It's not photography
Or is it? The medium is evolving. Again.
Have you seen this image?
By now, I’m guessing that you have. I quite like it. It’s a beautiful picture — evocative and weird in a wonderfully cinematic way. The image is from Boris Eldagsen’s PSEUDOMNESIA: Fake Memories series. Is it photography? Not quite. Here’s how he describes the work:
PSEUDOMNESIA is the Latin term for pseudo memory, a fake memory, such as a spurious recollection of events that never took place, as opposed to a memory that is merely inaccurate.
The following images have been co-produced by means of AI (artificial intelligence) image generators.
Using the visual language of the 1940s, Boris Eldagsen produces his images as fake memories of a past that never existed, that no one photographed. These images were imagined by language and re-edited between 20 to 40 times through AI image generators, combining “inpainting,” “outpainting,” and “prompt whispering” techniques.
Prompt whispering! Outpainting! Image generators! It’s a brave new world.
“The Electrician” is hurtling around the Web this week — here’s the backstory if you haven’t heard about it yet. A few weeks ago, Boris sent me an email (reprinted here with permission):
Dear Andy,
It happened. An AI-generated image won the first big international competition.
My work "The Electrician" won the "creative" category of the Sony World Photography Awards (SWPA had 450,000 photos submitted from 200 countries).
This is a historic moment for the relationship between photography and AI image generators that could be used for good. I entered the competition to see how far I would get and (if I am among the finalists) to use the attention that major international awards like this change their rules and set up separate competitions or categories for AI-generated images.
But: Sony knows for over a month that it was AI-generated but didn't want to communicate it so far. Press inquiries about the nature of the work have been responded to generally:
"Many thanks for your inquiry. Please find below a quote from Scott Gray, Founder and CEO of the World Photography Organisation: ‘As a medium photography has always been at the forefront: constantly adapting and evolving, it has a singular ability to transform itself and push boundaries. We are interested in photography as an art form, and within the Sony World Photography Awards, we have our Creative categories in the Professional and Open Competitions, which welcome photographers to experiment and explore the dynamism of the medium. With technological advancements, a wider audience of creators are engaging with lens-based work, and we look forward to seeing how this can expand the reach and impact of photography.’ Kind regards"
Right now, only parts of the German and Polish press are aware that the winning work is not photography. During the last month, I offered three times to do a public debate (online or panel) about the future relationship of photo competitions to AI-generated images. After the third time, they said that discussions are not part of their plans, but they could do an interview on their blog.
This is a missed chance.
It is important to realise that "the photographic" as a visual language has separated itself from its source and got a life of its own — as AI-generated images.
And it is important to separate "the photographic" and "photography" as different entities, however impossible this will become in the upcoming months.
I see my role as a practitioner of knowledge transfer. I do public talks and workshops on the current state of AI-generated images — for universities, magazines, agencies, festivals, museums, and organisations. As the ‘Head of Digital’ of Deutsche Fotografische Akademie (art photographers association founded in 1918), I am a member of the AI work group of Deutscher Fotorat, in which the German photo associations discuss the chances and risks of this disruptive technology at large. You will find my statement about SWPA on my webpage.
The Sony World Photography Awards ceremony will take place in London on April 13, followed by an exhibition in Somerset House which will then travel to different locations. I would like more media to take up the above-mentioned facts and start a public discussion that will lead to AI-generated images and photos no longer competing directly with each other in the same competition.
Perhaps you would like to help initiate this or know a journalist who would like to do so?
I dropped the ball in helping Boris spread the word about this project when he wrote to me on March 22. Keeping up with email is my Achilles’ heel — Sorry, Boris! I didn't know how to respond when I read his email the first time. Until now, I haven’t followed the AI/photo scene and didn’t know how I felt about this situation.
The truth is, I’m still figuring it out.
Photography appears to be evolving again. Or something entirely new is emerging. Either way, words matter, and we need a new vocabulary to talk about these things.
Boris took the stage at the Sony World Photography Awards on April 13 and caused a stir by refusing to accept his award. The international press has picked up the story over the past few days. (He’s posting personal updates on his website and Facebook if you want to read up on his perspective.) Boris emailed again on Sunday and sent a link to an interview he gave to Riding the Dragon. It’s a good read.
It occurs to me that we’re at one of those tricky cultural moments where lines are blurring, and old terms aren’t working as they used to. This is imagemaking, but is it photography? I’ve written previously about the process of picture-making. It’s only tangentially related but still seems relevant to the discussion. Make it or take it; photography is a construction. AI photography — or whatever it’s called — doesn’t feel too far removed from how many artists use photography: as a malleable medium that can be molded to create fictional realities.
