Hi, this is Wayne again with a topic “Is AI the end of photography as we know it?”.
Earlier this year, this photo by Berlin artist, Boris Elston won a Sony World photography, award, Sony’s press release, called it haunting and reminiscent of the visual language of 1940s family portraits, but Boris rejected the award, because this photo was AI generated as a person who makes a Living as a photographer and videographer on principle, I want to hate all of this work and all of the tools that make it possible, but in reality I haven’t been able to look away. So I went to Berlin Mom. I made it to see how it’s done. I’M Boris Elon, I’m a Berlin based visual artist, working with photography, video installation and uh for 1 and a half years now working with artificial intelligence. These are pieces from boris’s series, sudom nesia number, three meaning fake memories. It fuses the visual language of the 1940s and post-war photography with abstract art. It was entirely created with text based AI image generators text.
Firms for me are quite complex. I can go up to 13 text from elements and you see they are kind of poetic. He considers himself a promptography or someone who uses text to image generators to create the visual imagery that he wants and his process takes a great deal of time. What you’re about to see is a graphical representation of that process. I still like to start with text to image. The result is just an interim product.
I use the result and I blended it in mid Journey. That, again, is just an interim product, but I use those images combine them with text, so it becomes an image prompt, create something new out of it, and this I do multiple times and in the end I spend one or two days, uh in post production. Doing what in the past was called inpainting out painting and what Photoshop calls these days generative fill or expand, and then it can take 2 months to uh, have 15 images uh put jued, but clearly there’s more to it than that. So after he told me about his process, I asked him if he would sit down and show me how it’s done here.
Boris is using mid Journey, which you access via Discord. I could also use a negative text prompt it’s one of many generative AI programs weights and they can be positive or or negative one that I thought I was quite familiar with, but Boris was speaking a whole different language yeah. I could now exchange certain elements and I was totally confused. I to have the seat of those images. My red flag is thinking that I can do anything that anyone else could do so after spending two days with Boris and learning all about his process. I came home to see if I could do it too more on that, after the break more and more we’re seeing AI tools be integrated into our daily lives, from generating quick, inspiring art to capturing notes from important meetings, but with sap business AI.
Their tools are designed to deliver real world results, helping your business become stronger and helping you make decisions faster, faster. This revolutionary AI technology allows you to be ready for anything that is thrown at you. Okay, that’s it for me, but before we go, sap doesn’t influence the editorial of this video, but they do help make videos like this possible.
The best thing about attempting to be a promptography is that you really don’t need much to make it happen. I’M going to start with a simple object: a pancake and then I’m going to try to build a scene around it and have it. Look like film photos that I love, which are usually nectar. 100. It’S my favorite film stock and then I’m also going to try to put it in the 1970s cuz. That’S something that I can’t really do. Irl! Imagine a pancake. How could this possibly go wrong? Okay, here we go. Those are good pancakes. It leaned cartoon for three of the four: let’s change that, let’s change that the first thing Boris taught me was to build out my prompt pancake photo realistic, Diner 1970 film texture, Cod, ector H.
I like the text on the build building over here. I want more of that. It’S giving me kind of what I want, but I want more of like a scene. This feels very stock still. I also feel like it’s not really getting. My film look. My process continued on like this for hours, film green. What happened here, we got wonky forks and it looks like the ceiling fell down on this stack of pancakes. How do I reel this in? It also didn’t give me any text on that last one I want like and with each prompt came incredibly different results.
So many pancakes, and then I remembered what Boris told me about seeds, because the seed is like a geolocation uh in the the latent space of the training data and using the same seed over and over again, you can really work on a text prompt if you Put the same prompt into mid Journey twice, it will always generate different images. That’S because this program was designed to be random, but every time you generate an image, the program, a seed value for it and in really simple, not technical terms. The seed value is like a code for particular look and feel so if you want to maintain a consistent look with each image generation, you have to input a similar, prompt and then also input the same seed value as a previous image that you liked this process Will help you find tune, a prompt, okay? I really liked what I got here and I have the seed. So now I’m going to use the same prompt with the same seed, and I should get a very similar result that I can then many change fingers crossed after many hours and even more stacks of pancakes.
I still hadn’t achieved the exact look I was going for, though I was happy with some of the things I was getting. I feel like I’m just scratching the surface of any sort of skill that Boris uh has achieved. I mean this like this could not be more different than picking up a camera and taking a photo, even if the results are similar, which brings us all the way back to that photo competition that Boris stuped when he entered his work into the Sony World photography Awards his intention was to make a statement about the need to recognize the work he was doing as something different from photography. No, I think uh, it’s very important that um it’s separated into different categories or different competitions, because the way the image is produced is differently. It’S different Technologies, it’s different forms of images, it doesn’t matter if they look the same, it is not the same. I can have a plastic lemon and a real lemon and they don’t taste the same, and that is what I’m trying to to help uh to to get going uh. This is why we needed a new terminology. My suggestion was promptography and this is why it’s important to talk about workflow and motivation. Photographers tend to go out into the world to be present at a certain location, interacting people. Yes, there is technology and AI in the cameras, but we are still needing light.
That is reflected from and creating images with AI you don’t. I can sit in a dark Cellar. I just need my technology and Wi-Fi and that’s it. On our last night, in Berlin, there was an opening for boris’s work at a gallery. That’S dedicated to AI generated art, so what you’re looking at is both AI generated photos and found photos from the time all of the real photos are in brown frames and the AI generated and manipulated images are not in frames, seeing boris’s process and knowing how these Images were created completely changed how I viewed them that night going forward. It’S going to be important that everybody knows how the images that they’re viewing were created, which is something we are very much struggling to do currently and giving promptography a platform, allows everyone to know more about the tools that are available and in boris’s mind.
Well, this will advance all art forward. There is a study about Chess and you know at a certain level in time, humans were not able to win against chess computers, but did we stop no yeah? We continue to play and we use chess computers for training. So the level on which chess is played today is much higher than before: the invention of Chess computers, incorporating and and making use of, AI creativity, our creativity can get onto a higher level, and maybe the transformative creativity is something we can focus on. This is not the entire story of AI generated art. There are some big problems here around the legality of the training data. Where are these models learning from and are those artists being compensated properly? We made an entire video about it, I’ll link it down below I’m Becca. Thank you for joining me I’ll, see you in the next one .