TubeSum ← Transcribe a video

4K/60 FPS Explained - Frame Interpolation & Upscaling Compared (Aiarty Vs. Comfy UI)

Transcribed Jun 14, 2026 Watch on YouTube ↗
Intermediate 8 min read For: Content creators and video enthusiasts with basic knowledge of video editing and willingness to use command-line tools.
263
Views
9
Likes
1
Comments
0
Dislikes
3.8%
📈 Moderate

AI Summary

This video demonstrates how to upscale a video to 4K and interpolate it to 60 frames per second using both a manual Comfy UI workflow and the paid AI tool Aiarty Video Enhancer. The creator explains the processes of upscaling (increasing resolution) and frame interpolation (adding frames for smoothness), then compares the results and resource usage of the two methods.

[00:42]
Definitions of Upscaling and Interpolation

Upscaling increases resolution without quality loss, potentially adding detail via AI. Interpolation adds frames to increase FPS for smoother video.

[02:04]
Extracting Audio and Frames with FFmpeg

First, extract audio from the original video. Then use FFmpeg to extract all frames as PNG images. Commands are provided in the description.

[03:24]
Tools Mentioned: Lossless Scaling and Aiarty

Lossless Scaling is a Steam app for real-time frame interpolation in games/apps. Aiarty Video Enhancer is a paid AI upscaling tool (not sponsored).

[04:01]
Comfy UI Upscaling Workflow

Images are upscaled to 4K in Comfy UI. Using an AI model increases processing time significantly (from ~10 minutes to 1-2 hours). The creator's GTX 1070 with 8GB VRAM handles it, but 16GB RAM is insufficient.

[07:40]
Recombining Frames into Video

Use FFmpeg to combine frames back into a video, specifying frame rate and adding an empty audio track to avoid issues when merging with audio later.

[10:44]
Frame Interpolation in Comfy UI

A node multiplies frames (e.g., 30 to 60 FPS). The process requires significant RAM; the creator had to split the video into 50-frame segments due to crashes with 16GB RAM.

[14:46]
Combining Segments and Adding Audio

Use FFmpeg with a text file to concatenate video segments. Then add the original audio track. The final video is 4K 60 FPS.

[17:28]
Aiarty Video Enhancer Demo

Aiarty offers a simpler UI with options to upscale (using models), interpolate frames, adjust color, and denoise. It processes a 10-second video in about 10 minutes with better resource management.

Both Comfy UI and Aiarty can produce 4K 60 FPS video, but Comfy UI is free and highly customizable yet resource-intensive, while Aiarty is paid, easier to use, and more efficient. The choice depends on your hardware and willingness to tinker.

Clickbait Check

85% Legit

"Title accurately describes the content: a comparison of upscaling and frame interpolation methods."

Mentioned in this Video

Tutorial Checklist

1 02:04 Extract audio from original video using FFmpeg.
2 02:19 Extract all frames as PNG images using FFmpeg command.
3 04:01 Upscale images to 4K in Comfy UI (with or without AI model).
4 07:40 Combine upscaled frames into a video with FFmpeg, specifying frame rate and adding empty audio track.
5 10:03 Merge the video with the original audio track using FFmpeg.
6 10:44 For interpolation, split video into smaller segments (e.g., 50 frames) to avoid RAM issues.
7 11:50 Run each segment through Comfy UI's interpolation node to double frame rate.
8 14:46 Concatenate interpolated segments using FFmpeg with a text file.
9 15:55 Add audio to the final 60 FPS video.

Study Flashcards (8)

What is video upscaling?

easy Click to reveal answer

The process of increasing the resolution of an image or video without reducing quality or creating ugly stretches.

00:42

What is video interpolation?

easy Click to reveal answer

The process of adding more frames per second to a video by generating in-between frames to make it smoother.

01:05

Which command-line tool is used to extract frames from a video?

easy Click to reveal answer

FFmpeg.

02:19

Why add an empty audio track when creating a video from frames?

medium Click to reveal answer

To avoid issues when merging with audio later, because a video without an audio track is treated like a GIF and cannot have sound added easily.

07:58

What is the approximate RAM usage for interpolating a 1-second video (50 frames) in Comfy UI?

hard Click to reveal answer

Almost 50 GB (15-16 GB actual RAM plus 28-33 GB swap file).

