1,000,000,000 Parameter Super Resolution AI!

แชร์
ฝัง

ความคิดเห็น • 411

  • @sebaccimaster
    @sebaccimaster ปีที่แล้ว +467

    Upscaling keeps on blowing my mind. Perhaps more than img generation

    • @rollmell
      @rollmell ปีที่แล้ว +20

      well wasnt this one technically a mix of image generation and upscaling

    • @sgttomas
      @sgttomas ปีที่แล้ว +82

      Enhance…. Enhance…. Enhance…. Enhance….. I can see the suspect in the reflection of her eyes.
      And we all laughed at that!!! 😮

    • @guepardiez
      @guepardiez ปีที่แล้ว +63

      @@sgttomas We still do. If you can see the suspect in her eyes, it will be a made-up one.

    • @eyeles
      @eyeles ปีที่แล้ว +17

      Remember when they said CSI is completely fake because they zoomed in cameras and improved picture quality😂

    • @PopGoesTheWorld2023
      @PopGoesTheWorld2023 ปีที่แล้ว +6

      It certainly is more useful working professionally with graphics and layout. Also extend an image with generative fill in the current Photoshop beta has proven to be amazing and extremely helpful in daily work.

  • @fynnjackson2298
    @fynnjackson2298 ปีที่แล้ว +277

    Would love to see an image downscaled in Photoshop, then upscaled, then have the original and the upscaled version compared at different downscaling levels to see where it gets it correct and where it starts to fall apart so to speak. What a time to be alive!

    • @austinpalis4931
      @austinpalis4931 ปีที่แล้ว +22

      So now we wont only have over-compressed images, but also under-compressed images? De-compressed? over-decompressed? The future is weird man

    • @sc0rpi0n0
      @sc0rpi0n0 ปีที่แล้ว +13

      it won't work that way, as the details are 100% daydreamed or generated.

    • @Yasha_U
      @Yasha_U ปีที่แล้ว +45

      @@sc0rpi0n0 thats the point, as a reminder to see what might have been missed in the details
      a control variable, so to speak?

    • @spawn142001
      @spawn142001 ปีที่แล้ว +16

      The point is to see how good the second image comes out and how it compares and contrasts with the original.

    • @tuseroni6085
      @tuseroni6085 ปีที่แล้ว +32

      could be a good thing to remind lawyers that this technique is NOT "zoom and enhance" so they don't go entering AI daydreamed details into evidence.

  • @philip_hofmann
    @philip_hofmann ปีที่แล้ว +64

    We talked about GigaGAN in the upscaling community in march. Their results look amazing, but since there is no code/models for us to validate their claims on our own input images, we remain sceptical. In contrast DiffBIR (which just released recently), or StableSR, or ResShift, DAT, SRFormer, HAT etc, we can all run them or train models for them ourselves)

    • @darkandblue4118
      @darkandblue4118 ปีที่แล้ว +8

      Thanks for telling about all the cool projects

    • @theneonbop
      @theneonbop ปีที่แล้ว +1

      Isn't the code available now?
      Edit: I guess the code is available but not the model.

    • @Macatho
      @Macatho ปีที่แล้ว +1

      Thank you, was looking for this answer as I am currently trying to find a good upscaler. I can do a decent amount of upscaling in automatic 1111 but I run out of memory quite quickly and I need to get to around 10000x10000 in pixels for a decent DPI for actually printing these generated images.
      As you seem knowledgable, are there any free-to-use models that I could apply? I could even pay a small sum, just not hundreds of dollars per image.

    • @AgrippaTheMighty
      @AgrippaTheMighty ปีที่แล้ว +2

      I was just wondering, how about video upscaling?

    • @Macatho
      @Macatho ปีที่แล้ว +1

      ​@@AgrippaTheMighty That's a bit more problematic :)
      There is research into video and I guess in 2 years this problem will be solved and also Stable Diffusion will be able to generate video. Video is just different in so many ways, if you take a still from a movie, even in 4k, it's horrible quality compared to a photograph in the same resolution.
      You could of course try to upscale video yourself, just splice the video into images then upscale each image with a low denoising strength.
      I'm atm upcaling a 1500x2000 image to 15000x20000, it takes around 30 minutes on a 3090rtx 😭😅. What it does is basically breaking the picture down into sub pictures, because the picture as it is does not fit into the video memory, then it upscales each sub picture, stitches them together, then it does a band pass on the stitches and goes through them using a gradient of denoising strengths (that last one was me guessing, but that's what I would have done).

