[HN Gopher] Upscayl - Free and Open Source AI Image Upscaler
       ___________________________________________________________________
        
       Upscayl - Free and Open Source AI Image Upscaler
        
       Author : faebi
       Score  : 279 points
       Date   : 2024-03-31 20:45 UTC (1 days ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | wruza wrote:
       | If like me you're using Real-ESRGAN-ncnn-vulkan [1] and are
       | curious what upscayl-ncnn CLI [2] changed from it, there's not
       | much and nothing substantial [3]. Not a criticism, just wanted to
       | learn whether it's worth upgrading to for a CLI tool ($subj is a
       | separate GUI app based on it).
       | 
       | [1] https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan
       | 
       | [2] https://github.com/upscayl/upscayl-ncnn
       | 
       | [3] https://github.com/xinntao/Real-ESRGAN-ncnn-
       | vulkan/compare/m...
        
         | pluto_modadic wrote:
         | I mean... if people prefer a GUI that's not a bad thing...
        
           | amelius wrote:
           | Especially for something involving graphics.
        
         | NayamAmarshe wrote:
         | Upscayl NCNN has several fixes (like latest vulkan, bug fixes,
         | feature additions) and is coming up with more soon (we just
         | haven't pushed the changes). Also working on CPU support.
         | 
         | If you're going to use Real-ESRGAN, you're going to have to
         | deal with a lot of issues and a codebase that hasn't been
         | updated in a long time. Afaik, Upscayl NCNN is the only project
         | maintaining Real-ESRGAN NCNN as of now.
        
           | wruza wrote:
           | I've only used -i -o -n mode, but for me that just works. And
           | when something just works, I tend to see "a codebase that
           | hasn't been updated in a long time" as a good thing generally
           | :)
           | 
           | (Don't take it personally, it's my burnout from modern
           | software cycles.)
        
             | NayamAmarshe wrote:
             | I understand. With Upscayl it's a little more configurable.
             | 
             | For example, you can add compression to the images, change
             | the format (which Real-ESRGAN can't always do), drag and
             | drop images, have extra models not shipped by default and
             | in future even have face enhancement.
        
         | __rito__ wrote:
         | I came to the comments just to ask this.
         | 
         | I have used RealESRGAN for some years now, and several pictures
         | hang on my house that were enlarged using this.
         | 
         | I enlarged a lot of old pictures from family albums, and then
         | fixed the bad spots with something like Photoroom, Snapseed,
         | etc., and then sent them to be printed.
         | 
         | Works really great.
         | 
         | And not only that, if I find an old picture on the internet
         | that is low res with no high res found after much google-fu,
         | Duckduckgo, or Kagi, I use RealESRGAN to upscale, and then use
         | it as my wallpaper, presentation background or whatever!
        
           | NayamAmarshe wrote:
           | Yes! I Real-ESRGAN is still the best algorithm for enhancing
           | images. The only algorithm better than it is Topaz's but
           | that's to be expected from a paid product.
           | 
           | Real-ESRGAN can get better with a better trained model too,
           | which is on Upscayl's roadmap.
        
             | sgc wrote:
             | Does anybody have experience training/finetuning Real-
             | ESRGAN models? I downloaded one of their datasets to see
             | what they are working with, and it has 800 images at ~3Mp
             | resolution. I am curious if others have results based on
             | higher resolutions + more/fewer images in the dataset? I
             | would like to use it for fine art paintings by period /
             | style, etc.
        
       | graevy wrote:
       | upscayl is very approachable, but lacked many features i needed.
       | i ended up using https://github.com/AUTOMATIC1111/stable-
       | diffusion-webui after upscaling became part of my regular
       | workflow, but for someone who just needs a few images enhanced,
       | it's an ideal tool.
        
       | zebomon wrote:
       | I tried this out back in December. It is very straightforward.
       | Would recommend for anyone who is testing the waters and just
       | trying to start exploring the various tools.
       | 
       | From my understanding though, the quality is pretty far behind
       | that of the cutting edge. A friend recently recommended Topaz to
       | me, but that isn't open source.
        
         | NayamAmarshe wrote:
         | The quality is actually comparable in some places. Upscayl
         | being a free project though, does not have its own model yet
         | and as such, we depend on community models (which are great in
         | their own right).
         | 
         | I do have plans to create our own robust model though, once I
         | collect enough money :)
         | 
         | https://ckovalev.com/midjourney-ai/guide/upscaling-ai-art-fo...
        
           | __rito__ wrote:
           | What models do you use to upscale images other than
           | RealESRGAN?
        
             | NayamAmarshe wrote:
             | We have a custom-models repository with several models.
             | Upscayl by default ships with 6 models.
        
         | kristopolous wrote:
         | extras tab in a1111 is really the best results I can get. You
         | need to know what all those options mean of course - it's a
         | more complicated interface for sure
        
         | EVa5I7bHFq9mnYK wrote:
         | xz utils is open source, so whats your point?
        
       | esafak wrote:
       | What's the state of the art?
        
         | liuliu wrote:
         | SUPIR and other diffusion based models.
        
