<?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_RIFE_%28mlrt%29</id>
	<title>Vapoursynth RIFE (mlrt) - 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_RIFE_%28mlrt%29"/>
	<link rel="alternate" type="text/html" href="https://wiki.selur.net/index.php?title=Vapoursynth_RIFE_(mlrt)&amp;action=history"/>
	<updated>2026-11-19T05:14:38Z</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_RIFE_(mlrt)&amp;diff=601&amp;oldid=prev</id>
		<title>Selur: Update to current Hybrid behaviour; code as &lt;pre&gt; (via update-page on MediaWiki MCP Server)</title>
		<link rel="alternate" type="text/html" href="https://wiki.selur.net/index.php?title=Vapoursynth_RIFE_(mlrt)&amp;diff=601&amp;oldid=prev"/>
		<updated>2026-11-16T08:51:44Z</updated>

		<summary type="html">&lt;p&gt;Update to current Hybrid behaviour; code as &amp;lt;pre&amp;gt; (via update-page on MediaWiki MCP Server)&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw-interface=&quot;&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;en&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Older revision&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Revision as of 09:51, 16 November 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l36&quot;&gt;Line 36:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 36:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| Device ID || device_id || 0 – 16 || 0 || GPU to use; not for CPU and CoreML backends.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| Device ID || device_id || 0 – 16 || 0 || GPU to use; not for CPU and CoreML backends.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| Streams || num_streams || 1 – 16 || 1 || Parallel streams; &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;used by &lt;/del&gt;TensorRT, TensorRT RTX, OpenVINO (GPU), NCNN and CoreML.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| Streams || num_streams || 1 – 16 || 1 || Parallel streams; &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;enabled only for the backends that use it (&lt;/ins&gt;TensorRT, TensorRT RTX, OpenVINO (GPU), NCNN and CoreML&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;)&lt;/ins&gt;.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| CUDA Graphs || use_cuda_graph || on/off || off || TensorRT, TensorRT RTX and ONNX (CUDA) only.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| CUDA Graphs || use_cuda_graph || on/off || off || TensorRT, TensorRT RTX and ONNX (CUDA) only.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l55&quot;&gt;Line 55:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 55:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Example ==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Example ==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Default settings on a 10-bit YUV 4:2:0 source (640x356, 25 fps), interpolated to 50 fps:&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Default settings on a 10-bit YUV 4:2:0 source (640x356, 25 fps), interpolated to 50 fps:&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;syntaxhighlight lang=&quot;python&quot;&lt;/del&gt;&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;pre&lt;/ins&gt;&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;clip = misc.SCDetect(clip=clip, threshold=0.100, tools={&amp;#039;scd&amp;#039;: &amp;#039;scd&amp;#039;})&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;clip = misc.SCDetect(clip=clip, threshold=0.100, tools={&amp;#039;scd&amp;#039;: &amp;#039;scd&amp;#039;})&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;clip = core.std.AddBorders(clip=clip, left=0, right=0, top=14, bottom=14) # add borders to achieve mod 32 (vsRIFEmlrt) - 640x384&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;clip = core.std.AddBorders(clip=clip, left=0, right=0, top=14, bottom=14) # add borders to achieve mod 32 (vsRIFEmlrt) - 640x384&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l64&quot;&gt;Line 64:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 64:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;clip = vsmlrt.RIFE(clip, model=44, multi=Fraction(2, 1), backend=Backend.OV_CPU(fp16=False,bf16=False))&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;clip = vsmlrt.RIFE(clip, model=44, multi=Fraction(2, 1), backend=Backend.OV_CPU(fp16=False,bf16=False))&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;clip = core.std.Crop(clip=clip, left=0, right=0, top=14, bottom=14) # removing added borders from mod requirement (vsRIFEmlrt) -  640x356&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;clip = core.std.Crop(clip=clip, left=0, right=0, top=14, bottom=14) # removing added borders from mod requirement (vsRIFEmlrt) -  640x356&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;/&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;syntaxhighlight&lt;/del&gt;&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;/&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;pre&lt;/ins&gt;&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== How Hybrid calls it ==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== How Hybrid calls it ==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* The clip is converted to 32-bit float RGB (16-bit with FP16) and padded to the size the model and scale require; the padding is removed afterwards.