  • @DeKevers
    @DeKevers ปีที่แล้ว +118

    Since I've started watching you, I feel like I forgot how much AI has developed over 3 years, you have to look back to see how insane progress is

    • @Lucas-po6mn
      @Lucas-po6mn ปีที่แล้ว +12

      remember when DallE 1 was impressive, its not even an afterthought now

    • @itsjustme4026
      @itsjustme4026 ปีที่แล้ว +3

      Gta sa as a kid vs Rdr2 as an adult

    • @getsideways7257
      @getsideways7257 ปีที่แล้ว +4

      Still too early to call it "AI"... Just call it NN or ANN

    • @Lucas-po6mn
      @Lucas-po6mn ปีที่แล้ว

      @@getsideways7257 no, AI means any bot, hardcoded or with machine learning, what you are referring to is AGI

  • @M4rt1nX
    @M4rt1nX ปีที่แล้ว +4

    I'm so happy I found this channel years ago before all that recent AI frenzy.
    Last week I heard someone say that AI is new and I just though that I've been holding to my pappers for years now.

  • @signupisannoying
    @signupisannoying ปีที่แล้ว +1

    Wow, super cool. We can use this to make decades old photo look clearer.

  • @zRedPlays
    @zRedPlays ปีที่แล้ว +27

    I fell off my chair when I saw what this upscaler could do, from the dog to the humans, all those tiny hairs... It brings out so much detail it's hard to believe it's real. Mindblowing

    • @Cola-42
      @Cola-42 ปีที่แล้ว +3

      Okay man, but are you hurt in any way?
      Do I need to call the ambulance?

    • @Slav4o911
      @Slav4o911 ปีที่แล้ว +1

      Yes but the problem is they keep the model for themselves, which means it might not be that impressive in the real world. Stable Diffusion and Topaz Gigapixel are also impressive, it's like you're seeing AI upscaling for the first time.

    • @zRedPlays
      @zRedPlays ปีที่แล้ว +1

      @@Slav4o911 I've already seen upscaling, it's just that this model's quality especially with hair is outstanding. And yeah I'm aware they keep it for themselves, but that pretty much applies to any revolutionary/cutting edge technology

    • @zRedPlays
      @zRedPlays ปีที่แล้ว

      @@Cola-42 Nah dude my mind being blown counteracted my fall and I'm now on top of my chair

    • @Slav4o911
      @Slav4o911 ปีที่แล้ว +1

      ​@@zRedPlays Both SD and Topaz can recreate hair. That's why I'm not impressed, unless I see the model for myself or other people not connected to the company test it. Also they've probably hand picked the results.

  • @Timotheeee1
    @Timotheeee1 ปีที่แล้ว +143

    would have been nice if they had released the model

    • @lbgstzockt8493
      @lbgstzockt8493 ปีที่แล้ว +73

      reminds me of ""Open""AI

    • @descai10
      @descai10 ปีที่แล้ว +12

      @@terpy663 people run up to 30b parameter LLMs on their own pcs all the time

    • @deadman1999
      @deadman1999 ปีที่แล้ว

      What is Block N Load's prodigy doing here ??

    • @harrytsang1501
      @harrytsang1501 ปีที่แล้ว +5

      Especially because 1b parameter can fit on most consumer grade GPU nowadays

    • @bparlan
      @bparlan ปีที่แล้ว +2

      @@harrytsang1501 we do run 30b parameter LLMs on our own pcs mate. Models are just 30-60gb tenor files. Just 1 GPU can be a huge step into ML!

  • @GL-GildedLining
    @GL-GildedLining ปีที่แล้ว +3

    Between simulon featured in Matt Wolfe's most recent video, and GigaGAN here, it feels like a reminder that _yes, the singularity is still on schedule._

  • @ZOMBIEHEADSHOTKILLER
    @ZOMBIEHEADSHOTKILLER ปีที่แล้ว +11

    You should do a few videos showing where to get, and how to use, some of these different AIs you show.
    i know its not your normal thing, but it would be very helpful, and there probably isnt a channel that could do it better.

  • @piershanson1784
    @piershanson1784 ปีที่แล้ว +6

    I'm glad to see adversarial networks getting some more love!

  • @Cropinky
    @Cropinky ปีที่แล้ว +3

    the results are really cool, but it has to be mentioned that these are not being upscaled unconditionally, they are being conditioned by a prompt (CLIP) and that's what makes the upscaling so good, also some other cool techniques used in the paper.

  • @ivragi
    @ivragi ปีที่แล้ว +10

    Yeah, but it's GAN. It works in a specific pretrained patterns (e.g. human portrait, dog, elefant) and you need separate models for every new concept. And it works well with GAN-generated images, everything else is turned to mush when converted to format in which those models can work with.

  • @cosmicrdt
    @cosmicrdt ปีที่แล้ว +22

    Are there any public models available to use it yet? I'd love to give it a try.

  • @playbyan1453
    @playbyan1453 ปีที่แล้ว +2

    Upsampling and signal processing goes this far, people who did this paper need more recognition.