14:10

What is the recommended minimum RAM for smooth video interpolation in Comfy UI according to the creator?

medium Click to reveal answer

At least 64 GB.

14:43

Name two tools mentioned for frame interpolation besides Comfy UI.

medium Click to reveal answer

Lossless Scaling (Steam app) and Aiarty Video Enhancer.

03:24

How long does Aiarty Video Enhancer take to process a 10-second video?

easy Click to reveal answer

About 10 minutes.

19:02

💡 Key Takeaways

📊

Definition of Upscaling

Provides a clear, concise definition of a key concept.

00:42
📊

Definition of Interpolation

Explains the process of adding frames for smooth motion.

01:05
💡

RAM Usage for Interpolation

Reveals the extreme memory requirements (50 GB) for a short clip, highlighting hardware limitations.

14:10
🔧

Aiarty Demo

Shows a simpler, more resource-efficient alternative to Comfy UI.

17:28

✂️ Creator Tools: Viral Hooks

AI-generated clip ideas for Shorts based on the transcript

What is Upscaling & Frame Interpolation?

51s

Clear, concise explanation of two key video enhancement concepts that many viewers find confusing.

▶ Play Clip

My PC CRASHED trying to upscale!

60s

Relatable tech struggle with a dramatic failure that hooks viewers interested in DIY video processing.

▶ Play Clip

FFmpeg Command to Extract Frames

60s

Practical tutorial step with a specific command, appealing to creators who want to replicate the process.

▶ Play Clip

ComfyUI vs Aiarty: Which is Better?

60s

Direct comparison between a free but resource-heavy tool and a paid optimized alternative, sparking debate.

▶ Play Clip

RAM Usage EXPLODES to 50GB!

60s

Shocking system resource revelation that highlights the hardware demands of AI video processing.

▶ Play Clip

[00:00] Hello once again audience. Welcome back

[00:03] to another video. And today we're going

[00:06] to do something different. I'm going to

[00:07] show you guys how to upscale a video and

[00:10] interpolate a video to 60 frames per

[00:13] second. But first, please subscribe to

[00:16] the channel if you haven't already. I

[00:18] would greatly appreciate it. This video

[00:20] costs a lot of time and effort to make

[00:22] and I would really appreciate if you

[00:24] could just subscribe to the channel to

[00:26] get me to a th00and subscribers. I mean,

[00:29] we got a bunch of views already and a

[00:30] bunch of watch time. We just need the

[00:33] subscriber count. So, I'm going to

[00:36] explain real quick what upscaling means

[00:39] and what video interpolation also means.

[00:42] Upscaling is the process of increasing

[00:44] the resolution of an image or a video

[00:47] without reducing the quality or creating

[00:51] ugly stretches.

[00:53] And

[00:54] uh in this case you can also add more

[00:57] details by adding an AI model to improve

[01:00] the quality or add more details or more

[01:03] sharpness whatever you want.

[01:05] And video interpolation is the process

[01:07] of adding more frames per second to a

[01:11] video. So basically generating in

[01:12] between frames uh for your video so you

[01:16] can make them buttery smooth.

[01:19] And uh basically what I tried to do

[01:22] there was uh run a compui workflow to

[01:26] upscale a video

[01:29] uh which is getting split into separate

[01:31] images and that's the the video right

[01:34] there which I showed in the intro and

[01:36] those images are getting upskilled

[01:38] separately. However, due to my PC being

[01:41] kind of poopy and not that great uh it

[01:45] crashed. So, what I'm going to do is I'm

[01:47] going to manually

[01:50] um split the images. I'm pretty sure

[01:52] there is a compi workflow node somewhere

[01:56] which allows you to do parts of the

[01:59] batch.

[02:01] Uh so what I did first I was splitting

[02:04] the audio from the video because if you

[02:07] put images uh together you don't have

[02:10] the audio. So, you need to keep the

[02:11] audio from the original video uh

[02:14] somewhere safe, which is what I did

[02:16] first. And next up, I uh I use a little

[02:19] command using ffmpeg uh which is the

[02:22] program I use for video and audio

[02:26] uh processing, editing,

[02:29] uh just trying to combine videos and

[02:31] whatever if I get stuck uh grabbing

[02:34] images from videos, etc., etc. That's

[02:36] what FFmpeg It's open source library and

[02:40] what I'm doing now is I'm running a

[02:42] command to uh extract all the frames of

[02:46] the video and create PGs from them. And

[02:51] uh you can see it takes a little bit of

[02:53] time and it should be around 300 images

[02:56] because it's 300 frames obviously.

