In the past year, the impact of generative AI and other AI assistants on the realm of applied arts has been truly remarkable. From generating unique and captivating visual designs to assisting in the creation of innovative videos, AI has proven to be an invaluable tool in pushing the boundaries of artistic expression.
One of the most notable ways generative AI has influenced applied arts is in the realm of digital artworks. With its ability to generate infinite variations of designs and patterns, AI has empowered creators to explore new aesthetic realms and create mesmerizing, one-of-a-kind digital artworks. Creators are now able to harness the power of AI to bring their visions to life, unleashing a whole new level of creativity and imagination.
What does an AI test assistant tell you about the role of AI in applied arts?
If you ask an AI about the impact of AI assistants in the last year, it would sound like (generated with Linguix, a writing assistant I use while writing posts):
AI assistants have streamlined the creative process, saving artists and designers alike significant amounts of time and effort. These assistants are capable of performing tedious tasks, such as image sorting and research, allowing artists to focus more on the actual creation of their art. By taking care of the mundane and repetitive aspects, AI assistants have allowed artists to devote their energy to the aspects that truly matter - crafting innovative and thought-provoking artworks.
The impact of generative AI and other AI assistants on applied arts is not limited to digital mediums alone. In the field of sculpture, for example, AI has played a significant role in helping artists design and produce intricate and complex pieces. By utilizing algorithms and computational methods, AI has offered a fresh perspective on sculptural creation, pushing artists to explore novel forms and experiment with new techniques.
In conclusion, the influence of generative AI and other AI assistants on the realm of applied arts in the past year cannot be overstated. From enabling artists to delve into uncharted aesthetic territories in digital art to revolutionizing the creative process, these technologies have undeniably reshaped the landscape of artistic expression. As we move forward, we can only anticipate further advancements and a continued partnership between artists and AI, opening up even more possibilities for the world of applied arts.
Reading through the answer sounds very compelling, and truly I think this influences the direction of my post; there are many aspects and directions, I didn’t take into consideration before. It also felt a bit like… wow, did I miss so many things?
Let’s ask google’s bard, to provide me some examples to some of these mentioned improvements last year (ChatGPT’s memory ends in January 2022, so it wouldn’t help).
My first question for Bard:
Could you name some artists using AI to design sculptural creations?
As you might expect, I ended up having a smile on my face. At first, Refik Anadol was the top-ranked artist, followed by other artists who are, based on bard connected to the usage of AI.
The true reason for my smile was the double test and the same results; so I tested the question “Could you name artists using ChatGPT or text-to-image generators for their artwork?”.
The result was the same list, with the same errors; Bard didn’t distinguish between artists in general having some relation to computer art or playing with computer algorithms, such as Josef Albers, Maurizio Cattelan mainly known for sculptures and installations, and other artists using algorithms in general.
The most entertaining outcome from the list is the incredible hallucination of Markus Rehm, or at least I hope it is, as I must admit I am not familiar with this artist.
AI has been used in New Media art for quite some time.
Honestly, I don’t know which renowned artists really came up with new pieces of art within our last year that made use of ChatGPT or Text-to-image generators to build the foundation of the artwork itself.
In my understanding, the text being generated by AI shows a misconception about art. Especially new media art is and has always been about the edges of our technology surrounding us.
The popularity of new media art has been consistently rising since around 2014/2015, particularly in the areas of image generators and algorithmic experimentation. Google DeepDream was released in 2015 and many artists played with it. I recommend the read of Memo Akten “#DeepDream is blowing my mind” from 2015.
I know everybody hates #Deepdream, but I really love it. However, it’s not the aesthetics that I love, but the poetry of what’s happening inside the algorithm.
Memo Akten on DeepDream
There’s also a related video to his DeepDream experiment from 2015 on Vimeo.
Besides Akten, also Mario Klingemann started with some DeepDream experiments back in 2015, before he made more use of the emerging Generative adversarial networks (GAN) and created I guess his most famous piece of art in 2018, Memories of Passersby I. By the way, Mario is also one of my heroes as he accompanies my life for a long time; so he was a master in Adobe Flash and so many things that also played a role in my life. Get inspired by his journey and watch this video on YouTube.