    • @getsideways7257
      @getsideways7257 ปีที่แล้ว +2

      There is a huge difference between figuring out the fine details and "artistically visualizing" them. The latter can be fun and all, but only the former is useful for serious work.

  • @Neonalig
    @Neonalig ปีที่แล้ว +1

    Looks like we're progressively getting closer to that CSI Zoom and Enhance effect, but in reality.
    This theoretically opens up so much in the field of data compression. Whilst not perfectly lossless, you could store images in a literal 1/10th or even 1/100th the fraction of storage, and get a near equivalent output with only minor visual degradation.

    • @joelface
      @joelface ปีที่แล้ว

      Interesting! I think the issue is that while the results will look crisp and (probably) realistic, they'll be different each time. So pictures of your friends might not even look like your friends the next time you open the picture. That said, perhaps if you were to store the original image still in fairly high quality it could work. For example, have it upgrade the final difference between say a 2k and an 8k image -- the finer details might not be something you'd notice anyway, but would save a lot of space.

    • @cthudo
      @cthudo ปีที่แล้ว

      Of course the problem with using this in a CSI context is that these "enhanced" details are completely made up. I can't wait until this actually gets used in court one day and neither judge nor jury have the knowledge to call out the images thus enhanced by law enforcement as what they are: fabrications. I can even see an expert witness arguing "we are using a superhuman AI to reconstruct what the most likely details of this image look like, so it should absolutely be admissable as evidence!"

  • @VincentKun
    @VincentKun ปีที่แล้ว +4

    I followed lesson the last semester and my professor pointed out how difficult it is to have disentangled representation, so very Happy to see this results

    • @cyancoyote7366
      @cyancoyote7366 ปีที่แล้ว

      Did he ever give a reason as to why? I am genuinely interested.
      Is it just because there are so many less ways to have separate, narrowly defined representations than a jumbled mess of undefined "black box" representations that don't make intuitive sense for human brains?
      So is it just like... restricting the neural network to a "human-readable" domain, in a sense?

  • @Chris.Davies
    @Chris.Davies ปีที่แล้ว +1

    0:53 - It almost got the Porsche 356 shape right - but not quite. I am very familiar with it.
    I give it 7/10 - and eagerly await being able to award 11/10!

  • @Mr.MasterOfTheMonsters
    @Mr.MasterOfTheMonsters ปีที่แล้ว +6

    All that was missing was combining Upscallers with AI generation to understand what is the image about and keep them as accurate as possible. And it's finally here!
    I'm guessing this process would cause problems for more complex images or things that are hard to identify, like a gathering or a dense jungle. But who knows.

    • @spawn142001
      @spawn142001 ปีที่แล้ว +6

      AI image generation IS upscaling. It takes an image of 100% noise. And then it denoises it. Removes the noise. Upscalling the software first brings the original image to the target resolution. So it's not individual pixels at a lower res but giant blocks of 100s of pixels at the target higher resolution.
      Now this is where they are the same. The starting images just appear different. But they essentially do the same thing. The AI de-noises the image in small steps 20-100 times until the target image is found.
      Go watch a video on how generative AI works. There's a decoder network that translates the query or words into something the second generative network will understand.
      These two things all though very slightly different under the hood ARE the same thing or the same family of AI. The neural networks are structured in a remarkably similar way all though they might be trained on different data sets.
      I.e. the encoder networks are trained on images that were taken in high res and manually lowered so that it can compare its output to the original high res and learn from it.

    • @DajesOfficial
      @DajesOfficial ปีที่แล้ว +1

      Literally all upscalers work this way. Just with way less parameters and training data

  • @noisywan
    @noisywan ปีที่แล้ว +1

    2:11 I remember laughing at the scenes in movies where the nerd CIA officer enhances the face of a criminal captured from a 320x200 CCTV with the help of hitting ENTER on keyboard:)
    I used to play games like The Alley Cat on 80x86 IBM Ps/2 machines with CGA video card. What a time to be alive!

  • @Joshua-ew6ks
    @Joshua-ew6ks ปีที่แล้ว +3

    The zoom and enhance that CSI Shows has used is now real.