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* The clip is converted to 32-bit float RGB (16-bit with FP16) and padded to the size the model and scale require; the padding is removed afterwards.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* Factor and FPS are both turned into one exact multiplier; in FPS mode it is target rate &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;/ input &lt;/del&gt;rate. If the multiplier is not above 1, the filter is skipped with a note in the script and the frame rate stays.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* Factor and FPS are both turned into one exact multiplier; in FPS mode it is &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;the &lt;/ins&gt;target rate &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;divided by the frame &lt;/ins&gt;rate &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Hybrid tracks for the clip, so FPS mode also works for variable frame rate sources&lt;/ins&gt;. If the multiplier is not above 1, the filter is skipped with a note in the script and the frame rate stays.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* With scene detection Hybrid runs the detection itself before RIFE (RGB clips are converted to 16-bit YUV 4:4:4 for it); manual scene changes mark the listed frames instead.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* With scene detection Hybrid runs the detection itself before RIFE (RGB clips are converted to 16-bit YUV 4:4:4 for it); manual scene changes mark the listed frames instead.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* The model and the backend are always written; scale only when it is not 1.0, ensemble only when ticked.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* The model and the backend are always written; scale only when it is not 1.0, ensemble only when ticked.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Selur</name></author>
	</entry>
	<entry>
		<id>https://wiki.selur.net/index.php?title=Vapoursynth_RIFE_(mlrt)&amp;diff=417&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_RIFE_(mlrt)&amp;diff=417&amp;oldid=prev"/>
		<updated>2026-11-15T07:57:52Z</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;RIFE (mlrt)&amp;#039;&amp;#039;&amp;#039; runs the RIFE frame interpolation network as an ONNX model through vs-mlrt. Depending on the backend it works on the CPU or on NVIDIA, Intel and AMD hardware.&lt;br /&gt;
&lt;br /&gt;
&amp;#039;&amp;#039;Filtering → Vapoursynth → Frame → Interpolation&amp;#039;&amp;#039;&lt;br /&gt;
&lt;br /&gt;
[[File:Vapoursynth_RIFEmlrt.png|none|RIFE (mlrt) controls in Hybrid]]&lt;br /&gt;
&lt;br /&gt;
== What it does ==&lt;br /&gt;
RIFE estimates the optical flow between two frames and synthesizes the frames in between. An integer multiplier interleaves new frames; a fractional multiplier places the new frames at the exact time points. Frames marked as the last frame before a cut are duplicated instead of interpolated.&lt;br /&gt;
&lt;br /&gt;
== Requirements ==&lt;br /&gt;
* Hybrid&amp;#039;s vs-mlrt add-on with the RIFE models; without them the method is not offered.&lt;br /&gt;
* GPU backends: TensorRT and ONNX (CUDA) for NVIDIA, OpenVINO (GPU) for Intel, NCNN for Vulkan GPUs, DML for DirectX 12 GPUs; on macOS ONNX (CoreML) or CPU.&lt;br /&gt;
&lt;br /&gt;
== Settings ==&lt;br /&gt;
Tick &amp;#039;&amp;#039;&amp;#039;Frame Interpolation&amp;#039;&amp;#039;&amp;#039; and pick &amp;#039;&amp;#039;RIFEmlrt&amp;#039;&amp;#039; in the method list.&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;
| Factor/FPS || – || on/off || on || On: multiple of the input rate; off: absolute target rate.&lt;br /&gt;
|-&lt;br /&gt;
| Factor (num/den) || multi || 1 – 120000 || 2/1 || Multiple of the input rate.&lt;br /&gt;
|-&lt;br /&gt;
| FPS (num/den) || multi || 1 – 120000 || 2/1 || Target frame rate; the default of 2 fps must be changed before this mode does anything.&lt;br /&gt;
|-&lt;br /&gt;
| Model || model || 4.0, 4.2 – 4.26_heavy (incl. _lite/_heavy) || 4.4 || RIFE model version.&lt;br /&gt;