           | NayamAmarshe wrote:
           | But doesn't that defeat the purpose of upscaling? I see a lot
           | of people promoting Magnific AI (which costs $40 a month) but
           | it's not really an upscaler. It's more of an AI repainter. It
           | replaces most details by re-imagining them instead of
           | guessing the original details. I think we should be clear
           | about what an AI Upscaler is and what an AI re-painter is.
        
             | liuliu wrote:
             | ESRGAN is the same thing. You cannot recover signal that
             | are already lost without additional information (in
             | Diffusion case, model's prior). Upscaler are hallucinators
             | by that definition.
        
               | wruza wrote:
               | But results differ in perception. ESRGAN doesn't
               | hallucinate whole [sub]objects and that puts it into a
               | different category. Latent/denoising i2i re-scale is
               | different because its parameter range doesn't really
               | intersect with what ESRGAN does.
        
               | cchance wrote:
               | It can only hallucinate if your i2i noise level is high
               | enough, if you're adding enough noise that the latent is
               | basically filling in giant swaths of noise areas then of
               | course its going to make up new stuff, thats not
               | hallucinations as much as you asking the AI to draw that
               | entire area as something new.
        
               | amelius wrote:
               | OK, but I do hope that the hallucinations disappear when
               | you downscale (normal resize) an upscaled image (?)
        
       | mrbluecoat wrote:
       | I used to laugh so hard at those tv and movie scenes when they
       | would "enhance" an image: https://youtu.be/LhF_56SxrGk
       | 
       | I guess yesterday's science fiction is now our reality.
        
         | palad1n wrote:
         | I think I've got a twitch now, when I think about this. How
         | those stupid moviemakers would say, "enhance!" and I (along
         | with many of my geek brethren) were like, "there are no more
         | pixels, that can't be done!"
         | 
         | And now it exists. "Enhance" exists.
        
           | kyriakos wrote:
           | Or does it? If you enhance security footage to make a barely
           | visible face recognizable it will make it but it won't be the
           | person in the footage anymore.
        
             | wood_spirit wrote:
             | It would be really interesting to see what it upscales poor
             | security footage to be when we know the people in the
             | picture; how accurate was it?
        
               | wruza wrote:
               | The models usually bundled with ESRGAN don't enhance like
               | CSI. They straighten lines and jpeg blocking a little and
               | correct "subatomic" details, but cannot restore large
               | areas like faces, objects, etc. It's more of an AI-
               | flavored "Effects - Sharpen" than stereotypical
               | "Enhance!".
        
               | 112233 wrote:
               | You probably remember this:
               | https://petapixel.com/2020/08/17/gigapixel-ai-
               | accidentally-a...
        
             | kookamamie wrote:
             | It does not exist. The AI models generate "what could be"
             | instead of "what was", i.e. they hallucinate heavily in
             | upscale tasks.
        
               | lostlogin wrote:
               | > It does not exist.
               | 
               | The MRI scanner near you is potentially using AI to
               | increase image signal, then to increase pixel count 4x
               | (well, 2x in X direction, 2x in Y direction. Potentially
               | also generating a slice between each slice in 3D
               | datasets).
               | 
               | If you turn off the AI and actually acquire the
               | information, the scan is long, the patient moves and it
               | is blurry. However if the patient is still, the non AI
               | images look like the AI images.
               | 
               | Disagreeing with it is sort of moot now - it's in the
               | machines and is running. It works well, I've been using
               | it daily for a few years.
               | 
               | All vendors have it - I use the Siemens product 'Deep
               | Resolve' [1]. Their PR department undersells it, in my
               | view this is a bigger change than the 1.5T to 3T
               | transition.
               | 
               | [1] https://www.siemens-healthineers.com/magnetic-
               | resonance-imag...
        
               | j16sdiz wrote:
               | The scanner is faster because it collect less data.
               | 
               | The image is sharper because it have more data.
               | 
               | Where did the missing data came from?
               | 
               | It came from the training data set, not the patient.
               | 
               | No matter how good the image look like, it is not
               | something from from the patient.
        
               | tomrod wrote:
               | Yet, it can be "close enough" for horseshoes, hand
               | grenades, and surgery.
        
               | JeremyNT wrote:
               | Which may well be, but those detectives still aren't
               | going to suddenly be able to read the license plate from
               | an "enhanced" blurry photo, like their TV counterparts
               | were doing back in the early 00s.
        
               | tomrod wrote:
               | Correct. And the extrapolation region for the MRI is
               | reasonable, I reckon, versus extrapolation into pulling
               | enhanced blurry photos!
        
               | jncfhnb wrote:
               | If the model learns that it can get fundamentally the
               | same information from a lower res scan then it's moot
               | though.
        
               | bozhark wrote:
               | We have 7T at my old uni in Alabama
        
           | spookie wrote:
           | The better example of "Enhance!" still remains this piece of
           | software: https://www.youtube.com/watch?v=19wgu5GZDhk
        
         | userbinator wrote:
         | It just hallucinates the details now.
        
