Hacking Photography - one Picture at a time
AI-powered text-to-image generator, DALL-E, has been available to everyone for a while now. It’s absolutely amazing to play with, but from now on, it could become a part of other apps and find so many applications.
OpenAI has now opened DALL-E’s API to everyone, meaning that developers can integrate the generator straight into their apps and products. So if you’re an app creator, you can now start building with this same technology in a matter of minutes. How exciting!
Earlier this year, OpenAI introduced an AI image generator DALL-E 2, and chose one million creators for beta testing. And if you’ve been eager to test it out yourself – now you can. From now on, OpenAI is removing the waitlist for DALL-E, so anyone can sign up and start playing with it immediately.
It looks like the photography world is starting to get a little sick of AI-generated imagery. Or at least, much of it is sick of it being classed as “photography”. Last week, UK-based model and photographer website PurplePort AI-generated images on its website and now it seems that so have Getty Images/iStock and the “free” stock image website Unsplash.
Both platforms have made announcements in the past few hours stating in no uncertain terms that AI-generated images are banned from their platforms. Both companies also stress that this only applies to AI-generated images, and not human-created 3D render submissions or digital editing tools that are designed to enhance or manually create images from scratch (like Photoshop and Illustrator).
By now, you’ve probably heard of text-to-image prompt-based AI such as DALL-E2, Midjourney, and even Google‘s own version. These programmes pretty much do what they sound like – they take a text prompt or set of instructions, and turn them into an image. It’s usually either photo-realistic or it’s an illustration.
Tests have shown just how powerful this technology can be, and because it’s AI, it means that it’s constantly evolving and getting better and better. Well now, text-to-video AI has arrived, and it could be a complete game changer.
Earlier this year, OpenAI introduced DALL-E, an AI-based tool that generates images from a textual description. If you’ve joined OpenAI’s waiting list, get ready: the company has selected the lucky users who get the chance to test out DALL-E. One million people have been selected, and if you get to be among them, the developers have shared some details to help you out.
A photographer has successfully demonstrated how he sharpened an out-of-focus photograph using the text-to-image AI software Dall-E 2. Macro shots posted to his Twitter feed of a ladybird show the transformation.
Photographer Nicholas Sherlock shared his experiment with YouTuber Micael Widell, who was obviously blown away by the transformation. He even went so far as to state that “this could be the death of photography”. Trigger warning: video contains dogmatic opinions about the impending doom of photography.
I believe that you’re already familiar with the power of text-to-image AI. Tools like DALL-E and Google’s text-to-image AI turn any random text into illustrations. They try hard to make it as realistic as possible, but more often than not, the resulting images are bizarre.
So, have you ever thought about what happens when you put song lyrics into a tool like this? Jason Scott did. He took lyrics of a song about data encryption (how appropriate), let AI turn them into images and made everything into a video. The result – pure, unrefined nightmare-material that. But if you’re anything like me – you’re going to absolutely love it!
Cool new ideas for concept cameras come out with alarming regularity. Painstakingly modelled in 3D software like Blender or Maya or something and then textured, lit and rendered to look as real as possible. They’re a great way to see what the general population thinks of a camera design before actually manufacturing it. Or they’re a good way for independents to tell manufacturers “Hey, this is what we want!”
The cameras here, though, aren’t concept cameras. They weren’t even modelled by a human. They were created by the AI system known as DALL-E 2 which attempts to generate photorealistic images based on written sentences. Mathieu Stern wanted to test its limits to see if it could come up with some cool camera designs based on somewhat unorthodox themes and… Well, yeah, it did!
I’ve had the chance to write about some amazing and creepy AI solutions over the past couple of days. And today, I was mind-blown by another one. It’s called DALL-E 2, and yeah, it’s kinda like an AI blend of WALL-E and Salvador Dali.
OpenAI’s cleverly named AI is able to create realistic “photos” based on your textual description. An astronaut riding a bike, a koala dunking a basketball, a bowl of soup that looks like a monster… You name it, DALL-E 2 will turn it into a picture that’s likely never been seen before.
FIND THIS INTERESTING? SHARE IT WITH YOUR FRIENDS!