|-&lt;br /&gt;
| Ensemble || ensemble || on/off || off || Ensemble variant of the model (slower). Not for 4.21–4.23 and 4.25 or newer.&lt;br /&gt;
|-&lt;br /&gt;
| Scale || scale || 0.25, 0.5, 1.0, 2.0, 4.0 || 1.0 || Resolution of the flow estimation (0.5 suits 4K); only for models 4.0–4.6 without ensemble.&lt;br /&gt;
|-&lt;br /&gt;
| Backend || backend || OpenVINO (CPU/GPU), ONNX (CPU/CUDA), DML, TensorRT, TensorRT RTX, NCNN (macOS: ONNX CoreML/CPU) || OpenVINO (CPU); macOS ONNX (CoreML) || Runtime that executes the network.&lt;br /&gt;
|-&lt;br /&gt;
| FP16 / BF16 || fp16, bf16 || on/off || off / off || Half precision; the two exclude each other and are disabled for OpenVINO.&lt;br /&gt;
|-&lt;br /&gt;
| Device ID || device_id || 0 – 16 || 0 || GPU to use; not for CPU and CoreML backends.&lt;br /&gt;
|-&lt;br /&gt;
| Streams || num_streams || 1 – 16 || 1 || Parallel streams; used by TensorRT, TensorRT RTX, OpenVINO (GPU), NCNN and CoreML.&lt;br /&gt;
|-&lt;br /&gt;
| CUDA Graphs || use_cuda_graph || on/off || off || TensorRT, TensorRT RTX and ONNX (CUDA) only.&lt;br /&gt;
|-&lt;br /&gt;
| TRT backend optimization || builder_optimization_level || 0 – 5 || 3 || TensorRT engine build effort.&lt;br /&gt;
|-&lt;br /&gt;
| Implementation || _implementation || 1, 2 || 1 || vs-mlrt&amp;#039;s alternative ONNX implementation 2 (experimental, TensorRT); used only when its model file exists and scale is 1.&lt;br /&gt;
|-&lt;br /&gt;
| Dynamic Shapes (min/opt/max) || min_shapes, opt_shapes, max_shapes || sizes || unset || TensorRT engine sizes; with a minimum size the engine becomes dynamic.&lt;br /&gt;
|-&lt;br /&gt;
| Scene detection / threshold || – || on/off, 0.001 – 1 || on, 0.1 || Detects cuts before RIFE so they are not interpolated.&lt;br /&gt;
|-&lt;br /&gt;
| Manual scene changes || – || on/off, frame list || off || List of the last frames before each cut; excludes the automatic detection.&lt;br /&gt;
|-&lt;br /&gt;
| Tools: SCD || – || scd, misc (Windows), std, mv || – || Scene change detection, shown with Scene detection on; mv uses its own motion thresholds.&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, 25 fps), interpolated to 50 fps:&lt;br /&gt;
&amp;lt;syntaxhighlight lang=&amp;quot;python&amp;quot;&amp;gt;&lt;br /&gt;
clip = misc.SCDetect(clip=clip, threshold=0.100, tools={&amp;#039;scd&amp;#039;: &amp;#039;scd&amp;#039;})&lt;br /&gt;
clip = core.std.AddBorders(clip=clip, left=0, right=0, top=14, bottom=14) # add borders to achieve mod 32 (vsRIFEmlrt) - 640x384&lt;br /&gt;
# adjusting color space from YUV420P10 to RGBS for vsRIFEmlrt&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;
# adjusting frame count&amp;amp;rate with RIFE (mlrt)&lt;br /&gt;
from vsmlrt import Backend&lt;br /&gt;
clip = vsmlrt.RIFE(clip, model=44, multi=Fraction(2, 1), backend=Backend.OV_CPU(fp16=False,bf16=False))&lt;br /&gt;
clip = core.std.Crop(clip=clip, left=0, right=0, top=14, bottom=14) # removing added borders from mod requirement (vsRIFEmlrt) -  640x356&lt;br /&gt;
&amp;lt;/syntaxhighlight&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 with FP16) and padded to the size the model and scale require; the padding is removed afterwards.&lt;br /&gt;
* Factor and FPS are both turned into one exact multiplier; in FPS mode it is target rate / input rate. If the multiplier is not above 1, the filter is skipped with a note in the script and the frame rate stays.&lt;br /&gt;
* With scene detection Hybrid runs the detection itself before RIFE (RGB clips are converted to 16-bit YUV 4:4:4 for it); manual scene changes mark the listed frames instead.&lt;br /&gt;
* The model and the backend are always written; scale only when it is not 1.0, ensemble only when ticked.&lt;br /&gt;
* TensorRT builds an engine on the first run for each size.&lt;br /&gt;
&lt;br /&gt;
== Background ==&lt;br /&gt;
=== vs-mlrt ===&lt;br /&gt;
vs-mlrt&amp;#039;s RIFE needs 16- or 32-bit float RGB. Its documentation recommends running a scene detection before RIFE, since the result depends strongly on it, and suggests scale 0.5 for 4K material. The frame size must be a multiple of 32 divided by the scale (some newer models need larger multiples). TensorRT is clearly the fastest backend.&lt;br /&gt;
&lt;br /&gt;
=== Other RIFE versions ===&lt;br /&gt;
[[Vapoursynth RIFE|RIFE]] runs on Vulkan GPUs through ncnn, [[Vapoursynth TorchRIFE|TorchRIFE]] in PyTorch on NVIDIA GPUs.&lt;br /&gt;
&lt;br /&gt;
== Sources ==&lt;br /&gt;
* [https://github.com/AmusementClub/vs-mlrt/wiki/RIFE vs-mlrt wiki: RIFE]&lt;br /&gt;
* [https://github.com/AmusementClub/vs-mlrt vs-mlrt]&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>