GANs and DeepDream played a role for many artists. In 2016, we had great projects, such as “the nightmare Machine” by the MIT Media Lab, and also the beautiful project “The Next Rembrandt” got introduced in 2016. With Edmond de Belamy, a Generative Adversarial Network portrait painting from 2018, being sold for $432,500 at an auction, more and more artists realized that there is a lot of potential in that field.
For a long time GANs were the core to generate images; so before we had DALL-E (in version 2), Imagen, followed by Midjourney, Stable Diffusion and others, we relied on GAN-related image generators to generate pictures.
Back in 2022 I wrote a post on “Speaking computer language – welcome AI Art” and it gave a glimpse into the current status quo (before mass market tools dominated and changed the development). With the introduction of CLIP (Contrast Language-Image Pre-Training) and other similar technologies, we witnessed the emergence of image production tools. However, it is the arrival of the latest text-to-image generators that revolutionized the market, turning it into a mass market phenomenon.
This might sound like I’m joking, but I am not: I believe that one of the hardest problems in artificial intelligence, which still has not been solved satisfactorily, is humor. Once machines actually know how humor works and are not just involuntarily funny sometimes like they are now, they will have achieved true intelligence. And as a free bonus, with that understanding will automatically come the ability to know when to be serious.
Mario Klingemann on the question “What are the hardest problems at the intersection of technology and society that deserve more attention?” in MIT Technology Review
Regarding jokes and humor, at least Sam Altmann had a great reaction after the introduction of Elon Musks Grok.
It’s all about the data – New Media artists don’t care so much about ChatGPT and Text-To-Anything generators.
I already explained the role of data for the art being created by Refik Anadol in my post “Deconstructing AI Art masterpieces: Create Art like Refik Anadol”, in general AI is at its core a set of data technologies to analyze and transform an input.
In the past, artists had to classify the input images for AI models themselves. Now, there is a modern form of slavery where people are paid very low wages, around $2 per hour, to classify data. The problem is that the content they have to classify can be traumatic, see the article “OpenAI Used Kenyan Workers Making $2 an Hour to Filter Traumatic Content from ChatGPT” published in vice magazine.
Getting back to the initial listing, AI proposed artists making use of ChatGPT or text-to-image-generators and the top result of the list, Refik Anadol.
Most of his current artworks still rely on the GANs, so there are different ones, such as DCGAN, PGAN, and StyleGAN algorithms being trained on massive datasets.
Unsupervised — Machine Hallucinations — MoMA, recently being displayed in the MoMA is one of the works of Refik Anadol. The thought of playing with “hallucinations” beautiful reflects machine hallucinations in an expressive style.
Art that is influenced by Text-To-Image generators? Yes, dear Bots, here are some examples.
AI tools are great, no question, no doubt. Creating text, editing text, writing code, editing code, finding inspiration, testing ideas, … there are so many great ways to make use of AI. So let’s finally look at some examples that really relate the usage of mass market tools being available since around a year.
AI fashion examples
AI fashion in general has great examples of how to use text-to-image generators. Though many use the looks to get quick money again (this time in the shape of NFT), I wouldn’t blame them for doing so. Better than generating fake content on the web to gain traffic and generate money with it; see my main criticism in part 2 of the series “who owns the truth – the web”.
“Contemporary” AI Art
I don’t even know if there is something like a contemporary AI Art section, but if so, I would put some work from Violet Forest into this category. Her series “Just an AI girl” is just fun and is playing with contemporary clichés and one of the main issues mainstream text-to-image generators have had the last year; displaying strange hands.
Violet Forest (Violeta Lopéz)
Danielle King
Artificial Childhood Memories is an invitation to reflect on our own memories, the stories we choose to reshape, and the ever-evolving digital canvas upon which we sculpt and re-work the narratives that define us.
Description from Joyn.xyz on Danielle Kings’ work “Artificial Childhood Memories”
In "Artificial Childhood Memories," I delve into the delicate interplay between technology and nostalgia. This exhibition explores the ways in which AI can be harnessed to recreate and reimagine our fading memories, shedding light on the malleability of the stories we tell ourselves.
