heywood on 13/2/2024 at 23:44
What if skills are the real filter, and using AI tools allows us to express our imagination more richly and more directly?
Azaran's TTLG taverns were immediately familiar because I've imagined the same before, but I could never draw them myself.
Sulphur on 14/2/2024 at 02:26
Nothing's really stopping you from asking ChatGPT to give you prompts for interesting images to feed into DALL-E 3 et al. And if it's not great at it today, it'll be better at it tomorrow thanks to us; humans are built into the improvement algorithm anyway.
mxleader on 14/2/2024 at 03:01
Quote Posted by demagogue
AI taking over people's imaginations isn't a good thing in the cosmic scheme of things. It's not just that we get a flood of mediocre AI-generated tripe. I think we're already getting that now. But beyond that, it's that humans get detached from handling their own imaginations, and there's a filter there that shouldn't be there.
I agree but is there a huge difference between using text prompts to create AI art which requires writing skills and the ability to imagine and articulate directions? Also, people have been coding machines to make video games for decades now so there are some similarities. At the same time a human artist can more easily create what is in their head by physically doing the work. AI art generators are literally just fun and games at this point.
heywood on 14/2/2024 at 14:56
I think the average person can create the imagery in their head more easily using these tools. If you're not a well practiced artist, drawing and painting what's in your head is hard.
demagogue on 14/2/2024 at 18:09
Quote Posted by heywood
I think the average person can create the imagery in their head more easily using these tools.
Yes, this is actually part of my point, though I may be trying to be too subtle with this, and I don't know how well this stands up to scrutiny. But I think there's a fine line between translating what's in your head on to the page and the generation of the idea in your head. I know this for music, but I think it applies to visual arts as well, also dance, martial arts, a lot of things...
But to stick with music, when you learn to play an instrument, you know, you're doing scales, chords, arpeggios, runs, or whatever, and you're getting the feel of the instrument in your hands, where there's this coordination between your body, the instrument, and the sound, and that's where the ideas come from. Like your musical mind and fingers are guiding you create inspired music before your thinking mind can even catch up to understand where it's coming from. I have an idea there's a similar process when you're learning to paint or draw, with the feeling of the brush or the pen in your hands, and the ways it wants to move for art to come out.
That's what AI is taking away. Now it's a cognitive exercise where you build this image in your head divorced from the process... Well, let me step back. I think it's a new art with its own process. I think there's an art to understanding how prompts work, knowing how to iterate on parts to build up an image piece by piece, and even building up the model -- though I think a lot of people are going to just take what's already out there.
So what I'd say is that I recognize it as its own legitimate art, and power to the people that are thinking about how to use the process in inspired ways. But I think something is being lost when people lose the embodied part of most arts, the feel of the pen or the guitar in your hands, and the coordination between mind, body, and art/sound that emerges from deep recesses of your mind that even you didn't know you had in you until it comes out. If that feel is the source of a lot of what is inspired about art, then AI would actually be generating the important part, and there's not much coming from the person anymore. I'm fine with AI as this new art form, but I wouldn't want to see it undermining that, if that's what it's doing.
-----
Edit: Also it reminds me of a common thing I hear in jazz... I think Brad Mehldau said it in his interview with Rick Beato just yesterday, and Adam & Peter say it all the time on their You'll Hear It jazz podcast, but I think even a few days ago. Practice is supposed to be too hard! You're not making progress unless you're trying something that is beyond your ability, and practice it until you get it. When the things you're practicing start becoming easy, that's a signal that you need to take the next step into techniques that you can't do yet. Something being too hard is your map to the direction you need to go. AI is also taking that away, so art isn't a journey anymore. That would be a particularly bad loss.
Aja on 14/2/2024 at 18:23
I wonder if there's a parallel, dema, between using AI to create art and using a synthesizer or other software to create music. When I'm using my eurorack, I almost never have a sense in advance what I want to do. I experiment, mess around, and when I hear something I like, I focus on it and embellish it until I'm satisfied. I've heard it said that the key to being a good electronic musician is not necessarily mastery of an instrument but rather the ability to curate your own work, to know when what you have is good and what to do with it. In that sense using AI to create the kinds of videos that Azaran posted above doesn't feel especially different; it's all about experimenting with your tools and knowing when to keep what's good.
demagogue on 14/2/2024 at 19:02
As you know I synth a lot too, especially now with my Deluge. The thing is made for experimentation. Anyway that's why I stopped myself and said I recognize that using AI as a tool can be legitimate and inspired too. But I think there's still a difference between playing the tool and the tool playing you, so to speak. Really I think it's not the AI itself, it's a culture that can build around it where the user isn't really putting any thought into it anymore. They could, but in practice they're not as much.
I don't think it's even new. Even with a normal instrument, people might coast thoughtlessly playing, e.g., the pentatonic and few blues licks they know over and over. So it's the equivalent of that, but the difference is the AI can take that and add a lot of polish. I suppose there's technique in curating the sound over iterations, so they still could put thought into that. I guess the difference is there's less incentive to put thought into one's craft when you're starting out and you don't know what's what. With an instrument and especially synths, the learning curve forces you into uncomfortable places where you have to learn your way around. AI might trick many just getting into it that they don't have to go through that learning curve to get some result, even though a lot may still not be satisfied and want to push through learning the system better.
Azaran on 14/2/2024 at 19:57
They just updated our Dall E 3, and now it only generates about half the time it used to. Otherwise, it just hangs in generating mode forever, which I imagine is its deceptive way of censoring prompts.
I wonder what's so objectionable about "group of people dressed in black, inside a cave with frescos"?
The censorship is really getting absurd.
And they're not even transparent about what exactly they censor. I guess they don't want the public to know their inner algorithm?
Anyway, here's a redo of an old prompt I had done with Wombo years ago, dogs playing with sapphires on beach
Inline Image:
https://i.postimg.cc/XvjDvsGC/250573ed-0265-4ac4-b1a9-fc1fe2c45e75-1706710264803.png
mxleader on 15/2/2024 at 02:36
Quote Posted by Azaran
They just updated our Dall E 3, and now it only generates about half the time it used to. Otherwise, it just hangs in generating mode forever, which I imagine is its deceptive way of censoring prompts.
I wonder what's so objectionable about "group of people dressed in black, inside a cave with frescos"?
The censorship is really getting absurd.
And they're not even transparent about what exactly they censor. I guess they don't want the public to know their inner algorithm?
Anyway, here's a redo of an old prompt I had done with Wombo years ago, dogs playing with sapphires on beach
This is completely unrelated to this thread but I was in the middle of trying to defeat you last night during mission 10 of the Black Parade. Need to get back to it. :cheeky:
demagogue on 15/2/2024 at 07:24
Anyway (
https://www.facebook.com/groups/officialmidjourney/posts/727144782910422/) this is cool. It took me a bit of time to even realize it wasn't real.
(It's 3D. You can scroll around. I don't think the forum code will allow me to actually embed it in this post.)
I'm wondering how long it will be before someone figures out how to generate 3D architecture and texture it based off of a Midjourney, et al, render. It could be amazing to walk around inside some of these worlds.