    • @alpuhagame
      @alpuhagame ปีที่แล้ว

      Pretty much they had this technology 20 years ago, but only now it has surfaced 👌

  • @spawn142001
    @spawn142001 ปีที่แล้ว

    Just want to mention this because i can tell from the comments some people dont know. Inage Genrative AI and upscaling AI are almost the samw thing. They are remarkably similar under the hood in how they work and how they are structured.
    Key differences would be training. Generative had to match images to words and is trained on data sets that have pictures with words stating what the picture is or whats in it.
    Upscalling you take high resolution pictures, reduce the resolution. Give the network the low res ask for the high res. Compare the output to the original high res, train the network from there.
    It might even go deeper and do object recognition first on the lower res, to more specifically know what it should fill in the missing pixels with to be more realistic. For example upscaling a dog at low res. You dont see individual hairs, but the network sees its a dog and knows it ahould produce fine hairs in the output.
    Upscaling IS generative but instead of starting with pure noise, and finding the target image, it starts with a low res image thats first put into a higher target res format (not upscaled just taking individual pixels and scaling them into giant pixels) maybe it even noises this image up a bit before starting.
    But where they are both the same is they both take the original image, be it pure noise for generation or the lowscale image for upscale. It iteratively removes a little bit of noise in small steps doing 20-100 or more iterarions depending on the structure of that AI until your output image is found. Remove too much noise in one step and your quality goes down significantly.
    Its alot more nuanced than this, alot of them do things inbetween each step that are difficult to explain here. So that say query "dog with wings" doesnt produce a dog with a tiny wing on its nose and a large wing not attatched in the corner of the screen.
    It kinda of in somesense fact checks to the query and makes the image more relevant but this has to do with modifying the noise image on each iterative step through a seperate process.
    Its best to find videos that actually explain the behind the scenes of both upscaling and image generation. These are REALLY good. And its crazy hearing how it actually does it.
    Theres also different types of image generation. I believe i described a difusion based system. But might have the names mixed up

  • @perplexedon9834
    @perplexedon9834 ปีที่แล้ว

    Whats really cool is that this could make video and image compression absurdly good. If you have a fast, local program that can upscale images in ways that are fully plausible to humans, then you only need to store a low res version.
    Its like how traditional compression can utilise redundancies in an image (like large blocks of the same colour), AI upscaling dependent compression could utilitse redundancy in human perception (fur looks like fur no matter the specific hair orientations).
    Imagine a 4k movie being stored in 10s of megabytes.

  • @lewisbamford337
    @lewisbamford337 ปีที่แล้ว +2

    Your the only TH-camr I have notifications on for 😅I just love watching your videos 😊

  • @cyber1714
    @cyber1714 ปีที่แล้ว +1

    WHAT A TIME TO BE ALIVE!!!

  • @MattCruikshank
    @MattCruikshank ปีที่แล้ว +1

    At 2:07 there's a mistake. It says "Coarse," but it's actually spelled "Horse." ;)

  • @alexlohr7366
    @alexlohr7366 ปีที่แล้ว +1

    This is really incredible. However, I can already see people attempting to claim that this could make the classical crime tv "enhance" trope a reality - but the upscaled version does not contain more actual signal, so it only looks like something that could be true, but need not be.

  • @galgrunfeld9954
    @galgrunfeld9954 ปีที่แล้ว

    This is an absolute game changer! The amount of applications this can have is just absolutely *huge*!

  • @TeamUnpro
    @TeamUnpro ปีที่แล้ว +1

    so the depixelization we seen in movies is finally real

  • @rocco549
    @rocco549 ปีที่แล้ว

    Can't wait for it to become available for video restoration. It will create wonders.

  • @swanknightscapt113
    @swanknightscapt113 ปีที่แล้ว +1

    I've always known GAN will be making a comeback. SD'd better watch its back!

  • @Sekir80
    @Sekir80 ปีที่แล้ว +26

    I love the upscaling. I wonder how temporally coherent it is. In other words: can we use this for video upscaling?

    • @Chaosligend
      @Chaosligend ปีที่แล้ว +7

      No. Without any kind of feedback loop of the outputs it's impossible to have any kind of coherence. It's like asking two artists to draw the same image without communicating. The architecture needs significant changes in order to improve temporal coherence. Usually that also means significantly slowing down the model.

    • @Sekir80
      @Sekir80 ปีที่แล้ว +1

      @@Chaosligend Dumb question: how do you know there's no feedback?

    • @Chaosligend
      @Chaosligend ปีที่แล้ว +8

      @@Sekir80 I have a degree in AI and happen to specialize in Computer Vision so I'm familiar with the kind of architecture that the paper is using and what kind of architecture is needed in order to make temporal cohesion. The problem is that at this moment the computers are not nearly strong enough to allow for temporal cohesion with a naive approach. There are some attempts being made to use a very advanced approach to solve this issue but it needs at least a year or two to produce any decent results.

    • @Sekir80
      @Sekir80 ปีที่แล้ว +2

      @@Chaosligend Thank you! I'm not in the field, an expert's opinion is truly appreciated.

    • @Sekir80
      @Sekir80 ปีที่แล้ว +1

      @@acmhfmggru Thanks to you as well! I was asking that, because without understanding the paper (which I didn't read, at all) I can't be certain there's no feedback. But you both telling me that implies the nature of this kind of AI thing isn't meant to do it on itself. And of course, if it would have a temporal coherence part, they would be boasting about it. I think.

