From Machine Learning @ Berkeley Blog
In recent months there has been a bit of an explosion in the AI generated art scene.
Ever since OpenAI released the weights and code for their CLIP model, various hackers, artists, researchers, and deep learning enthusiasts have figured out how to utilize CLIP as a an effective “natural language steering wheel” for various generative models, allowing artists to create all sorts of interesting visual art merely by inputting some text – a caption, a poem, a lyric, a word – to one of these models.
[The linked story provides about 3 dozen stunning examples of inputs and generated images as well as an extensive links to resources, preprints, and journal articles.--martyb]
Related Stories
Dick Clark's New Year's Rockin' Eve has become a woke, sanitized shell of its former self. The crowd of rowdy, inebriated locals and tourists is long gone. What you see now is bouncing and screaming for the latest flash-in-the-pan artists while industry veterans like Duran Duran barely elicit a cheer.
Youtuber and music industry veteran Rick Beato recently posted an interesting video on how Auto-Tune has destroyed popular music. Beato quotes from an interview he did with Smashing Pumpkins' Billy Corgan where the latter stated, "AI systems will completely dominate music. The idea of an intuitive artist beating an AI system is going to be very difficult." AI is making inroads into visual art as well, and hackers, artists and others seem to be embracing it with enthusiasm.
AI seems to be everywhere lately, from retrofitting decades old manufacturing operations to online help desk shenanigans to a wearable assistant to helping students cheat. Experts are predicting AI to usher in the next cyber security crisis and the end of programming as we know it.
Will there be a future where AI can and will do everything? Where artists are judged on their talents with a keyboard/mouse instead of a paintbrush or guitar? And what about those of us who will be developing the systems AI uses to produce stuff? Will tomorrow's artist be the programming genius who devises a profound algorithm that can produce stuff faster, or more eye/ear-appealing, where everything is completely computerized and lacking any humanity? Beato makes a good point in his video on auto-tune, that most people don't notice when something has been digitally altered, and quite frankly, they don't care either.
Will the "purists" among us be disparaged and become the new "Boomers"? What do you think?.
US firm Getty Images on Tuesday threatened to sue a tech company it accuses of illegally copying millions of photos for use in an artificial intelligence (AI) art tool:
Getty, which distributes stock images and news photos including those of AFP, accused Stability AI of profiting from its pictures and those of its partners. Stability AI runs a tool called Stable Diffusion that allows users to generate mash-up images from a few words of text, but the firm uses material it scrapes from the web often without permission.
The question of copyright is still in dispute, with creators and artists arguing that the tools infringe their intellectual property and AI firms claiming they are protected under "fair use" rules.
Tools like Stable Diffusion and Dall-E 2 exploded in popularity last year, quickly becoming a global sensation with absurd images in the style of famous artists flooding social media.
Related:
- Adobe Stock Begins Selling AI-Generated Artwork
- Pixel Art Comes to Life: Fan Upgrades Classic MS-DOS Games With AI
- NVIDIA Research's GauGAN AI Art Demo Responds to Words
- Alien Dreams: An Emerging Art Scene
(Score: 3, Touché) by Rosco P. Coltrane on Monday July 05 2021, @06:26PM
Clever UIs figure out how to sell NFTs of their artwork to stupid humans.
(Score: 2) by dast on Monday July 05 2021, @06:27PM (1 child)
This stuff is really fun to use and can give you some amazing output. Also, it's free to use for anyone with a Google account. Fire up a Colab notebook, put in your parameters, and give it a run.
Here's a good one. It's in Spanish, but it's pretty easy to figure out.
https://colab.research.google.com/drive/1go6YwMFe5MX6XM9tv-cnQiSTU50N9EeT?usp=sharing#scrollTo=ZdlpRFL8UAlW [google.com]
(Score: 0) by Anonymous Coward on Monday July 05 2021, @09:58PM
Here's the CLIP-GLaSS model:
https://colab.research.google.com/drive/1fWka_U56NhCegbbrQPt4PWpHPtNRdU49?usp=sharing#scrollTo=zvZFRZtcv8Mp [google.com]
(Score: 2) by vux984 on Monday July 05 2021, @07:33PM (4 children)
So how long does work for book covers, album covers, office/restaurant/etc, video game artwork, etc have left.
Fine art is probably fine, the intrinsic value is in the fact that the piece was created by a particular artist.
And some applications will need very specific artistic interpretations that will require human artists for a long time yet. But I can see a lot of the work going away replaced by 'serviceable' AI compositions generated in a few minutes time based on keywords by someone in marketing.
(Score: 3, Touché) by oumuamua on Monday July 05 2021, @11:53PM (1 child)
Well you know what they say 'When automation takes over we can all become artists'
Guess we will all be starving artists
(Score: 0) by Anonymous Coward on Tuesday July 06 2021, @12:57AM
They will provide the training materials for the AI. Don't do this.
(Score: 0) by Anonymous Coward on Tuesday July 06 2021, @01:00AM
"Art" will move into the spaces. As long as there is human despair. Imagine a world filled by AI art and McDonalds Happy Meals. These are not happy people.
(Score: 0) by Anonymous Coward on Tuesday July 06 2021, @09:19AM
I'm waiting to see the DeviantArt/FurAffinity/et.al. "Commissions"... an easy $350 for typing the sucker's description of their online avatar into one of these free-to-use Notebooks.
(Score: 4, Informative) by FatPhil on Monday July 05 2021, @09:19PM
You can see that deep down it's not actually evolved that far in those intervening years. That one was of course deliberately trained on a very restricted training set for lulz, don't be fooled into thinking that the AI itself is twisted. The ability to stimulate the generation with textual keywords was always programmed into the AI, the internal model of what it's learnt is basically independent of the method it got the input. Show me the realtime demo of you speaking too it, accompanied with what the AI thinks the visuals should be. Let me play!
Great minds discuss ideas; average minds discuss events; small minds discuss people; the smallest discuss themselves