Loopy Pro: Create music, your way.

What is Loopy Pro?Loopy Pro is a powerful, flexible, and intuitive live looper, sampler, clip launcher and DAW for iPhone and iPad. At its core, it allows you to record and layer sounds in real-time to create complex musical arrangements. But it doesn’t stop there—Loopy Pro offers advanced tools to customize your workflow, build dynamic performance setups, and create a seamless connection between instruments, effects, and external gear.

Use it for live looping, sequencing, arranging, mixing, and much more. Whether you're a live performer, a producer, or just experimenting with sound, Loopy Pro helps you take control of your creative process.

Download on the App Store

Loopy Pro is your all-in-one musical toolkit. Try it for free today.

"A.I." (Machine Learning Algorithms) To Generate Art

1568101123

Comments

  • edited August 2022

    @monz0id said:

    @auxmux said:
    None of us is advocating replacing artists and designers.

    What you advocate is neither here nor there. You have zero control over where this will go, and whose livelihoods it will destroy.

    Likewise, it remains to be seen how this will impact things at scale.

    I'm sure there were priests who hated print because they were like who will need manuscripts now. Same thing when photography was seen as replacing paintings.

  • edited August 2022

    @AudioGus I'm finding DreamStudio pretty literal so far and I'm not liking the results compared to dalle or midjourney. I'm testing using the same prompts I used before. This is especially true when using different artist interpretations. Seems like it might be not that as good as combining abstract concepts.

  • Further down the line, can we imagine the coming death of internet? When there is no way to tell what is autogenerated or not, be it text, images, sounds or videos, whether interactions are people or bots, whether that political discussion is actually real or just some prompt-engineered result ... people give up on internet and go to the town square for physical interaction instead :D Time to short the big tech stocks, you heard it here first. Has this movie or novel already been done?

  • edited August 2022

    @AudioGus said:

    @monz0id said:

    @auxmux said:

    @monz0id said:

    @auxmux said:
    I guess we should've stopped at the printing press too.

    Why? It's been quite a useful invention for authors, so I've been told.

    Because it made the replication of knowledge too easy and for the masses. 😄

    Knowledge, generally, is a good thing. Creativity and passion is a good thing.

    Typing some words into a piece of software that scrapes existing artists and photographers work without permission, and passes off the results as art or illustration, is not a good thing.

    Because ultimately it can destroy the livelihoods of the actual professionals who created the original work that's being scraped, they'll have to stop doing it, and then all we'll have to look at is random, soulless wallpaper.

    But hey, surf the wave, man.

    I get what you are saying but that isn't really how this works. When you type a prompt in, the AI does not go to the internet looking for images. You can actually run this stuff locally offline. If you are interested there are a bunch of videos that describe diffusion rendering and how datasets are made and what latent space is etc. It is not like a database of images that are then copy/pasted/rearranged. It is more like how a person can learn what something looks like and has the skill to reproduce it, but obviously that is not required for a person to use this.

    But yah, nerd stuff aside, this will dramatically impact a lot of livelihoods and unfortunately some people will not be able to adapt or may essentially be edged out in part by their own work having been machine learned from.

    Machine learning and (eventually) artificial intelligence and general purpose robots are going to replace literally ALL professionals who have spent a lifetime honing their craft. Why? Because of demand. The supply of professionals continues to drastically decrease due to demographic changes worldwide. There is a massive contraction of skilled labor, but an increase in demand for these professionals and their services. The rise of the "artificial professional" addresses this.

    And on a related note, in Tesla's upcoming "A.I. Day" presentation on September 30th they are expected to unveil a working prototype of their "Optimus" general purpose robot worker. Depending on how it goes, they plan on releasing a version of this robot next year.

  • @AudioGus said:

    @echoopera said:
    What’s the max resolution for Stable Diffusion renders @AudioGus is it still limited to 1024x1024?

    I am not sure. 960 x 512 is as large as I go (for 16:9) and then Topaz Gigapixel is great for uprezzing for presentations. Typically I 3d / overpaint everything that makes the filter so I dont need tons of pixels.

    Fwiw, I’ve been using Pixelmator Photo to upres everything from MidJourney with great success.

    Yah Pixelmator I think is the best on iOS.