Lately, I’ve been seeing folks on Twitter talk about AI-generated imagery in the same sentence as the phrase “post-photography." I’m only slightly familiar with that term. What does it mean? I’m doing my best to bone up on this vocabulary, and I’d appreciate any insights you may have to offer. This may sound nuts, but I put the question to ChatGPT, and here’s how it responded:
Post-photography is a term used to describe a broad range of artistic practices that challenge and expand the traditional definition of photography. It refers to the use of photography in combination with other media, such as digital technology, video, performance, sculpture, and installation, to create new forms of visual expression.
Post-photography is often associated with the digital revolution, which has transformed the way we create, manipulate, and distribute images. In this context, post-photography refers to the shift away from traditional photographic techniques and the embrace of digital technologies, which have enabled new forms of image-making and distribution.
Post-photography is also used to describe the ways in which photography has been used to explore and critique issues of identity, gender, race, and politics. Artists working in this vein often use photography to challenge conventional norms and explore new forms of representation and expression.
In summary, post-photography is a term used to describe the expansion and transformation of traditional photography in response to the digital age and the changing cultural and social landscape.
Sounds about right. Photography is evolving. Again.
For one thing, it’s no longer a physical experience — not by default, anyway. That has all kinds of ramifications that impact every aspect of the photographic experience: how we make, discover, see, view, and share images. Digital platforms have transformed how we consume, look at, read, and pay attention to photography. With artificial intelligence in the mix, what pictures mean is changing too.
It’s an exciting time to be into photography — and a potentially dangerous one. Pictures were never entirely to be trusted, but AI technology makes it even more likely that we’ll encounter fake images. And this is just the beginning. Has photography’s definition changed? Or is it in the process of expanding?
I’ve been mulling these ideas over all weekend and woke up this morning with a question in my mind: In 2023, how do we define photography? It’s not as easy as it sounds. I figured getting back to basics might help to ground the conversation. Again, I posed the question to ChatGPT. It replied:
As an AI language model, my definition of photography remains constant regardless of the year. However, I can provide an explanation of what photography is.
Go on…
Photography is the art, science, and practice of creating images using light and a camera. It involves capturing and recording visual images of the world, people, and objects through a lens or a photosensitive material. Photography is often used for various purposes, such as preserving memories, recording history, documenting scientific observations, artistic expression, and communication.
In the digital age, photography has become more accessible and widespread with the use of smartphones and advanced digital cameras. The process of capturing images has become easier, and the possibilities for creative expression have expanded. However, the fundamental principles of photography remain the same, which involve using light and a camera to capture and record visual images.
I can get behind that — Photography involves light and a camera to capture and record visual images. You’ve got to start somewhere. But where does it end?
I asked ChatGPT a final question. Are AI-generated images photography? Its reply made sense, and I appreciated this distinction:
No, AI-generated images are not photography in the traditional sense because they are not created by capturing light through a lens and sensor. Rather, they are created through the use of algorithms and data input, which are processed by a computer to create a visual output.
While AI-generated images can simulate real-world objects, scenes, or even people, they are not actual representations of the physical world captured through a camera lens but rather digital interpretations of it.
That being said, AI-generated images can still be considered a form of visual art and can have significant creative and aesthetic value.
There’s much to think about here, and I’m grateful Boris kickstarted the conversation for us. I would love to hear from you — Are we at an exciting turning point in photo culture? Or is everything going to hell in a handbasket?
Please let me know your thoughts by commenting or replying to this email. And you can join us in the FlakChat too. I’m looking forward to hearing from you!
Hi Andy,
Let me start by saying that I am old school - a dinosaur - who shoots film on an old M6. I am smiling a little here, because the number of debates I have had discussing digital vs analog is extensive. I realize that AI is a new thing, but is it really? Are we not talking about pressing the 'enhance' button on our digital camera, 'add effect' on the laptop, etc.? Is this not already a series of processes to take a photograph and change it to something different. There are of course degrees of change, but how many times have we not seen competitions won or lost by people who have merged images, or artificially improved in some sense using technology. I think we are long past the split in the family tree. Analog to the left, digital to the right. Perhaps this is just digital splitting again into 'AI digital' and 'pure digital'. I assume 'pure digital' at least starts with a camera of some sort and a string of 1s and 0s on a card.
I don't have the answers, but am moved by those in the digital space who are outraged by this. Wasn't there something about an ant-eater that was stuffed showing up in a night photograph by some nature photographer wiz-kid that won a major competition? I was outraged then. Now, I just smile.
We get what we deserve. We keep challenging the boundries. It seems the chicken has come home to roost. Or perhaps the elephant in the room has laid an egg. I am sure AI could come up with a deceptively elegant photograph of that too.
Take care,
soren
Wow, this leaves me rather pissed off at Sony. AI images are visual art and absolutely should not be considered Photography. Saying Post-Photography is an insult to all photographers. This is more a kin to painting and collage. That said in my opinion most commercial digital photography should be called mixed media (if you manipulate the image more than light and color balance). Very happy to hear that he refuses the prize. Weird situation.