  • @Shurgath
    @Shurgath ปีที่แล้ว +1

    Looking forward to your take on the 3D Gaussian Splatting paper! There is also a new paper that just came out, which extends it to dynamic scenes. Seems to work pretty well there as well.

  • @zetathix
    @zetathix ปีที่แล้ว

    I just choked my coffee when I saw that enhanced elephant image. That is a really good image to prove the quality.

  • @DanielLCarrier
    @DanielLCarrier ปีที่แล้ว +2

    I'm hoping for fast enough upscaling that you could have it as a browser addon, and zooming in doesn't make stuff pixelated.

  • @Fanny-Fanny
    @Fanny-Fanny ปีที่แล้ว +2

    Wow! How long before we can tell an AI 'i want to watch a movie that is The Empire Strikes Back, but done in a Film Noir style, with Ice Cube as Han Solo and where the movie is from the perspective of The Empire being the good guys. Blend with jokes and characters from The Office, and make it 8 x 5 minute long animated cartoons in the style of The Power Puff girls. But add a twist at 3 points in the movie, based on Pulp Fiction and Snow White' and it produces a quality product that is super enjoyable?
    I think 14 years 3 months and 17 days (approx). That is a time to be alive, I tell you what!

    • @the_real_glabnurb
      @the_real_glabnurb ปีที่แล้ว +1

      I think you should ask ChatGPT that question.
      After all, who knows better than an AI, what an AI will be capable of?

    • @Fanny-Fanny
      @Fanny-Fanny ปีที่แล้ว

      @@the_real_glabnurb good idea! It said 'can eat more'... not even sure what that means?

  • @richbynoon
    @richbynoon ปีที่แล้ว +2

    What a time to be alive....another video

  • @dingozi3428
    @dingozi3428 ปีที่แล้ว +3

    I love how AI could turn blurry images into none blurry images, good job little AI👍🏻👍🏻

  • @Dimencia
    @Dimencia ปีที่แล้ว +1

    During one demo, you showed an image being upscaled, then zooming in on some subsection and upscaling that too... what a great example of the power and usefulness of upscaling. If the upscaling is good enough, you could give it a map to have it draw the world
    I'm still just waiting for some ridiculous new compression ratios using similar techniques, though

    • @joelface
      @joelface ปีที่แล้ว +3

      The issue being that it is fabricating the results, not upscaling to actual truth.

  • @mattmarket5642
    @mattmarket5642 ปีที่แล้ว +9

    The comparison to Stable Diffusion seems WAY off... they must be using the original SD 1.5 from a year ago instead of some of the incredible community-made finetunes or the new SDXL. I'm sure this GAN has it's use cases but I see way more mutilated images compared to SD.

    • @sevret313
      @sevret313 ปีที่แล้ว +2

      Yes, this is the problem with researchers doing their own benchmark as they're always incentivised to make their competition underperform.

    • @mattmarket5642
      @mattmarket5642 ปีที่แล้ว +3

      @@sevret313 So very very true. Too bad Károly doesn't call them out when they do such blatant mischaracterization. I've come to realize this channel needs to be taken with a massive grain of salt over the last year, as I've gotten more into the weeds of AI projects.

    • @DajesOfficial
      @DajesOfficial ปีที่แล้ว

      This paper is 5 months old, so no SD XL back then

  • @PushyPawn
    @PushyPawn ปีที่แล้ว +1

    What it's like to trip on acid: 1:08

  • @jerchongkong5387
    @jerchongkong5387 ปีที่แล้ว +2

    This would be very useful on video, there are movies like the star wars prequels that were shot at 1080p, upscaling them to 8K would be easy with this.

    • @solenoidnull9542
      @solenoidnull9542 ปีที่แล้ว

      Once this tech is perfected the input resolution almost won't matter to the layman anymore, now someone chooses their output resolution and its viola. Those fine hairs from nothing in the sample show that even 420p video would be crisp 4k with full detail, giving a full experience either way though not technically accurate to the 4k original if it existed.

  • @glr
    @glr 10 หลายเดือนก่อน

    Need something like this which can handle the continuity of video.

  • @ulamss5
    @ulamss5 ปีที่แล้ว +3

    Finally a GAN breakthrough!! What a time to be alive!

  • @AllisterVinris
    @AllisterVinris ปีที่แล้ว +1

    Mind blowing.
    Are you going to talk about DLSS3.5 and ray reconstruction or is it not crazy enough ? Because I think I understand how it works, but I wouldn't be against a more precise explanation

  • @PutItAway101
    @PutItAway101 ปีที่แล้ว +1

    Looks good, but it still lacks the common sense that humans apply. Like the scarf on the dog, a human looks at the low res dots on the scarf and thinks "that's probably a repeated pattern of the same thing, mostly likely just round white dots" but the AI tries to make a unique shape for each dot based on the way it happened to get pixellated.

