Search Results for: node/diffusion

Getty launches another AI-generated service with iStock

Jan 12, 2024 Alex Baker

Getty Images has launched a second AI generator as part of its stock image services. This new feature will be a part of iStock and…

Midjourney soon to generate AI videos, reports say

Jan 5, 2024 Dunja Đuđić

Midjourney has become even better at generating photos with its latest version, but the company seems to have more surprises. According to recent reports, you’ll also be able to generate videos through Midjourney in only a few months.

Midjourney tried to copy famous photographers’ styles, court docs reveal

Jan 4, 2024 Dunja Đuđić

Midjourney came under the spotlight again for all the wrong reasons. Recently revealed court documents show a massive list of names Midjourney keeps to “feed” its image generator and make it copy the distinctive styles of various artists. They include illustrators, painters, animators, and more. And, of course – photographs are no exception.

What did AI mean for photographers in 2023?

Dec 29, 2023 Alex Baker

Artificial Intelligence took the reigns in 2023 with a new development every other day (or so it seemed). How is it possible that ChatGPT and…

Groundbreaking AI “reads your mind”: Turns thoughts into images with 75% accuracy

Dec 6, 2023 Dunja Đuđić

In a groundbreaking study, researchers in Japan have reconstructed images from human brain activity using artificial intelligence. While this isn’t the first study of this kind, it is the first that managed to reconstruct images without the subject looking at them. In other words – only their thought was enough, and AI achieved an astonishing accuracy of over 75%!

Stability AI’s new AI generator creates images faster than you imagine them

Dec 1, 2023 Dunja Đuđić

On Tuesday, Stability AI introduced a new AI image-synthesis model, Stable Diffusion XL Turbo. The bombastic name reveals its main advantage: it generates images at an unprecedented speed. It produces images in a single step, compared to the 20-50 steps its predecessor required. In other words, it can generate images as fast as you can type… maybe even faster.