           | pixelesque wrote:
           | Yes - I can't find it now, but a few weeks ago I saw a demo
           | website for some other upscaler with an example image of a
           | picture of food, and it was pretty clear that the upscaled
           | "version" was different bread than the original lower-res
           | version, and things like herb "sprinkles" (oregano?) in the
           | original became pine nuts or something in the upscaled
           | version....
        
             | NayamAmarshe wrote:
             | Yes, I personally think it's false advertising. AI Re-
             | painter is not AI Upscaling. I even received a review on
             | Mac App Store saying Upscayl is worse because it does
             | upscaling instead of repainting like Magnific.
        
         | forgingahead wrote:
         | The correct phrase should have been "Hallucinate!"
        
         | holoduke wrote:
         | Except that when you try to enhance the numberplate of a
         | suspected killer you get a platenumber which is based on
         | avarage noise and mqybe different than reality.
        
         | NayamAmarshe wrote:
         | > I guess yesterday's science fiction is now our reality.
         | 
         | That's actually what's written on https://upscayl.org, "From
         | Science Fiction to Reality" haha
        
       | sgilani wrote:
       | Is there something similar for video? Or is topaz still the only
       | option?
        
         | NayamAmarshe wrote:
         | I still have video upscaling planned for Upscayl but we're just
         | 2 people, working on Upscayl in our free time.
        
         | yterdy wrote:
         | Video2x/Waifu2x GUI. Unfortunately, the models they ship with
         | are tuned towards anime.
        
       | feverzsj wrote:
       | The upscaled image feels sharper but loses some detail.
        
         | NayamAmarshe wrote:
         | Every model will give you different results. You can try the
         | custom models as well to see what works for you :)
        
       | jiveturkey wrote:
       | This should have been called Enhanse (sticking with the
       | misspelling theme)
        
       | _fw wrote:
       | UpScayl is great, I use it a lot for work. Upscaling low-res
       | graphics and illustrations for use in graphics in a pinch,
       | upscaling portrait photos of people for print and photoshop...
       | upscaling old copies of things for editing purposes, you name it.
       | 
       | It's not perfect but no alternative is. Bloody useful though.
        
         | NayamAmarshe wrote:
         | I'm glad you like it! We're working on making it even better :D
         | and with the introduction of Upscayl Cloud the possibilities
         | for professionals will be endless (within reason of course,
         | haha)!
        
           | _fw wrote:
           | Like it? My brother I was trying to hide my enthusiasm to
           | look cool in front of people on YC.
           | 
           | I use UpScayl pretty much every day and doing so feels like
           | magic every time. Your user interface tweaks here and there
           | are always appreciated and UpScayl is a joy to use.
           | 
           | Feel proud, UpScayl is witchcraft and I love it
        
             | NayamAmarshe wrote:
             | Haha thank you so much! Always a joy to see a happy user!
             | 
             | Mind if I showcase your comment on the Upscayl website? :D
        
               | _fw wrote:
               | Yeah boiii. I'll email you a proper quote tomorrow if
               | that works?
        
               | NayamAmarshe wrote:
               | Yessir!
        
       | vouaobrasil wrote:
       | I wonder if image upscaling is actually reflective of a greater
       | disease in society: we are exceptionally obsessed with holding
       | onto everything. I mean, my God, if the situation comes down to a
       | desire to upscale an image, just let the image go.
        
         | drusepth wrote:
         | There are lots of reasons someone might want to upscale
         | something, not just "holding onto everything".
         | 
         | I painted something on my iPad over the last few weeks. I'll be
         | upscaling it so it's high enough resolution to do a large print
         | on my wall. It's not something I need to "just let the image
         | go" for.
         | 
         | (And, of course, there's nothing wrong with holding onto
         | things...)
        
       | pvankessel wrote:
       | Are there any models out there for cleaning up an image, not just
       | upscaling? I have a bunch of old photos taken on early low-res
       | point-and-shoots that have JPEG artifacts etc and this seems like
       | something a modern model could easily be fine-tuned to resolve,
       | but every few months I look around and have yet to find anything
        
         | iampims wrote:
         | Check out these models:
         | https://replicate.com/collections/image-restoration
         | 
         | Most of them can be run locally, but I'd recommend testing them
         | with replicate before investing in understanding
         | cog/docker/hf...
        
           | pvankessel wrote:
           | Oh this sounds like exactly like what I've been looking for,
           | can't wait to give these a try - many thanks
        
       | yterdy wrote:
       | Unfortunately, for video, nothing I've seen yet has matched the
       | quality of Topaz Labs' (paid) tool. Clarity and consistency
       | always seem to be an issue with other implementations. If love to
       | be proven wrong because I have a project that's stalled due to
       | the low quality/resolution of the source.
        
       | aktuel wrote:
       | I still find current upscalers surprisingly underwhelming
       | compared to advances in other areas.
        
       | ewuhic wrote:
       | On a related note, what would be the equivalent app for watermark
       | removal?
        
       | p0w3n3d wrote:
       | Another upscaler, for images and video
       | 
       | https://github.com/k4yt3x/video2x
        
       ___________________________________________________________________
       (page generated 2024-04-01 23:02 UTC)