  • @AriaAlessandra
    @AriaAlessandra ปีที่แล้ว

    I Cant wait for this to be publicly available!!!

  • @Vartazian360
    @Vartazian360 ปีที่แล้ว +1

    Now make it available for thr public to use? The upscalers out there suck

  • @adrianm7203
    @adrianm7203 ปีที่แล้ว +5

    If you zoom into the upscaled image and then upscale it again could you do an infinite zoom? I wonder what kind of artifacts the upscaler would create.

    • @michaelleue7594
      @michaelleue7594 ปีที่แล้ว +1

      You could, but it would do a bad job for anything but fractal-style images. It wouldn't know how to just up the resolution. Let's say your GAN is trained on human faces like this one is, then when you zoom in it would try to make the zoomed in portion look like a human face inside of the larger human face. That would end up looking monstrous or stupid for most applications.

    • @perfectionbox
      @perfectionbox ปีที่แล้ว

      Read "Blind Lake"

  • @theodoreroosevelt7224
    @theodoreroosevelt7224 ปีที่แล้ว +1

    Skip to the bit where he says Teddie-bear 2:56

  • @fraizie6815
    @fraizie6815 ปีที่แล้ว +1

    Is it really upscaling, though? It generates new pixels that aren't there, purely by guessing what the image shows (person, horse, etc.) so the image you see isn't actually reflecting reality, though what the AI thinks what the reality should look like.

  • @mocmocmoc13
    @mocmocmoc13 ปีที่แล้ว

    Holy moist papers! Those super res upscale blows everything we currently have outta the water.

  • @Flashbry
    @Flashbry ปีที่แล้ว

    That is astounding! What a time to be alive!!!

  • @Exilum
    @Exilum ปีที่แล้ว +2

    Now I need to see this applied in stable diffusion. SD tooling is already insane, but I can't imagine how far you could go, especially with things like comfyUI.

    • @michaelleue7594
      @michaelleue7594 ปีที่แล้ว

      Matching up GANs with generative AI is challenging because of how GANs are trained for very, very specific kinds of images. I guess what you could do is have a large list of GANs in A1111 or whatever and then manually select an appropriate GAN for the kind of image you've generated, but unless you're limiting yourself to pretty limited sets of subject matter, you're going to fill up your whole hard drive with GANs pretty quick. Not to mention someone actually has to make the GAN models in the first place, which is far from trivial. These are not simple or small, like Loras.

    • @Exilum
      @Exilum ปีที่แล้ว

      @@michaelleue7594 People using comfyui already built an habit of using different models for different tasks at each step of their composition, so it wouldn't be that far fetched doing the same with a GAN model. The super-resolution ability would certainly be fit for this workflow.

    • @michaelleue7594
      @michaelleue7594 ปีที่แล้ว

      @@Exilum That's fine, if you're looking for super resolution on a portrait, or for a cat or dog, but you're gonna have a rough time if your composition is even slightly more complex than that. And frankly, there are easier ways to get great resolution on extremely simple compositions already, without resorting to giant, hyper-specific models.

    • @Exilum
      @Exilum ปีที่แล้ว

      @@michaelleue7594 I mean sure, I won't fight you on this. I do like bringing my guns to a sword fight though, so my hopes and dreams are still there.

    • @Exilum
      @Exilum ปีที่แล้ว

      @@michaelleue7594 (to clarify, comfyui allows you to work on sections of an image easily, so you can do 100x superresolution per-subject, then bind the seams using another model)

  • @oren000
    @oren000 ปีที่แล้ว

    Looks like the CSI "Enhance... enhance... enhance... " technology is here with us now.

  • @95TurboSol
    @95TurboSol ปีที่แล้ว

    When and where can we use this? I have a ton of old cell phone pictures I would love to upscale!

  • @Shunarjuna
    @Shunarjuna ปีที่แล้ว

    I can’t wait for all these things to come standard with new desktop and laptop computers.

  • @aadmi
    @aadmi ปีที่แล้ว

    Fun fact Raster images can be viewed as vectors with fast upscaling, downscaling

  • @thelazy0ne
    @thelazy0ne ปีที่แล้ว +7

    Well... The "enhance image" from Hollywood movies that anyone that ever played with Paint knew it was BS is now a real thing..... "Never say never" has never been more true.

