<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
	<id>https://wiki.selur.net/index.php?action=history&amp;feed=atom&amp;title=Vapoursynth_RealESRGAN</id>
	<title>Vapoursynth RealESRGAN - Revision history</title>
	<link rel="self" type="application/atom+xml" href="https://wiki.selur.net/index.php?action=history&amp;feed=atom&amp;title=Vapoursynth_RealESRGAN"/>
	<link rel="alternate" type="text/html" href="https://wiki.selur.net/index.php?title=Vapoursynth_RealESRGAN&amp;action=history"/>
	<updated>2026-11-19T04:55:04Z</updated>
	<subtitle>Revision history for this page on the wiki</subtitle>
	<generator>MediaWiki 1.46.2</generator>
	<entry>
		<id>https://wiki.selur.net/index.php?title=Vapoursynth_RealESRGAN&amp;diff=591&amp;oldid=prev</id>
		<title>Selur: New filter page (via create-page on MediaWiki MCP Server)</title>
		<link rel="alternate" type="text/html" href="https://wiki.selur.net/index.php?title=Vapoursynth_RealESRGAN&amp;diff=591&amp;oldid=prev"/>
		<updated>2026-11-16T08:51:19Z</updated>

		<summary type="html">&lt;p&gt;New filter page (via create-page on MediaWiki MCP Server)&lt;/p&gt;
&lt;p&gt;&lt;b&gt;New page&lt;/b&gt;&lt;/p&gt;&lt;div&gt;&amp;lt;div style=&amp;quot;float:right; margin:0 0 1em 1em;&amp;quot;&amp;gt;__TOC__&amp;lt;/div&amp;gt;&lt;br /&gt;
&amp;#039;&amp;#039;&amp;#039;RealESRGAN&amp;#039;&amp;#039;&amp;#039; runs the non-upscaling community models of the vs-realesrgan package: line refinement, denoising of MPEG-2 HDTV and LD/DVD anime, and cleanup of modern anime rips. It runs on an NVIDIA GPU through PyTorch; the upscaling models are in [[Vapoursynth RealESRGAN Resize]].&lt;br /&gt;
&lt;br /&gt;
&amp;#039;&amp;#039;Filtering → Vapoursynth → Other&amp;#039;&amp;#039;&lt;br /&gt;
&lt;br /&gt;
[[File:Vapoursynth_RealESRGAN.png|none|RealESRGAN controls in Hybrid]]&lt;br /&gt;
&lt;br /&gt;
== What it does ==&lt;br /&gt;
Every frame is cleaned by a small Real-ESRGAN-style (compact) network trained on synthetic degradations. All models keep the frame size except &amp;#039;&amp;#039;DeNoise LDVD&amp;#039;&amp;#039;, which doubles it.&lt;br /&gt;
&lt;br /&gt;
== Requirements ==&lt;br /&gt;
* Windows, Hybrid&amp;#039;s torch add-on and an NVIDIA GPU with CUDA.&lt;br /&gt;
* Tensor RT additionally needs Torch-TensorRT from the add-on; it cannot be combined with TensorRT in vs-mlrt filters in the same script.&lt;br /&gt;
&lt;br /&gt;
== Settings ==&lt;br /&gt;
{| class=&amp;quot;wikitable&amp;quot;&lt;br /&gt;
! Control !! Parameter !! Range / values !! Hybrid default !! Meaning&lt;br /&gt;
|-&lt;br /&gt;
| Model || model || AniScale2 refiner, DeNoise Hi, DeNoise LDVD, Fix HD || AniScale2 refiner || AniScale2 refiner: light sharpening and line fixing/thinning. DeNoise Hi: MPEG-2 artifacts of Japanese HDTV. DeNoise LDVD: dot crawl, rainbows, halos and ringing of LD/DVD anime (2× output). Fix HD: light cleanup and sharpening of modern anime.&lt;br /&gt;
|-&lt;br /&gt;
| GPU ID || device_index || 0 – 4 || 0 || CUDA device.&lt;br /&gt;
|-&lt;br /&gt;