    Oh cool...going to try this out. I've been looking for a solution on the desktop. I know that Pixelmator Photo is headed to the Mac as well....but this might be better.

    Thanks!

  • @auxmux said:
    @AudioGus I'm finding DreamStudio pretty literal so far and I'm not liking the results compared to dalle or midjourney. I'm testing using the same prompts I used before. This is especially true when using different artist interpretations. Seems like it might be not that as good as combining abstract concepts.

    The same prompts will not work. You need to get to know the Ai and prompt accordingly.

  • @echoopera said:

    @AudioGus said:

    @echoopera said:
    What’s the max resolution for Stable Diffusion renders @AudioGus is it still limited to 1024x1024?

    I am not sure. 960 x 512 is as large as I go (for 16:9) and then Topaz Gigapixel is great for uprezzing for presentations. Typically I 3d / overpaint everything that makes the filter so I dont need tons of pixels.

    Fwiw, I’ve been using Pixelmator Photo to upres everything from MidJourney with great success.

    Yah Pixelmator I think is the best on iOS.

    Oh cool...going to try this out. I've been looking for a solution on the desktop. I know that Pixelmator Photo is headed to the Mac as well....but this might be better.

    Thanks!

    I already have Pixelmator Pro on desktop. It has been available for some time.

  • @NeuM said:

    @echoopera said:

    @AudioGus said:

    @echoopera said:
    What’s the max resolution for Stable Diffusion renders @AudioGus is it still limited to 1024x1024?

    I am not sure. 960 x 512 is as large as I go (for 16:9) and then Topaz Gigapixel is great for uprezzing for presentations. Typically I 3d / overpaint everything that makes the filter so I dont need tons of pixels.

    Fwiw, I’ve been using Pixelmator Photo to upres everything from MidJourney with great success.

    Yah Pixelmator I think is the best on iOS.

    Oh cool...going to try this out. I've been looking for a solution on the desktop. I know that Pixelmator Photo is headed to the Mac as well....but this might be better.

    Thanks!

    I already have Pixelmator Pro on desktop. It has been available for some time.

    Pixelmator Photo is a different app and being ported to Mac now.

  • @echoopera said:

    @AudioGus said:

    @echoopera said:
    What’s the max resolution for Stable Diffusion renders @AudioGus is it still limited to 1024x1024?

    I am not sure. 960 x 512 is as large as I go (for 16:9) and then Topaz Gigapixel is great for uprezzing for presentations. Typically I 3d / overpaint everything that makes the filter so I dont need tons of pixels.

    Fwiw, I’ve been using Pixelmator Photo to upres everything from MidJourney with great success.

    Yah Pixelmator I think is the best on iOS.

    Oh cool...going to try this out. I've been looking for a solution on the desktop. I know that Pixelmator Photo is headed to the Mac as well....but this might be better.

    Thanks!

    Gigapixel Topaz has a few different modes you can select as well as noise and blur functions. It also does batch images so great for animation or series of images. There is a free demo too, oh and it works as a photoshop plugin of sorts.

  • @AudioGus said:

    @auxmux said:
    @AudioGus I'm finding DreamStudio pretty literal so far and I'm not liking the results compared to dalle or midjourney. I'm testing using the same prompts I used before. This is especially true when using different artist interpretations. Seems like it might be not that as good as combining abstract concepts.

    The same prompts will not work. You need to get to know the Ai and prompt accordingly.

    Hmm, ok, I'll play with it some more.

  • @auxmux said:

    @NeuM said:

    @echoopera said:

    @AudioGus said:

    @echoopera said:
    What’s the max resolution for Stable Diffusion renders @AudioGus is it still limited to 1024x1024?

    I am not sure. 960 x 512 is as large as I go (for 16:9) and then Topaz Gigapixel is great for uprezzing for presentations. Typically I 3d / overpaint everything that makes the filter so I dont need tons of pixels.

    Fwiw, I’ve been using Pixelmator Photo to upres everything from MidJourney with great success.

    Yah Pixelmator I think is the best on iOS.

    Oh cool...going to try this out. I've been looking for a solution on the desktop. I know that Pixelmator Photo is headed to the Mac as well....but this might be better.

    Thanks!

    I already have Pixelmator Pro on desktop. It has been available for some time.

    Pixelmator Photo is a different app and being ported to Mac now.

