DIY Photography

Your one stop shop for everything photo-video

Search

Submit A Story

midjourney

Scientists have created a tool that stops AI stealing your photographs

by Add Comment

Are you worried about AI image generators stealing your artwork and spitting it out as its own? If so, you’re in luck. Scientists from Chicago University are fighting fire with fire, so to speak. They have developed a sort of AI invisibility cloak that will make your images unable to be sampled by the image generators.

The software is called Glaze and “cloaks” the images so that models incorrectly learn the unique features that define an artist’s style. This way, it makes AI plagiarism much less likely.

Research shows that AI image generators can replicate existing photos

by 2 Comments

It might be a good time to study law. Or copyright law, at least. Researchers have released a study that proves that AI image generators can and do, copy existing images that they’ve ‘looked at’ during the machine learning process. This means that there is a chance that anything spat out by the software could be an exact replica of a copyrighted image.

This debunks the favorite argument that AI machines are no different from humans’ learning processes and that everything they sample is merely ‘inspiration’ to create something new. This appears to not be the case, according to the study. Although it is relatively rare at the moment, the researchers predict that with time it could become a greater problem.

I asked A.I to write a PRD for the perfect mirrorless camera

by 3 Comments

As A.I. is getting stronger and more potent, I wanted to see if it is capable of writing a Product Requirement Document (PRD) for the perfect mirrorless camera. Getting a good PRD for a new product is at the heart of camera brands’ work. You can think about it as an effort to decipher the needs of the market and then to bring a product that will meet those needs.

If the PRD is bad, no good camera will come out of it. Of course, a good PRD does not provide a guarantee to a good product, it can still fail on R&D, Manufacturing, Marketing, Supply chain issues and a million other things. But a good PRD is the foundation on which a camera is built. And if the foundation sucks, no amount of R&D, logistics or marketing can turn it into a good camera.

It’s official: Midjourney used a “hundred million” images without permission to train is AI

by 19 Comments

David Holz, the founder of Midjourney, recently admitted something we’ve already assumed: the company’s AI was trained on hundreds of millions of images without consent from their authors. This revelation has sparked outrage among both artists and privacy advocates. It has raised concerns about the ethical implications of such actions, as well as copyright issues that might emerge.

This photographer used AI to help create these exquisite Joan of Arc images

by 1 Comment

Artificial Intelligence (AI) has been hitting the headlines a lot lately. According to popular opinion, it will likely destroy art, photography, and the creative industries as we know them. But is that the whole story? Perhaps we are missing something here. Surely there is a reverse side to all the doom-mongering?

Well, photographer and digital artist Chris Koeppen may actually have found that silver lining. Chris, who goes under the creative alias of An Ethereal Fire, has been using AI for good instead of, you know, evil. He has been using text prompt AI imaging to enhance his creative output and has recently created this series of extraordinary composite images based upon the legendary Joan of Arc. Chris took the time to chat to DIYP about how he made them and about where he sees the future of photography and AI.

Photographer faithfully recreates his work using text-to-image generator

by Add Comment

You may know Antti Karppinen for his amazing conceptual photos and photo manipulations. He’s been merging illusion with reality in his work for a while now, and now he’s added an interesting twist to it: artificial intelligence.

Thanks to tools like DALL-E and Midjourney, you can create an image from pretty much anything you can spell. Antti was curious whether it will be possible with his work. Since it’s dreamy and surreal, Midjourney seemed like a logical choice – and it did a remarkably good job!

Stock photography sites shut down AI images as Getty and Unsplash implement outright bans

by Add Comment

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).

Getty bans AI-generated art due to potential copyright issues

by 1 Comment

Getty Images, one of the biggest stock image platforms, has banned AI-generated images. If you want to upload and sell work you created through DALL-E, Midjourney, Stable Diffusion, or any other text-to-image tool, you won’t be able to do it there.

The reason? Potential copyright issues. Getty is concerned about the legality of such content, so they want to protect the site’s customers from unwanted copyright claims.

Have your photos been used to train AI image generators? This website lets you check

by 1 Comment

Several major text-to-image generators have been launched so far, such as Midjourney, Stable Diffusion, or DALL-E. As you probably know, billions of photos, paintings, and illustrations are used to train these programs so they could render your text into an image with better accuracy.

Have you ever wondered if your photos were used for this purpose? If you have, there’s now a way to check it.

You’ve heard of text-to-image AI, now text-to-video is here

by Add Comment

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.

Free Resources

Advanced lighting book

Learn photography

Recent Posts