| Tile (x/y) || tile || 32 – 8192 || off, 256 / 256 || Splits the frame into tiles to save GPU memory.&lt;br /&gt;
|-&lt;br /&gt;
| Tile pad || tile_pad || 0 – 64 || 10 || Overlap of the tiles; only with tiling.&lt;br /&gt;
|-&lt;br /&gt;
| Streams || num_streams || 1 – 64 || 1 || Number of CUDA streams.&lt;br /&gt;
|-&lt;br /&gt;
| Batches || batch_size || 1 – 64 || 1 || Frames processed together.&lt;br /&gt;
|-&lt;br /&gt;
| Tensor RT || trt || on/off || off || Uses TensorRT; the engine is built on the first run and cached.&lt;br /&gt;
|-&lt;br /&gt;
| FP16 || – || on/off || off || Half precision (16-bit float clip), with and without Tensor RT.&lt;br /&gt;
|-&lt;br /&gt;
| max WSS || trt_workspace_size || 0 – 1073741824 || 0 || With Tensor RT: workspace size; 0 = not set.&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Example ==&lt;br /&gt;
Default settings on a 10-bit YUV 4:2:0 source (640x356):&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
# adjusting color space from YUV420P10 to RGBS for vsRealESRGANFilter&lt;br /&gt;
clip = core.resize.Bicubic(clip=clip, format=vs.RGBS, matrix_in_s=&amp;quot;470bg&amp;quot;, range_in_s=&amp;quot;limited&amp;quot;, range_s=&amp;quot;full&amp;quot;)&lt;br /&gt;
# using RealESRGANFilter&lt;br /&gt;
clip = RealESRGAN(clip, model=201, device_index=0)&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
== How Hybrid calls it ==&lt;br /&gt;
* The clip is converted to 32-bit float RGB (16-bit float with FP16) and padded to mod 4.&lt;br /&gt;
* Model and GPU ID are always written, and so is the tile pad while tiling is on; streams, batches and max WSS only when they differ from the defaults.&lt;br /&gt;
* With DeNoise LDVD Hybrid continues with the doubled frame size.&lt;br /&gt;
* With Tensor RT the engines are cached in the engine path from Hybrid&amp;#039;s path settings (or the temp folder); one engine per resolution.&lt;br /&gt;
* RealESRGAN also offers the [[Vapoursynth common filter options|common options]] (Masked, ApplyOnlyTo, Merge, OnRegion, Gimmick).&lt;br /&gt;
&lt;br /&gt;
== Background ==&lt;br /&gt;
=== Real-ESRGAN ===&lt;br /&gt;
Real-ESRGAN (Wang et al., ICCV workshops 2021) extends ESRGAN with a high-order degradation model, so it is trained on synthetic data that resembles real-world blur, noise and compression. The models offered here are community models built on its compact architecture.&lt;br /&gt;
&lt;br /&gt;
=== vs-realesrgan ===&lt;br /&gt;
HolyWu&amp;#039;s vs-realesrgan runs Real-ESRGAN and community models in VapourSynth with PyTorch, optionally with TensorRT. A 16-bit float clip runs the network in half precision, a 32-bit float clip in full precision.&lt;br /&gt;
&lt;br /&gt;
== Sources ==&lt;br /&gt;
* [https://github.com/HolyWu/vs-realesrgan vs-realesrgan]&lt;br /&gt;
* [https://github.com/xinntao/Real-ESRGAN Real-ESRGAN]&lt;br /&gt;
* Hybrid&amp;#039;s tooltips&lt;br /&gt;
&lt;br /&gt;
[[Category:Vapoursynth Filters]]&lt;/div&gt;</summary>
		<author><name>Selur</name></author>
	</entry>
</feed>