Welcome to Doom9's Forum, THE in-place to be for everyone interested in DVD conversion. Before you start posting please read the forum rules. By posting to this forum you agree to abide by the rules. |
27th February 2023, 15:39 | #42 | Link | ||
Registered User
Join Date: Mar 2012
Location: Texas
Posts: 1,666
|
Quote:
Quote:
Training a model on Oyster does sound interesting. I read that Zarxrax used avs filters to train some of his models. Done. Last edited by Reel.Deel; 27th February 2023 at 16:12. |
||
27th February 2023, 16:14 | #43 | Link |
Registered User
Join Date: Nov 2009
Posts: 2,361
|
The same image from the linked post, 472x400 pixels. I will try the tiling option. I mean my GPU is not THAT bad : ) TBH I'm waiting for an affordable +10Gb card, be it this gen or the next one, the xx70 sitting on 8Gb for 8 years is as ridiculous as the current prices.
__________________
i7-4790K@Stock::GTX 1070] AviSynth+ filters and mods on GitHub + Discussion thread |
27th February 2023, 17:04 | #44 | Link | ||
Registered User
Join Date: Sep 2007
Posts: 5,377
|
Quote:
Quote:
chaiNNer is free. Reel.Deel posted instructions how to convert earlier. https://github.com/chaiNNer-org/chaiNNer/releases |
||
27th February 2023, 17:17 | #45 | Link |
Registered User
Join Date: Mar 2012
Location: Texas
Posts: 1,666
|
It's very easy to convert also. Load the required nodes, connect them and then hit run by either pressing the play button at the top or F5. Just make sure you've installed the dependencies.
Side note for Win7 users like me. Alpha v0.17.1 is the last version that works and you have to place the api-ms-win-core-path-l1-1-0.dll in the Python folder which appears after the first time starting the program. |
27th February 2023, 21:33 | #46 | Link | |
Registered User
Join Date: Dec 2005
Location: Sweden
Posts: 703
|
Thanks Reel.Deel!
Quote:
|
|
9th March 2023, 10:58 | #47 | Link |
Registered User
Join Date: Jul 2018
Posts: 1,070
|
Finally iterative solution for chicken and egg problem in motion compensating denoising - https://forum.doom9.org/showthread.p...52#post1984152
Now I think if it possible to replace either MAnalyse or MDegrain in that solution with some neural network processing from existing but keeping the iterative idea of checking each generation result with non-distorted input source. In each iteration the algorithm refines both denoised clip and MVs field. But there is no current NN plugins capable of return MVs field in compatible with mvtools format ? May be instead of MDegrain create an interleaved clip with MCompensated frames from input MVclip for each iteration and pass it to RIFE denoise ? Last edited by DTL; 9th March 2023 at 11:02. |
18th March 2023, 20:53 | #48 | Link | ||
Registered User
Join Date: Mar 2012
Location: Texas
Posts: 1,666
|
I'll respond here to not hijack Selur's thead.
Quote:
Quote:
I have not tried many models but all of Zarxrax's models work fine and also 1x_SwatKatsLite_360000_G. Edit: It works now due to something very odd, this is my script: Code:
FFVideoSource("HT1-1-RainbowsSample.m2v") # NTSC DVD TFM(PP=0) TDecimate() ConvertToPlanarRGB() o = last ConvertBits(32) mlrt_ncnn(network_path="...\2x_AnimeClassics_UltraLite_510K.onnx", builtin=false, tilesize_w=width/4, tilesize_h=height/4, overlap_w=8, overlap_h=8) ConvertBits(8) #Interleave(o,last) Last edited by Reel.Deel; 18th March 2023 at 21:04. |
||
19th March 2023, 06:09 | #49 | Link | |
Registered User
Join Date: Jul 2018
Posts: 450
|
Quote:
|
|
19th March 2023, 17:25 | #52 | Link | ||
Registered User
Join Date: Sep 2007
Posts: 5,377
|
Quote:
Just with a "normal" script ? Code:
a=colorbars() b=a.bicubicresize(a.width*2, a.height*2) interleave(a,b) Quote:
|
||
19th March 2023, 17:38 | #53 | Link |
Registered User
Join Date: Mar 2012
Location: Texas
Posts: 1,666
|
With a "normal" script it works fine. But when avs-mlrt is involved and the interleaved videos are different dimensions, it causes VDub2 to hang. At least for me. Can you try this script:
Code:
ColorBars(pixel_type="RGBPS") o = last mlrt_ncnn("2x_AnimeClassics_UltraLite_510K.onnx", builtin=false) Interleave(o,last) ConvertBits(8) Last edited by Reel.Deel; 19th March 2023 at 17:40. |
19th March 2023, 17:45 | #54 | Link | |
Registered User
Join Date: Sep 2007
Posts: 5,377
|
Quote:
I get the "Interleave: videos must be of the same size. " message in avspmod; but vdub2 hangs |
|
20th March 2023, 02:38 | #57 | Link | |
Registered User
Join Date: Sep 2007
Posts: 5,377
|
Quote:
Other common "culprits" for some people's silent fails were non meeting the avs+ minimum version, and GPU memory (use tiles) . Neither current produces a useful error message, which could be an improvement |
|
26th March 2023, 00:37 | #59 | Link |
Registered User
Join Date: Nov 2009
Posts: 2,361
|
I found new interesting models, not sure how feasible is it to convert to onnx, compatibility-wise:
Code:
Photos: Real ESRGAN 4x Plus Real ESRGAN General WDN 4x V3 (photos, paintings or anime illustrations) Latent Diffusion Super Resolution (LDSR) (SUPER slow though) SwinIR Swin2SR Remacri Anime/LineArt Illustration Upscale: Real ESRGAN 4x Plus Anime6B
__________________
i7-4790K@Stock::GTX 1070] AviSynth+ filters and mods on GitHub + Discussion thread Last edited by Dogway; 26th March 2023 at 15:26. |
27th March 2023, 00:14 | #60 | Link | ||
Registered User
Join Date: Mar 2012
Location: Texas
Posts: 1,666
|
Quote:
I did not test them, but so far these models convert to to onnx without any problems:
With the Swin2SR models I get an error when trying to covert: Quote:
|
||
|
|