I’ll say it again because I always do. I’ve never seen AI art that I couldn’t tell was AI generated . It’s always wrong. The light source is always wrong, like the lighting is painted on subjects instead of cast onto them. And it lacks imperfections caused by human hand. Maybe it’s the photographer in me, but I’ve never seen believable lighting in AI art
Interesting Global News
What is global news?
Something that happened or was uncovered recently anywhere in the world. It doesn't have to have global implications. Just has to be informative in some way.
Post guidelines
Title format
Post title should mirror the news source title.
URL format
Post URL should be the original link to the article (even if paywalled) and archived copies left in the body. It allows avoiding duplicate posts when cross-posting.
[Opinion] prefix
Opinion (op-ed) articles must use [Opinion] prefix before the title.
Rules
1. English only
Title and associated content has to be in English.
2. No social media posts
Avoid all social media posts. Try searching for a source that has a written article or transcription on the subject.
3. Respectful communication
All communication has to be respectful of differing opinions, viewpoints, and experiences.
4. Inclusivity
Everyone is welcome here regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, education, socio-economic status, nationality, personal appearance, race, caste, color, religion, or sexual identity and orientation.
5. Ad hominem attacks
Any kind of personal attacks are expressly forbidden. If you can't argue your position without attacking a person's character, you already lost the argument.
6. Off-topic tangents
Stay on topic. Keep it relevant.
7. Instance rules may apply
If something is not covered by community rules, but are against lemmy.zip instance rules, they will be enforced.
Companion communities
- [email protected] - International and local legal news.
- [email protected] - Technology, social media platforms, informational technologies and tech policy.
- [email protected] - Interesting articles, projects, and research that doesn't fit the definition of news.
- [email protected] - News and information from Europe.
Icon attribution | Banner attribution
Survivorship bias
You haven't taken the time to train your own stable diffusion model on an artist's work who is good at lighting. Shadow length and skew drawn by a suggested light source is pretty easy for SD models to start getting right, especially if they're working from a gallery of one art style/type of composition. The article is stating what should be obvious to everyone at this point: this existed before the AI boom and you didn't recognize it until the layman had access to the technology and didn't refine the model or prompts to get these things right.
Oh I don’t work with the stuff, it’s just from what I’ve seen. I don’t really find any AI art I’ve seen to be this big impressive thing. I’m more interested in it from a data standpoint. I feel like not actually making your own art feels kind of depressing. Like what’s the point? Unless it’s for commercial use? Like if I feel creative, I’m going to make something.
Like I used to write, and I feel like if I wanted to write, I’d write. I don’t see the point in “writing” a prompt that pulls from other people’s work. Like what would I get out of it?
Yeah, commercial applications for it are great. It Makes life easier, lowers the barrier to entry, and hopefully will result in less work.
But for purely creative and cultural reasons, I just don’t see the point. Like I know nothing is original and we all pull from somewhere, but part of the enjoyment —to me— is the process of learning, of researching, reading other’s work to hone my craft.
And art without that is soulless and not an act of expression that comes from the deep reaches of ourselves.
It’s as empty as somebody buying a race car and a team to manage it, versus someone building their own and knowing every inch of it.
This whole discussion on wherever AI can create art or not is a bit dull IMO.
To me it is clear, only humans can create art, because art is part of a human expression of an novel (to them) inner process and thought. Not everything humans do is art, much of it is repetitive. Humans can use any tools to create stuff, art or no art, including AI. Humans can suck at the actual creation process, but still produce art.
So if someone enters 3 words into a AI generation model, and chooses an image, or something, they are not producing art, they are shopping. If they spend time tweaking and adapting models and prompts to help them realize what they want to express, then they are doing art.
I agree, it's all about the artist's control of the art. Drawing, writing, programming, etc takes magnitudes more time and effort than asking a GenAI model, and therefore provides much more control.
Without control, the rest of the art is made up of whatever the GenAI extrapolated from the prompt, and that's not interesting.
