
...and your "shaking" is not like Blackfyre's V2 shaking, which is quite obvious not only on those lines but in a whole frame

Yes, i think you're right. I tried to simplify the base.py and generate.js and ended up with this:
https://gyazo.com/5f8efd7ead2c79d6a3afeaa852161184
but micro shaking still persists. Which confirms that it's caused by the color space conversion required for Vapoursynth.
Easiest way to fix it would be to allow Vaporsynth to also apply the same conversion process on the source frame too.
This way all outputed frames should line up and 100% fix the micro-shaking.
Is this possible? (even if it will increase the computational processing needed)

Blackfyre's V2 whole-frame obvious shaking takes priority, though.
Thanks again for putting the time and effort to look through the magnifying glass.

This below is basically the reason why the RTX 3090 outperforms the 4080 and 4080 Super with RIFE, someone can correct me if I am wrong:

The RTX 3090 boasts an additional 8GB of VRAM and features a broader 384-bit data bus, surpassing the 256-bit memory of the RTX 4080. Furthermore, its impressive 936.2 GB/s memory bandwidth is a 30.6% advantage over the RTX 4080’s 716.8 GB/s.

Whats the default align/valign values for SVP4 Pro? I forgot that I used 2x2 all the time, maybe thats why all models starting 4.16 looks fragmentary smooth!

Fragmentary smooth - when a small parts of one large object can be interpolated differently, even being a same large object! For example: faces, 4.4 to 4.16 faces looks buttery smooth, from 4.17 to 4.26 small parts like lips, cheeks, ears and other objects can be separated from the frame! There were cases when the lips moved apart alone, never happens for 4.4 to 4.16 before, also happens when the main object in the frame is interpolated correctly, but all the background moving both axis, looks like one step forward-two steps back frame!

The 4.26 new model is worse than 4.15 lite in Matrix rooftop 3 agents opening the doors, pattern errors on door textures, no door errors in 4.15v2 (both mod32 and mod64 input)!

Too noticeable door errors 4.4 (worst)
Less noticeable door errors 4.9 (okay)
No door errors 4.11 to 4.16 (perfect)

dawkinscm wrote:

Nope. Still crashes out. I've got the TRT error log and it says that broadcast dimensions must be comformable.

It seems 4.26 also crashes when the width or height of the resized video is not divisible by 64 with:
...
So we also need to change the code from "C:\Program Files (x86)\SVP 4\script\generate.js" from:

    var pw = Math.floor((media.dst_w-1)/32+1)*32 - media.dst_w;
    var ph = Math.floor((media.dst_h-1)/32+1)*32 - media.dst_h;

to

    var pw = Math.floor((media.dst_w-1)/64+1)*64 - media.dst_w;
    var ph = Math.floor((media.dst_h-1)/64+1)*64 - media.dst_h;

Attaching files that load both v1 and v2 correctly below.

dawkinscm wrote:

oriento wrote:

the onnx file is available now

Yep. But it does not work properly with SVP. It might look like it is working but the engine parse crashes. Looking at the new vsmlrt script there are a lot of changes and I'm not sure which ones are relevant. Especially since SVP moved some functionality into helpers.py.

i suppose you must change 32 into 64

multiple_frac = 32 / Fraction(scale)

the onnx file is available now