    What's the difference?

  • @auxmux said:

    Same thing when photography was seen as replacing paintings.

    But photography didn’t take the actual work of artists, to be used as their replacement. It’s not the same thing.

  • @monz0id said:

    @auxmux said:

    Same thing when photography was seen as replacing paintings.

    But photography didn’t take the actual work of artists, to be used as their replacement. It’s not the same thing.

    If you look up the early complaints about photography, which is well documented from the 1800s, you'll see there were very similar complaints. That painters would be rendered obsolete by photography, because it was too easy and quick.

  • @auxmux said:

    @monz0id said:

    @auxmux said:

    Same thing when photography was seen as replacing paintings.

    But photography didn’t take the actual work of artists, to be used as their replacement. It’s not the same thing.

    If you look up the early complaints about photography, which is well documented from the 1800s, you'll see there were very similar complaints. That painters would be rendered obsolete by photography, because it was too easy and quick.

    That doesn’t make it the same.

  • edited August 2022

    Conceptually it is. New technology + conceived perception that it will replace existing skilled labor. But I think it's best not to keep arguing back and forth.

    While I'm not an art historian, one can think of how photography actually pushed painting towards abstract art in some ways, since replication of realistic forms (which were often overly idealized e.g. Bougoureau) was no longer needed. If we think more positively, AI art may push traditional/digital art in new directions that we can't yet imagine.

  • edited August 2022

    @auxmux said:
    Conceptually it is. New technology + conceived perception that it will replace existing skilled labor. But I think it's best not to keep arguing back and forth.

    Are you deliberately ignoring the point I’ve made?

    AI software can do what it’s doing as it has scraped existing artwork and photos, from the very artists it may potentially replace, and spits them out as ‘new’ content.

    Photography, as far as I’m aware, didn’t evolve from mashing up Dali’s old canvases and regurgitating them in the darkroom as a portrait of Aunt Maude.

    It’s a totally separate medium and technology, that doesn’t require existing artists work to exist.

    So it isn’t a valid comparison.

  • edited August 2022

    @AudioGus said:

    @echoopera said:

    @AudioGus said:

    @echoopera said:
    What’s the max resolution for Stable Diffusion renders @AudioGus is it still limited to 1024x1024?

    I am not sure. 960 x 512 is as large as I go (for 16:9) and then Topaz Gigapixel is great for uprezzing for presentations. Typically I 3d / overpaint everything that makes the filter so I dont need tons of pixels.

    Fwiw, I’ve been using Pixelmator Photo to upres everything from MidJourney with great success.

    Yah Pixelmator I think is the best on iOS.

    Oh cool...going to try this out. I've been looking for a solution on the desktop. I know that Pixelmator Photo is headed to the Mac as well....but this might be better.

    Thanks!

    Gigapixel Topaz has a few different modes you can select as well as noise and blur functions. It also does batch images so great for animation or series of images. There is a free demo too, oh and it works as a photoshop plugin of sorts.

    Wow...this thing is amazing! Thanks for the info. Good to have this on the desktop. Now I don't have to worry about /Fast rendering limits on MJ :)

    Does a great job on upressing: No Post Work to color grade and add bits and bobs...but great to build on top of.

  • @monz0id said:

    @auxmux said:
    Conceptually it is. New technology + conceived perception that it will replace existing skilled labor. But I think it's best not to keep arguing back and forth.

    Are you deliberately ignoring the point I’ve made?

    AI software can do what it’s doing as it has scraped existing artwork and photos, from the very artists it may potentially replace, and spits them out as ‘new’ content.

    Photography, as far as I’m aware, didn’t evolve from mashing up Dali’s old canvases and regurgitating them in the darkroom as a portrait of Aunt Maude.

    It’s a totally separate medium and technology, that doesn’t require existing artists work to exist.

    So it isn’t a valid comparison.

    I agree, both the painter and photographer were both human, the competition this time is definitely not.

    Those AI machines are certainly ‘gas guzzlers’, to think resources will be magically produced from the ether to sustain both humanity and AI is quite an assumption, we have trouble sustaining ourselves, but maybe they’ll machine learn themselves with more efficiency and trim us down to better efficiency too.