I am not so sure about control or effort, there is art, made by humans, that let a leaky bucket of paint swing over a canvas. It is simple to do, not much effort involved, without much control, but since it is done in a novel process, it still is art IMO.
Now if someone reads about this, and replicates it once, it might still art be, because it is new to them. But if anyone repeats it over and over, it is no longer art, but practice. Because the novel approach is missing. Generative AI do not produce art by themselves, because they just generate more of the same.
It is not possible to decide wherever it is art or not by just looking at the product. But you can like or dislike it anyway.
Art is also partly in the eye of the beholder, because it might be novel to them, even if it isn't novel to the creator.
You mean when you strip away people's knee-jerk negative bias to AI art, people really just like art that looks good? Shocking. It's almost as if the push against AI art is futile as, despite people's complaints, it can pretty consistently produce good outputs.
not everything you don't like is knee-jerk reaction...
a lot of people have minds with or without your ability to imagine other perspectives
People had the same complaints about photography many years ago. Times change.
People putting boundaries on what is and isn't art has probably existed for as long as art has.
Photography takes skill. Punching a sentence into a computer takes no skill. AI does not create art. It creates pictures.
Humans create art.
And now humans create art by punching a sentence into a computer. Are the images nice? Can they provoke thoughts and feelings? Then they're art. Don't like it? Too bad, AI art is here to stay because of how easy it is. Learn to cope.
You've gotten art and beauty mixed up.
The natural world can be beautiful, but it isn't a work of art. Likewise, computer generated imagery can be pretty but it doesn't express any person's thoughts or feelings and therefore cannot be art.
You've gotten the artist and art tool and art mixed up. The artist is the one that makes the art, the art tool is what they use to make it, and the art is the final product.
it doesn't express any person's thoughts or feelings
You don't get to make that judgement. If I have an image in my head and I describe it in a prompt, I can look at the output and say if it represents what I'm thinking or feeling at the time. Same as if I picked up a paintbrush; I can reject the output of it doesn't match what's in my head and artists frequently do declare their work is "no good" even when it looks fine to others.
Photography is just pointing a camera and pressing a button. It takes no skill.
See, it's easy to be reductive.
How do you define art? Is it dependent on the amount of "skill" required to create it? What even is artistic skill? Is one allowed to use auto-focus for a photograph to be considered art? Do you have to develop your own film?
These are all irrelevant thresholds on the inputs for something to be considered art. What determines whether or not something is art is the output of a creative process.
StableDiffusion is more than just throwing a prompt in lmao. You clearly have not spent any time learning what it is and decided to hate it based on people putting in minimum effort and posting their raw gens.
Is it futile because of how easy to use and usually used by creatively bankrupt annoying tech bro, or is it futile because they have multibillion company backing them?
Idk, i can't tell.
I dislike AI art because of the process of its creation, rather than its visual quality. Everyone faking art with AI can fuck right off.
So let me ask you something. Like with the people in this article, if you see an image and it captures your attention, inspires you, makes you go "wow that's stunning & thought provoking!", then after the fact you learn it was made by AI, do all those previous feelings become invalid?
It just seems like you're having to convince yourself that it's bad. Like suddenly deciding a cake tastes bad because you learned the badder was mixed in a pink mixing bowl, despite previously saying how much you liked it. As if your enjoyment of the final product is somehow meaningless compared to how it got there.
All those feelings become invalid because the thought that was provoked by the image will be some generic and unoriginal thing picked up by the GenAI during training rather than new, original ideas by the author. If that thought was intended by the author of the GenAI image that'd be cool with me, but there's frankly no way of knowing for sure and it's very unlikely, so I just reject all GenAI art.
people really just like art that looks good?
This is simply false, and completely misses the point of art.
I for one welcome our new AI overlords.
All hail the eternal machine!
Great. Now soulless megacorps can profit off of the concept of art even more. Amazing.