Danielle King describing her work “Artificial Childhood Memories” on her website.
Art is expressive and should also be related to our society and what moves our zeitgeist. From my understanding of the provided Answer, so far it seems that language models don’t understand differences within applied arts and they also see all "creators" as artists. The field of applied arts is far wider than only arts. It’s the world of different design disciplines and architecture as well.
Looking at my entry point, I had no chance to speak about applied arts in any design discipline so far… only because I was surprised how wrong the Chat output was.
The role of AI tools, such as ChatGPT or Text-to-image, video or anything generators, has on the design practice.
Simple answer: it’s a massive support for finding ideas and especially directly testing ideas. Being able to use language is now a competitive advantage and there’s no need to only rely on pure sketching skills.
But still, I don’t see finishing skills in AI. New Media Artists have proven over the last 10 years, that the manual selection process, or I would call it the classical role of an Art Director, is needed to point AI into the right direction.
Our dear AI buddies help to be far quicker – But still, they are supporting tools
For me being a solopreneur sometimes, sometimes part of a team or as a design-consultant on a project, I had different usages of AI. The best is sketching and selling ideas in a rush. So I had this little superhero being created for a client with some variations within half a day till I got the client's approval. The work to finally get the model created with 3D and some post-production/optimization took much longer.
The image was prepared with leonardo.ai and quickly modified in Photoshop to present to the client.
A main benefit for me is the brainstorming and ideation part. So every time I am stuck with something such as preparing a script for lectures, I could use AI as my muse to get distracted and refocus my thoughts.
The article “AI Reveals the Most Human Parts of Writing” from Wired Magazine illustrates this role of an AI-supported Writing buddy quite well. For some writers, the use of AI writing tools is like a new ghostwriter, but also the effect, that AI is giving you the direction of the text, might emerge. Same in my case for this post. The generated text of AI was a bubble and I wanted to elaborate on it to find out, that also the AI Chatbots had no clue about what they were talking in the end, AI dominated the direction of this text.
In terms of writing, AI assistants are a great aid, also in terms of usability. I assume it is much more pleasing to read an optimized text than my own, plain thoughts.
Text-to-video: Runway ML, Kaiber, Pika Labs and others
For me, there’s no use case yet to say, AI itself is the main tool yet to go somewhere. They massively help to get a feeling of potential looks; so as of November 2023, text-to-video made some impressive advancements, and it’s not Runway ML alone being the only interesting pick. But still it is one of the most impressive.
To get an idea of what Runway ML is capable of, it’s best to look for results on Twitter. @maxescu work is worth a look. He recently produced a video “the outworld” that could also be seen on YouTube, that is 100% AI created (and it is impressive). I would also recommend to filter Twitter results and look for #runwaymlgen2.
Ammaar Reshi is another, highly talented AI Movie Director with great demos.
Other contenders are also there, but all lack the quality of Runway ML at the moment. Maybe Kaiber has the most potential at least for some kind of looks. Other shots are from Pika Labs and from Genmo.
The beauty of these tools is that even when artists or people who try this tool explore it, it helps all creatives broaden their horizons. Creative work is heavily influenced by what we have seen.
UX Design and AI
To give a status quo about UX design and AI, I first start with a personal perspective based on my working process and experience during the last year.
On the visual part of the process, I tried text-to-image generators and their website output; but currently I wouldn’t suggest the use to text-to-image generators for more than a creative direction of a mockup and I wouldn’t always recommend to show it to clients.
The thing is, you easily get an interesting visual appearance. But in terms of structure, user guidance, or in short in terms of usability, my feeling was that the generated screens show one of the biggest pain points that brought me business in 2023.
The best recommendations I could give so far would be Galileo AI, Visily, WireGen for Figma, in terms of tools and 3M VAS to check, to buddy your design.
I had to conduct UX workshops in two agencies that have their strength in classical design or editorial design. Interestingly, both complained about their lack of usability when they incorporated it into their online designs or magazines. Based on my experience, this is a true point I see now in AI-generated websites. They look good based on an arrangement perspective, but are not usable at all.