[02:59] Uh, don't worry. I'll put all the

[03:01] commands in the description because uh,

[03:04] you're not going to remember everything

[03:05] I type. And I guess typing it well,

[03:07] pausing the video is also kind of

[03:08] annoying. So, don't worry. I put

[03:09] everything into the description. Um, so

[03:12] now we have the little uh, images here.

[03:15] I'm just going to put them in a separate

[03:17] folder for safekeeping

[03:20] so I can easily use that folder in a

[03:22] comfy UI.

[03:24] And besides Scumview, I also have

[03:26] Lossless Scaling for frame

[03:28] interpolation, which is like a Steam

[03:31] program which you can use for screen uh

[03:35] applications or games to create 60 fps

[03:38] without actually having to do any video

[03:39] editing. Uh, and I'm also going to show

[03:42] ART video enhancer, which is a paid AI

[03:45] tool. I got a free trial. I'm going to

[03:46] show you guys how it works. Uh, I'm not

[03:49] sponsored, by the way. I have to say I'm

[03:51] not sponsored. Uh, I hope they sponsor

[03:54] me. So, if you're watching the ARD, yo,

[03:56] sponsor your boy, please.

[03:59] So, what I did here is, uh, basically I

[04:01] had a little conf workflow and I grabbed

[04:06] a batch of images and I upskilled them

[04:09] to, uh, 4K resolution uh, without the

[04:13] use of the model. I do have a model in

[04:15] this little preview, but uh actually

[04:20] using that model kind of tenfolds the

[04:23] time. This already took over an hour to

[04:25] do in total. So, I'm just using like

[04:27] little batches here to to upskill them.

[04:32] And uh you can see that it takes about a

[04:36] minute for like 50 I want to say.

[04:40] uh maybe a bit longer but the process of

[04:43] like generating the images and doing all

[04:45] that stuff setting up confiu is such a

[04:48] drag uh I'm using Pinocchio

[04:52] and I think it has like 18 gigs of

[04:54] storage usage just for nodes and other

[04:58] libraries and whatnot. It's huge and uh

[05:02] it really eats up my PC.

[05:05] Uh, I I had a previous version of this

[05:08] video and there was just static noise

[05:10] and just the viewing experience wasn't

[05:13] that great. Honestly, I'm sorry. It's

[05:16] just cuz um because of my PC was kind of

[05:19] dying. So, that's why I'm re-recording.

[05:22] If you saw the other video, that's why

[05:24] I'm re-recording

[05:26] for uh for better audio because I I

[05:29] checked it out. I'm like, dude, this is

[05:30] awful. I cannot just put this out. And

[05:33] also I added some some nice new tweaks

[05:36] during the results section. So I I'm

[05:39] really happy how that turned out and

[05:41] might be a bit easier to spot the

[05:43] differences now.

[05:45] So uh yeah, you can see I think this

[05:48] takes like 2 minutes for 70 uh and then

[05:51] it's sourced to disk. So let's say it

[05:54] takes about two minutes for 60 and it's

[05:57] uh 300 frames.

[05:59] That's about uh uh 10 minutes for

[06:03] upscaling.

[06:05] Uh which isn't too bad uh considering

[06:11] ARD also takes about 10 minutes.

[06:14] Uh but there is a quality difference

[06:16] because ARD is using a

[06:20] AI model to increase the details and I'm

[06:23] not doing that here because that would

[06:25] probably make the runtime close to one

[06:28] hour maybe two hours

[06:31] uh just for for the image upscaling and

[06:34] then I'd still have to do 4K and

[06:38] I combining it back into a video. So,

[06:42] and for the sake of the video, I'm not

[06:44] using a model, but you could use a model

[06:46] if you have more RAM. Uh, I have a GTX

[06:50] 1070

[06:52] and it's doing fine. It's got 8 gigs of

[06:55] VRAM and it's it's holding up fine. The

[06:57] problem is,

[06:59] uh, mostly the RAM. I'm running out of

[07:01] RAM. I have 16 gigs of RAM, which is

[07:03] fine like like

[07:05] uh like eight years ago when I got the

[07:07] PC, but nowadays it's not. And and Comy

[07:12] UI just eats everything up and

[07:16] uh like I'm not sponsored by by ARD, but

[07:19] ARD has better um system resource

[07:24] management basically. So I'm just

[07:26] showing off the um the image there. it.

