Share this page!

Roland Meyer Profile picture
@bildoperationen
Mar 30 • 8 tweets • 4 min read Twitter logo Read on Twitter
Mainly for the sake of my own future reference, I am collecting my longer threads on AI image generation here, starting with this one from last year (which, unlike the others, is still in German)
1/
This one from January speculates on different business models for #VirtualImageArchives and the further platformization of multimodal AI
2/
This one is about AI-generated movies that never existed, and the role of #ArtificialNostalgia
3/
Here I try to develop the idea of #ArtificialNostalgia further by relating it to the notion of »vibe«
4/
This one is about the »fluffy glamour glow« (@pookerman) of current commercial AI generators
5/
Here I ask what it means that these models simulate the look of photographic visuality without trying to simulate photography as an optical medium
6/
In this thread I ask the question if we can find something like a »punctum«, as Roland Barthes famously analyzed it for photography, in AI-generated images as well
7/
And here I argue that AI image generation might be nostalgic by design, which might be one reason why we find so much #NostalgicWeirdness in aesthetically ambitious uses of AI
8/

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Roland Meyer

Roland Meyer Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @bildoperationen

Roland Meyer Profile picture
Apr 1
The recent wave of pope-related AI images, and the accompanying hot takes about whether or not we've now finally left an era of »visual truth« made me think about the relationship between two modes of online image interpretation: #WildForensis and #InstantMemeification 1/9 Midjourney-generated image,...
Popular versions of image forensics have been a staple of social media for some time: People just love to speculate about whether or not a widely shared image has been manipulated, and to look for hidden clues of tampering. That’s what I call #WildForensis
2/9
AI images in their current form are a perfect object of such #WildForensis: Clues that an image was generated are now often so subtle that they're only visible at second glance. But you still don't need any technical skills to find them, they are usually hidden in plain sight
3/9
Read 9 tweets
Roland Meyer Profile picture
Mar 31
Giovanni Battista Piranesi, aus dem Zyklus: »Proposta del Ministero della Ricerca tedesco per riformare la legge sui contratti di lavoro a tempo determinato in ambito accademico«, 1753 Midjourney-generiertes Bild...
Aus demselben Zyklus, ebenfalls 1753 Prompt: Act on Fixed-Term E...
Und hier noch ein weiteres Blatt, rückwärtig bezeichnet als »Assemblea delle parti interessate presso il ministero« Midjourney, prompt: Stakeho...
Read 4 tweets
Roland Meyer Profile picture
Mar 9
This is truly remarkable and makes me think again about the relationship between AI and photography. What interests me about these generative models is that they simulate a photographic visuality without simulating anything of photography as a lens-based, optical medium
1/6
This sets them apart from a whole tradition of computer-generated images: In what @bernardionysius calls the »scopic regime of computation,« computers were used to simulate three-dimensional worlds made of points, lines, and vectors that could be captured by virtual cameras
2/6
In contrast, AI image generation doesn't use a model of spatial constellations computed in accordance with the laws of optics and the rules of perspective. Rather, by interpolating the visual qualities of masses of digital photographs, it simulates a photographic ›look‹
3/6
Read 7 tweets
Roland Meyer Profile picture
Mar 7
Now that the DALL-E has been successfully midjourneyfied, it is becoming apparent that instead of simulating all possible ›styles‹, AI is fostering the emergence of a distinct visual style, born out of popular aesthetic preferences dominating platforms like DeviantArt
1/6 Midjourney generated image, prompt: Cloud in a museum galler
One main characteristic of this AI style seems to be what @pookerman has aptly called »fluffy glamour glow«: The default mode of these images is to shine and sparkle, as if illuminated from within. These are images that radiate
2/6 Midjourney generated image, prompt: Fluffy Glamour Glow
This effect seems to be due in no small part to a particular color scheme, a striking preference for contrasting warm earth tones with blue-greenish metallic colors, reconciling intense lighting and high dynamic range with overall chromatic harmony
3/6 Midjourney generated image, prompt: painter's color palette
Read 9 tweets
Roland Meyer Profile picture
Mar 6
It seems that the new version of Dall-E, probably for legal reasons, ignores the names of artists whose work is still copyrighted. Instead of imitating their individual style, it only produces very generic images, at best vaguely according to styles like »Pop« or »Expressionism«
Interestingly enough, #Midjourney is quite competent in imitating the style of contemporary artists maybe lesser known to a general public, e.g. here Peter Doig ... Midjourney, prompt: New York Subway, painting by Peter Doig
... or Maria Lassning here ... Midjourney, prompt: "Swimming pool in a container"
Read 8 tweets
Roland Meyer Profile picture
Feb 22
Playing around with AI-generated, non-existent movies and the idea of #ArtificialNostalgia, I started thinking about the notion of ›vibe,‹ how it might describe what I'm looking for in these images and what distinguishes it from concepts like ›style‹ or ›mood‹
1/16
Much of the discussion around AI-generated images has involved questions of style, and for good reason. »In the style of ...« is maybe the most common phrases used in prompts, as #DallE, #Midjourney, and #StableDiffusion promise to produce images in any possible style
2/16
This category of style transcends cultural hierarchies: Style can mean the brushstroke of a painter, the visual qualities of historical technical media, or the look of certain games & TV shows: Van Gogh, Polaroid, Unreal Engine, or Southpark – everything becomes a ›style‹
3/16
Read 18 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

Send Email!

:(