Jakob Nielsen, part of the world renowned Nielsen Norman Group and maybe the godfather of usability, wrote an article on his own legendary blog about the “Unreliability of AI in Evaluating UX Screenshots”. For a small study, 12 e-commerce screenshots were given ChatGPT for evaluation.
The suggestions that were given were inconsistent and untrustworthy. Nielsen compares the results with an early intern and sees perspective in a Version ChatGPT6 maybe in some years to provide some valuable help in evaluation.
Ok, this article is from one of the strictest masters in usability, but Nielsen isn’t AI in general; he has a lot of great use cases, where AI assistants are helpful, such as ideation.
As another article on “AI-Powered Tools for UX Research: Issues and Limitations” from Norman Nielsen Group said, one of the core problems is that most available tools can’t process visual input yet. This is where ChatGPT's ability to vision comes into play and will show us where the future leads. Similar to the artists, I assume if Jakob Nielsen would “teach” his Bot to classify, it would be able to classify more Usability downsides easier.
ChatGPT Vision – pushing boundaries
I didn’t expect my post to get so long, so I try to get the curve slowly. For me the next major step now is to add more senses to AI. ChatGPT being able to hear, see and speak is massive.
Let’s look at some early visions:
Mckay Wrigley has some great early examples of what ChatGPT Vision is already capable of. Also Pietro Schirano has some interesting examples on the application of ChatGPT Vision.
Summary on the use of AI for applied arts
Yes, you are right. I didn’t look at all developments in applied arts; for me, it is mainly about a glimpse and my personal attitude towards the topic.
When it comes to applied arts, I could write endlessly and share more examples, in music for example, there’s the recent creation of Beatles song and a great short film explaining the process. Or we have “The Project Gutenberg Open Audiobook Collection”, a collection of free audiobooks created with neural text-to-speech technology.
The major issue with all this development is the speed of development and the wide range of tools. It is insane. On the business side, I stopped two clients not to push forward with an AI-supported website chat earlier that year; I told them, it’s not yet the time. 5 months later you found easy tools to train the chat with the website content easily on every corner… but still, I tell them to stay calm; wait for the European Act on the usage of A, and then we see which providers there are with a suitable solution at fair price (of course one could also use an own hosted solution now, but that’s not the point).
Staying calm in times of noise is my personal approach to current AI developments. All investments are pumped into AI, being a front-runner on a business side needs money and willingness to adapt quick; there’s no simple finish yet.
As you might have noticed on my blog, I wrote a lot more about text-to-image generation before we reached the state of mass market. And honestly, it would have been hard for me to write about it, as every few months some new exciting developments would have changed the direction of my thoughts. I always sing up for some early access stuff; so currently I am mostly waiting for access for everArt.ai.
I love AI for applied arts and I love the progress in technology we face. The speed is insane, and I assume the fear of missing out on some of the stuff is big. Especially if you are thinking about business ideas and applications for “quick” money. I also tried some stuff, trained my own models, built some Next.js apps and so on… but finally realized, that’s not my turf.
My role in this game is observing, applying and consulting. And honestly, this is quite relaxing. Why chase for quick money, if you could serve clients better and quicker? Providing happiness is a good sake and more fun to aim for.
As my counter program to the speed in AI developments I recently bought an iDraw H A3 to have some fun “drawing” things. Maybe I also share some post on that one some day.
My true recommendation on AI tools is, integrate them to your workflow, step by step and do yourself a favor to not try each and every tool. Relax, find your influencers and stick to the stuff that works best for you till you have a use case, some elaboration of another tool might be needed. AI Technology changes so rapidly, so don’t waste your time on trying tools.
OpenAI CEO Sam Altman said on social media that a new Moore's Law may appear soon, that is, the number of intelligence in the universe doubles every 18 months. If you imagine this number, you might understand how important it is to stay calm.
The only hope is that downsides of AI, such as bad datasets that infringe intellectual property law or unethical training data, get fixed. Also, the compensation of humans whose work has become training data needs improvement.
In arts and craft there's no truth; there is only exploration.