[07:30] It's upscaled to 4K now. It looks maybe

[07:33] a little bit sharper. I don't know.

[07:34] We're going to find out at the results

[07:37] section later in the video. And what I'm

[07:40] doing now is I'm uh combining

[07:44] the

[07:46] uh frames back into a video. And I'm

[07:49] specifying using the minus r uh

[07:53] parameter. I'm I'm specifying the frame

[07:55] rate basically. And I'm also setting up

[07:58] a empty audio clip. Uh because when you

[08:03] want to merge like concatenate videos or

[08:05] if you want to add audio to an existing

[08:08] video, it's sometimes it kind of

[08:11] uh like doesn't want to because you

[08:14] don't have an audio track on the video.

[08:17] So it's like just just a GIF basically.

[08:20] It treats it like a GIF and a GIF can't

[08:22] have sound. So if you have an empty

[08:23] audio track uh by using the 128k thingy

[08:28] um you ensure that you are not going to

[08:31] run into issues later

[08:33] uh adding audio or combining videos

[08:35] which do have audio and videos with jon

[08:37] of audio. So I had like um a banner

[08:42] project before. I had like a banner and

[08:44] I tried to merge it uh with like an

[08:46] actual video but the banner didn't have

[08:48] any sound. It was like just one frame of

[08:50] banner. um and um that caused issues. So

[08:55] that's why I know you you find out stuff

[08:57] like that. Uh again, don't worry. I'm

[08:59] just putting everything into the

[09:01] comments.

[09:02] And you can see this takes quite a long

[09:04] time. Uh probably because each of the

[09:06] images is like five megs big, five

[09:08] megabytes, over 300 images. That's um do

[09:13] the math, 1.5 gigs of images.

[09:17] uh it's it's adding into a video and

[09:21] honestly the video turns out to be like

[09:24] 55 megabytes or something. It's not

[09:26] really that big. Uh and ARD basically

[09:30] has the same thing. You know it it takes

[09:31] a 2 gig raw video and it converts it

[09:34] into like 55 or 20 megabytes video 4K.

[09:38] So it does do some very good

[09:40] optimization there. uh which I think

[09:43] it's H 264 265 something.

[09:48] So

[09:50] uh now I'm going to be

[09:55] uh let me check.

[10:00] I

[10:03] grab the video and I grab the audio.

[10:06] Yeah. And I combine them back to one. So

[10:09] now we are finished with our 4K video.

[10:13] We we've upscaled it perfectly and we're

[10:16] going to combine it with the other. This

[10:18] is a very fast process cuz basically

[10:21] you're just adding the track to to it.

[10:25] And this is how it looks like now. And

[10:27] at the end of the video, I'll be making

[10:29] comparisons so you can compare for

[10:31] yourself. And let me know in the

[10:33] comments if you think it looks any

[10:34] different. Uh and if so, which version

[10:37] do you think looks better? I'm really

[10:39] excited to hear you guys opinion. So

[10:41] this again is the um

[10:44] load video note which is the first one

[10:47] on the left there. Uh you can load a

[10:49] video in and then you can kind of

[10:52] interpolate it using another node. Uh

[10:55] basically I'm multiplying it to two

[10:57] meaning it will get uh 60 frames instead

[11:00] of 30. And then uh like the first node

[11:03] is actually splitting the video into

[11:05] images which uh basically I was doing

[11:08] myself before as well. Uh and then the

[11:11] the middle node is taking those images

[11:14] and then adding in between frames. And

[11:17] then the last node is actually combining

[11:22] the images back into a video. So

[11:26] basically

[11:28] I could work with only getting the in

[11:31] between frames and then generating the

[11:33] file myself. But the last node is not

[11:35] the issue. The first node is the issue

[11:38] which again crashed my PC because I

[11:41] don't have enough RAM. So I had to

[11:45] create smaller bits of video. So I I cut

[11:50] all the 300 frames into little parts.