    • @gwentarinokripperinolkjdsf683
      @gwentarinokripperinolkjdsf683 ปีที่แล้ว +15

      Just... probably don't use it in the court room

    • @TheTopTuber
      @TheTopTuber ปีที่แล้ว

      Kids in 2030: " Wow, is this CSI a memory pod or just top notch cinéma vérité? "

    • @glenneric1
      @glenneric1 ปีที่แล้ว

      don't forget it's hallucinating, not actually recalling real data

  • @doctorartin
    @doctorartin ปีที่แล้ว

    I wonder how it performs on photos of birthmarks and melanoma. Does it "hallucinate" OR identify the disease based on macroscopic images?

  • @rebeccawhite5333
    @rebeccawhite5333 ปีที่แล้ว +1

    Amazing video as always. Would really like to see the pre-pixalated images vs the upscaled ones but I'm assuming those weren't available

  • @zhin13
    @zhin13 ปีที่แล้ว +1

    "Zoom! Enhance!"

  • @drkpaladin777
    @drkpaladin777 ปีที่แล้ว

    The zoom and enhance feature from all those CSI shows finally works in real life!

    • @fitybux4664
      @fitybux4664 ปีที่แล้ว +2

      ENHANCE! ENHANCE! 😎

  • @AlphaVisionPro
    @AlphaVisionPro ปีที่แล้ว

    I'm testing GigaGan and it works very well.

  • @Yaddlezap
    @Yaddlezap ปีที่แล้ว

    Let's put Patterson-Gimlin footage through this

  • @mohammadrezadm1828
    @mohammadrezadm1828 ปีที่แล้ว

    can it be used to upscale videos? Consider that this feature is used in the browser and can see high quality video with low size!

  • @kenshi21
    @kenshi21 ปีที่แล้ว

    Everytime mind blowing papers.

  • @thekaxmax
    @thekaxmax ปีที่แล้ว +11

    Note for upscaling: remember that 100% of the added detail is made up, so you can't do the 'enhance' trick from TV and movies where they discover new information but unfuzzing a picture. Seeing what's there in a bad photo can give info by showing what's there, but details will still be made up.

    • @businessmanager7670
      @businessmanager7670 ปีที่แล้ว +2

      yes it makes a prediction based on the context of the scene, which would be an approximate representation of the actual scene. nobody disagrees with that.
      but what suprises is, with the way this technology can upscale images, unlike old technologies, where upscaling barely made a difference that is significant.

    • @thekaxmax
      @thekaxmax ปีที่แล้ว +5

      @@businessmanager7670 Yes. Just making the point that you can't add truth to an image no matter how good the AI. Unlike TV and movies, where they get a 'true' image they can act on. Note that some people _do_ believe this can be done.

    • @businessmanager7670
      @businessmanager7670 ปีที่แล้ว +1

      @@thekaxmax you can make a prediction of the truth though, which sometimes can be the actual Truth.
      that's the whole point with prediction systems like the brain and AI.
      sometimes our predictions can represent the truth.

    • @txorimorea3869
      @txorimorea3869 ปีที่แล้ว +3

      True, that is fabricating evidence and that is a crime.

    • @fitybux4664
      @fitybux4664 ปีที่แล้ว +1

      "As you can see here, if you take the reflected image from his sunglasses and ENHANCE ENHANCE ENHANCE!!! the pink elephant did it!" 😀

  • @alejmc
    @alejmc ปีที่แล้ว

    What a marvel of technology.
    Would it be possible to have a video of how/where to access these tools? Ideally as user friendly as possible first… for example DrawThings works even on iPads but it’s SDXL only to my knowledge and not GAN? (myself I don’t even know the difference yet).
    Thanks for these videos (and the free Raytracing courses, started watching those and they are a blast!)

  • @tartarosnemesis6227
    @tartarosnemesis6227 ปีที่แล้ว

    "Zoom in. More! Now enhance resolution..."
    A common movie quote now reality.

  • @vitriolveio
    @vitriolveio ปีที่แล้ว

    When will the public be able to try this out??

  • @AnthonyGoubard
    @AnthonyGoubard ปีที่แล้ว

    When looking at the pixelated photos, it's clear to me that it's pictures created with a mosaic effect from high resolution images. They are perfectly pixelated, no artifact (like often in JPEG format). So until someone else, like a journalist tests it on more realistic low resolution photos, I would remain caution about the upscaling claim.

  • @JorgetePanete
    @JorgetePanete ปีที่แล้ว

    What about "sticky textures" when moving the subject around? Does this one have that?

  • @fitybux4664
    @fitybux4664 ปีที่แล้ว +2

    Could you do a really good infinite zoom with these upscaling techniques? ENHANCE! ENHANCE! 😀

    • @glenneric1
      @glenneric1 ปีที่แล้ว +2

      it would become all hallucination very quickly

  • @motivation_hubPJ
    @motivation_hubPJ ปีที่แล้ว

    Hi doc please demonstrate on how can we use this demo

  • @hinro
    @hinro ปีที่แล้ว +1

    Has it been made available? The upscaling sounds pretty neat. run some old manga scans through it and see how it does.