  • @auxmux said:

    @AudioGus said:

    @auxmux said:
    @AudioGus I'm finding DreamStudio pretty literal so far and I'm not liking the results compared to dalle or midjourney. I'm testing using the same prompts I used before. This is especially true when using different artist interpretations. Seems like it might be not that as good as combining abstract concepts.

    The same prompts will not work. You need to get to know the Ai and prompt accordingly.

    Hmm, ok, I'll play with it some more.

    By that token though it does not lean abstract like MJ does, which is why it is more of a commercial art disrupter. It may not be able to do what you want. I do still use Mj for more mashup weird stuff still.

  • edited August 2022

    @monz0id said:

    @auxmux said:
    Conceptually it is. New technology + conceived perception that it will replace existing skilled labor. But I think it's best not to keep arguing back and forth.

    Are you deliberately ignoring the point I’ve made?

    AI software can do what it’s doing as it has scraped existing artwork and photos, from the very artists it may potentially replace, and spits them out as ‘new’ content.

    Photography, as far as I’m aware, didn’t evolve from mashing up Dali’s old canvases and regurgitating them in the darkroom as a portrait of Aunt Maude.

    It’s a totally separate medium and technology, that doesn’t require existing artists work to exist.

    So it isn’t a valid comparison.

    Even drawing completely from public domain sources and adding new video and procedural 3d renders these things would soon still be just as powerful, if not even more than they are now. 'Taking a snapshot of the internet as it is today' which is what the current researchers say, is really just a shortcut.

  • edited August 2022

    @knewspeak said:

    Those AI machines are certainly ‘gas guzzlers’, to think resources will be magically produced from the ether to sustain both humanity and AI is quite an assumption, we have trouble sustaining ourselves, but maybe they’ll machine learn themselves with more efficiency and trim us down to better efficiency too.

    Looking at the quality of the current mutated output that's still relatively close to the source content, I doubt it though. They'll need to keep guzzling that arty gas...FEED ME!

    @AudioGus said:

    Even drawing completely from public domain sources these things would soon still be capable of completely disrupting many art careers.

    Yep, the scope for disruption is potentially endless. If it scrapes new source content. If it's only reference is what it's already produced, then it ain't gonna be pretty:

    'Siri, can you draw a picture of the Eiffel Tower, in the midst of a sandstorm?'

    Three minutes of mangled steel, twisted dolls heads and rotten leaves later...

    'Siri...that isn't...quite...what I asked for...'

    At present, artists jobs are safe. But it all depends on how good the generated stuff becomes, and the lowering of expectations from those commissioning the artwork.

  • @monz0id said:

    @knewspeak said:

    Those AI machines are certainly ‘gas guzzlers’, to think resources will be magically produced from the ether to sustain both humanity and AI is quite an assumption, we have trouble sustaining ourselves, but maybe they’ll machine learn themselves with more efficiency and trim us down to better efficiency too.

    Looking at the quality of the current mutated output that's still relatively close to the source content, I doubt it though. They'll need to keep guzzling that arty gas...FEED ME!

    @AudioGus said:

    Even drawing completely from public domain sources these things would soon still be capable of completely disrupting many art careers.

    Yep, the scope for disruption is potentially endless. If it scrapes new source content. If it's only reference is what it's already produced, then it ain't gonna be pretty:

    'Siri, can you draw a picture of the Eiffel Tower, in the midst of a sandstorm?'

    Three minutes of mangled steel, twisted dolls heads and rotten leaves later...

    'Siri...that isn't...quite...what I asked for...'

    At present, artists jobs are safe. But it all depends on how good the generated stuff becomes, and the lowering of expectations from those commissioning the artwork.

    I am pretty sure there are enough public domain pictures of the Eifel Tower and sandstorms that Stable Diffusion would render it completely accurately if only limited to those sources.

  • @AudioGus said:

    @monz0id said:

    @knewspeak said:

    Those AI machines are certainly ‘gas guzzlers’, to think resources will be magically produced from the ether to sustain both humanity and AI is quite an assumption, we have trouble sustaining ourselves, but maybe they’ll machine learn themselves with more efficiency and trim us down to better efficiency too.

    Looking at the quality of the current mutated output that's still relatively close to the source content, I doubt it though. They'll need to keep guzzling that arty gas...FEED ME!