[11:55] and like 50 frames per video, which is

[11:58] like 1.8 seconds, I guess, on a 30 frame

[12:02] video, 30 frames per second video. And I

[12:05] cut them in six parts cuz it crashed.

[12:09] And uh this this worked. And it's

[12:13] basically the same command as before.

[12:14] We're just trying to to create another

[12:16] video with the um 30 frames per second

[12:21] parameter, the minus or 30. empty audio

[12:24] track just cuz. And uh uh yeah, we

[12:28] create six of them. And I have a very

[12:30] bad naming schemes, you know, B1, A1,

[12:33] C1. Uh I just want to like get this done

[12:36] and I remove all the files afterwards.

[12:38] So like when I'm doing stuff like this,

[12:40] I usually have very default commands in

[12:42] a in a notepad or something

[12:45] uh with like a b c uh and they are

[12:48] sequenced. So I know like oh I'm at C

[12:51] step which is the third step. So I'll

[12:53] try to do the same in the comments as

[12:55] well for you guys. So you can easily

[12:57] copy paste it in sequence for one

[12:59] project and then uh you have like a a

[13:02] nice finished end result.

[13:05] So uh this like 50 frames not too long

[13:08] takes uh almost 30 seconds. Yay.

[13:12] And now I put it in into the um load

[13:16] video again. Uh I do notice that you can

[13:19] kind of limit the frames. Uh maybe you

[13:22] can set a different starting frame. Uh

[13:24] and you can kind of batch it like that.

[13:29] That might work. But I'm also scared

[13:31] that it's because it's a larger video,

[13:33] it's trying to still load some stuff

[13:35] into memory, which is going to cause it

[13:38] to die again, and I don't want it to die

[13:40] again because just sucks so much.

[13:44] Um like I didn't get a blue screen. My

[13:47] entire PC just completely froze. But you

[13:49] can see that the first step was finished

[13:51] way faster now, which again, less RAM

[13:54] needed. So, it all fits into my little

[13:57] 16 gigs memory. Uh, if you have more

[14:00] RAM, I I guess you could do this a lot

[14:03] easier with bigger videos. Let's look at

[14:06] the the the usage there. It is already

[14:10] for 50 frames already almost capping my

[14:13] my memory. It's taking 30 gigs of my

[14:15] swap file on my hard disk. like you can

[14:18] set up a certain section of your hard

[14:20] disk for extra RAM, which is really

[14:23] slow, but you can see that's also taking

[14:25] like 30 gigs, 28 to 33. Um, and that's

[14:30] that's besides my 15 to 16 gigs actual

[14:33] RAM usage. So, it's almost 50 gigs of

[14:36] RAM usage for a 1 second video for

[14:40] interpolation. So, that's you need like

[14:43] 64 gigs at least to do this stuff.

[14:46] Uh, so I finished all the uh little

[14:48] parts there

[14:50] and I'm combining them in order. You can

[14:52] have a little text file with ffmpeg

[14:55] and it will combine those videos in

[14:58] order and it will just concatenate those

[15:00] videos uh without any transitions. You

[15:03] might be able to do a transition with

[15:05] some fancy stuff maybe. I don't know.

[15:08] You would have to look it up. But if you

[15:10] don't have a video editor, but you want

[15:12] to have like a transition between clips,

[15:15] uh you could maybe do something like

[15:17] that. And also

[15:19] um you can easily combine clips using

[15:22] ffmpeg. You don't need a fancy video

[15:24] editor. You don't need Adobe Premiere

[15:27] for just combining clips. Uh also Adobe

[15:31] Premiere sometimes just crashes and

[15:32] doesn't want to combine videos and and

[15:34] just creates corrupted stuff. Uh, Fmpe

[15:38] is really stable for video creation, but

[15:40] if you want to do animations and like

[15:44] fancy text and whatnot, you might need a

[15:46] video editor.

[15:48] So, I combined the 60 fps video now as

[15:51] well. There we go. It's now 4K 60 fps.

[15:55] There is no sound again because we do

[15:57] have to add the sound to the video

[16:01] again, which as we know from before is a

[16:04] very fast process. So,

[16:07] almost done with the 4K 60 fps uh AI

[16:10] version.