    • @Vlow52
      @Vlow52 ปีที่แล้ว +1

      No, gotta wait until they implement it somewhere and start selling it

    • @DajesOfficial
      @DajesOfficial ปีที่แล้ว

      @@Vlow52 this is adobe. I am pretty certain I know where they will sell it

  • @EDToasty
    @EDToasty ปีที่แล้ว

    seeing Geoffrey Hinton's pixelated face staring in to my soul was not what i needed tonight

  • @panjak323
    @panjak323 ปีที่แล้ว +1

    Well "super resolution". It's pretty much making up the detail in the image.

  • @QuentinKim428
    @QuentinKim428 ปีที่แล้ว

    What a time to be alive!!!!!!!!!!!!!

  • @HogwartsStudy
    @HogwartsStudy ปีที่แล้ว

    what a time to be alive!

  • @ThankYouESM
    @ThankYouESM ปีที่แล้ว

    Awesome! However... I'm wondering if I missed the memo about A.I. finally generating hands perfectly.

  • @annesortland3947
    @annesortland3947 ปีที่แล้ว

    this new Technic is incredible

  • @wojciechfioka5819
    @wojciechfioka5819 ปีที่แล้ว

    Woooow!!! I will try it in some projects!🎉

  • @n0madfernan257
    @n0madfernan257 ปีที่แล้ว

    maybe it can now help viewing the skies better with a modest telescope. wat a time to be a.i. !

  • @henryogan2017
    @henryogan2017 ปีที่แล้ว +2

    Not gonna lie... This is probably the most legitimately exciting research I've seen in a while. This could very well be a first step towards ideal AI art creation, in my opinion

  • @zdenek7220
    @zdenek7220 ปีที่แล้ว

    ...enhance 34 to 36, pan right and pull back, stop, enhance 34 to 47... once there, Im hooked.

  • @elliotmarks06
    @elliotmarks06 ปีที่แล้ว

    Can't wait for the code to be released!

  • @Fx_Explains
    @Fx_Explains ปีที่แล้ว

    i can't wait these to be implemented in VR headsets.

  • @bingbang9643
    @bingbang9643 ปีที่แล้ว

    if this is not the best result for upscaling then what is it? would love to have an Ai that not only upscale but increases dynamic range and turns compressed or oversaturated images to be more raw looking... like turning an old phone camera look like a a new DSLR in terms of color, dynamic range, details, etc... if it makes sense.

  • @sighko05
    @sighko05 ปีที่แล้ว

    Detective: “Enhance… enhance… ENHANCE!! Would you look at that; I think we’ve got our guy. Send out an APB for a suspect with really strange hands.”

  • @randomtitbits1337
    @randomtitbits1337 ปีที่แล้ว

    As someone who makes PC mods for things like AI Background Upscale (Final Fantasy IX and Chrono Cross): Is this already usable via Python or whatever?

  • @andrewbrock8920
    @andrewbrock8920 ปีที่แล้ว +1

    See and click as usual…bravo!

  • @NeilMoore
    @NeilMoore ปีที่แล้ว

    When you're long gone, an ai will be continuing your work on youtube and it will say "what a time to be dead!" instead of "alive"

  • @nossir
    @nossir ปีที่แล้ว

    Remember those scenes in movies where they would pause a video on a security, zoom in and press the magic upscaling buttom? Well... It's now possible

  • @alexmattheis
    @alexmattheis ปีที่แล้ว

    Absolutly Amazing. 😄

  • @jbcom2416
    @jbcom2416 ปีที่แล้ว +1

    AI is progressing so rapidly with each month producing so many advances, that papers from just few months ago feels like ages ago.

    • @DajesOfficial
      @DajesOfficial ปีที่แล้ว

      This paper is 5 months old xD

    • @jbcom2416
      @jbcom2416 ปีที่แล้ว

      @@DajesOfficial why would you assume im talking about this particular paper

    • @DajesOfficial
      @DajesOfficial ปีที่แล้ว +1

      @@jbcom2416 why would you edit if that's not the case?

  • @delpinsky
    @delpinsky ปีที่แล้ว

    Out of this world! 🤩

  • @Ken1171Designs
    @Ken1171Designs ปีที่แล้ว

    Please correct me if I am wrong, but if it's 1 BILLION params, that probably means we cannot run it on a consumer-grade GPU with a 24GB VRAM limit. Not for mere mortals?

  • @badpuppy3
    @badpuppy3 ปีที่แล้ว

    I used to watch your videos with excitement. Now I watch them with dread.

  • @steffenaltmeier6602
    @steffenaltmeier6602 ปีที่แล้ว

    somehow the CSI "zoom in on the reflection" meme is becoming reality!