    @AudioGus said:

    Even drawing completely from public domain sources these things would soon still be capable of completely disrupting many art careers.

    Yep, the scope for disruption is potentially endless. If it scrapes new source content. If it's only reference is what it's already produced, then it ain't gonna be pretty:

    'Siri, can you draw a picture of the Eiffel Tower, in the midst of a sandstorm?'

    Three minutes of mangled steel, twisted dolls heads and rotten leaves later...

    'Siri...that isn't...quite...what I asked for...'

    At present, artists jobs are safe. But it all depends on how good the generated stuff becomes, and the lowering of expectations from those commissioning the artwork.

    I am pretty sure there are enough public domain pictures of the Eifel Tower and sandstorms that Stable Diffusion would render it completely accurately if only limited to those sources.

    It was a joke Gus, though potentially accurate if they used your spelling ;)

    Replace ‘Eiffel Tower’ with something new that they haven’t scraped.

  • edited August 2022

    Anyone seen this one?
    https://apps.apple.com/mr/app/voiceart/id1635947799
    Free app (appears to be unlimited but with occasional ads) and uses Stable Diffusion apparently.
    Oh and iPhone only but works on iPad with usual scaling issue

  • @monz0id said:

    @AudioGus said:

    @monz0id said:

    @knewspeak said:

    Those AI machines are certainly ‘gas guzzlers’, to think resources will be magically produced from the ether to sustain both humanity and AI is quite an assumption, we have trouble sustaining ourselves, but maybe they’ll machine learn themselves with more efficiency and trim us down to better efficiency too.

    Looking at the quality of the current mutated output that's still relatively close to the source content, I doubt it though. They'll need to keep guzzling that arty gas...FEED ME!

    @AudioGus said:

    Even drawing completely from public domain sources these things would soon still be capable of completely disrupting many art careers.

    Yep, the scope for disruption is potentially endless. If it scrapes new source content. If it's only reference is what it's already produced, then it ain't gonna be pretty:

    'Siri, can you draw a picture of the Eiffel Tower, in the midst of a sandstorm?'

    Three minutes of mangled steel, twisted dolls heads and rotten leaves later...

    'Siri...that isn't...quite...what I asked for...'

    At present, artists jobs are safe. But it all depends on how good the generated stuff becomes, and the lowering of expectations from those commissioning the artwork.

    I am pretty sure there are enough public domain pictures of the Eifel Tower and sandstorms that Stable Diffusion would render it completely accurately if only limited to those sources.

    It was a joke Gus, though potentially accurate if they used your spelling ;)

    Replace ‘Eiffel Tower’ with something new that they haven’t scraped.

    Is it scraping when a human learns from a photo? Asking for a friend.

  • @AudioGus said:

    Is it scraping when a human learns from a photo? Asking for a friend.

    Learns? You mean using photo reference?

    You can use one as derivative reference, with permission. So no, not like scraping.

  • @monz0id said:

    @AudioGus said:

    Is it scraping when a human learns from a photo? Asking for a friend.

    Learns? You mean using photo reference?

    You can use one as derivative reference, with permission. So no, not like scraping.

    With permission?

  • edited August 2022

    @AudioGus said:

    @monz0id said:

    @AudioGus said:

    Is it scraping when a human learns from a photo? Asking for a friend.

    Learns? You mean using photo reference?

    You can use one as derivative reference, with permission. So no, not like scraping.

    With permission?

    Yes. Unless it’s very loosely used.

  • edited August 2022

    @monz0id said:

    @AudioGus said:

    @monz0id said:

    @AudioGus said:

    Is it scraping when a human learns from a photo? Asking for a friend.

    Learns? You mean using photo reference?

    You can use one as derivative reference, with permission. So no, not like scraping.

    With permission?

    Yes.

    So if I wanted to learn to draw like Bill Watterson I need to ask his permission?

  • edited August 2022

    @AudioGus said:

    @monz0id said:

    @AudioGus said:

    @monz0id said:

    @AudioGus said:

    Is it scraping when a human learns from a photo? Asking for a friend.

    Learns? You mean using photo reference?

    You can use one as derivative reference, with permission. So no, not like scraping.

    With permission?

    Yes.

    So if I wanted to learn to draw like Bill Watterson I need to ask his permission?

    < ignore button activated >

Sign In or Register to comment.