[16:12] I am also going to create a

[16:16] nonupskilled 60fps version. See how that

[16:19] runs and I'll show the comparison later.

[16:24] That was me. Sorry, I pressed the

[16:26] recording button. Uh that's not your

[16:28] Windows doing a little plink sound.

[16:29] That's just me. I'm sorry. I hate it

[16:31] when YouTubers make a sound like Discord

[16:33] notification or whatnot and they don't

[16:35] mention it. This was me, okay? So, I'm

[16:37] sorry. Uh, don't don't be scared. So,

[16:40] again, we're we're combining the audio

[16:42] with the um with the video. And like I

[16:47] said before, I was going to try to do a

[16:49] 60 fps version with out upscaling. And

[16:53] that one took maybe like 20 to 30

[16:58] minutes. Uh, but it didn't crash my RAM.

[17:01] It just took a very long time. Like I

[17:02] was still able to watch some YouTube and

[17:05] and open Discord. I could I could do

[17:06] stuff while it was running. So,

[17:10] it's really good. Uh, that's the wrong

[17:13] version. Here we go. This is the uh the

[17:16] sound version again.

[17:18] 60 fps with sound.

[17:21] It looks It looks decent. I guess I'll

[17:23] have to compare it with uh with the

[17:25] original one later.

[17:28] Uh, but that's basically it. It took us

[17:29] about 15 minutes and 70 minutes even.

[17:33] And now I'm going to show you ARD video

[17:36] enhancer. I'll put the link in the

[17:38] description. Again, I'm not sponsored.

[17:40] Uh, but it's very easy. It's very

[17:42] optimized and it checks your hardware

[17:44] and everything. You can upscale using a

[17:47] model. You have three models of choice.

[17:49] I'm not sure if you can get other models

[17:50] somehow. You can upscale to 4K. You can

[17:53] use step mode for higher quality. You

[17:56] can use turbo for faster processing. Uh

[18:01] but it is uh uh it is lower quality. So

[18:05] here you can see like I have a little

[18:07] slider. You can see the edge of the uh

[18:10] ridge basically gets a little sharper.

[18:12] Let's look at Maido for a sec. Um yeah,

[18:16] he does get sharper. Like clearly

[18:17] sharper. Let's zoom in a little bit.

[18:19] There you go.

[18:21] Uh so you can see he does get a little

[18:23] sharper. You do have to be careful with

[18:25] the strength though, especially when you

[18:27] have a very low res image. Uh sometimes

[18:30] AI is adding some weird details like

[18:33] with text. I've had instances where uh

[18:37] the C turns into a D or a O. And uh as

[18:42] you can see, you can also increase the

[18:43] frame rate very easily. Uh you can

[18:46] change the color. Uh you can use HDR uh

[18:50] audio D noiseis like whatever you want.

[18:53] and you just press the the uh export

[18:56] button. You can even do a batch export

[18:58] of multiple videos using the same

[19:00] settings. So, you can see it takes about

[19:02] 10 minutes for a 10-second video. Uh

[19:06] it's a lot less setup. It's very

[19:09] much faster. So, I hope you enjoyed this

[19:12] and I hope you enjoy the results in a

[19:14] little bit. Uh because yeah, I think

[19:18] they look pretty cool. So, please

[19:20] consider subscribing to the channel if

[19:21] you have not already. I would greatly

[19:23] appreciate it and I hope to see you all

[19:24] next time. Let me know in the comments

[19:26] which versions you like the most and if

[19:29] you notice any big differences or not.

[19:32] So, thank you for watching. I hope you

[19:35] found this useful or interesting at

[19:37] least. And see you tomorrow with Maple

[19:40] Story again. I'm sorry. Okay, bye-bye

[19:43] everyone.

[19:46] [music]

[19:56] >> [music]

[20:08] >> Don't

[20:36] >> [music]

[21:06] [music]

[21:43] >> And now a shout out to our members. On

[21:46] the extreme tier we have Dustin H. On

[21:49] the normal tier we have Daniel Chavez.

[21:53] Thank you all so much.

[21:55] See you all next

⚡ Saved you time reading this? Transcribe any YouTube video for free — no signup needed.