Toronto-based AI startup Ideogram has officially launched its platform. The company specializes in generative text-to-image technology, so this is yet another text-to-image generator and competition to Midjourney, DALL-E, and Adobe Firefly.
Midjourney has added a new inpainting feature that many users have requested. Much like Adobe’s Generative Fill, it lets you change only a part of your image that you manually select. As for the rest of the image, it stays intact. Of course, I just had to test it out, and I bring you some Midjourney images of cats and dogs I created with this new tool.
Leading AI image generator, Midjourney, can still create misleading and harmful images, according to a recent study. All AI image generators have a series of blocks and restrictions that stop users from generating what could be harmful content. Most of these restrictions protect misinformation about public figures or sexually explicit or hate-fuelled content, for example.
The Center for Countering Digital Hate, a nonprofit group, shared the study with Bloomberg. They discovered that these restrictions could quite easily be circumnavigated simply by substituting words for visibly similar non-triggering items.
The world of art has always been a space for creativity, expression, and innovation. Throughout history, artists have pushed boundaries, challenged conventions, and embraced new technologies to create groundbreaking works. Artificial intelligence (AI) has brought about a significant shift in the artistic landscape in recent years, sparking both fascination and concern.
One platform that has captured the attention of many artists is MidJourney, which offers new functionality that allows users to zoom out and generate images endlessly quickly. This capability has opened up a realm of possibilities for storytelling and experimentation. This new feature inspired me, and immediately, I wanted to use it to tell a story. I settled on a music video as a concept.
Midjourney has just launched its new version, 5.2, and it’s a game-changer! There are several new features in the new update, but the hottest one is the “Zoom Out” feature, which creates a wider view of your image and automatically fills in the rest. I played with it to test it out, and while there are still some hiccups – it’s pretty impressive overall. So, let’s dive right in and see how it works.
Sony World Photography Awards recently published the winners and shortlists of its Open competition. The photos are absolutely stunning, but there’s just one problem – the Creative category winner isn’t a photo at all. The winning image resembles a portrait photo from the 1940s, with a characteristic vintage, nostalgic feel. But on a closer look, you can spot the weird hands – one of the biggest weaknesses of text-to-image generators.
This case sparked some serious debate in the photo community. It also made me think about AI and its place in photography. Should AI-generated art enter and win photography contests? Is it fair? Are there legal issues? I wanted to discuss all of this and more in this article.
I don’t know many photographers these days who aren’t comfortable using post-processing software such as Photoshop or Lightroom. Many of these programmes are beginning to introduce AI features, with Adobe launching its own text-to-image generator Firefly this last month.
I can see the allure of using AI to fix skin retouching issues or make masking easier, for example. But how could we utilize text-to-image generators such as Midjourney to our advantage without denigrating ourselves as photographers? In this video, photographer Andrea Pizzini attempts to answer that question by demonstrating the new ‘describe’ feature.
Text-to-image generator Midjourney has stopped free trial due to “trial abuse,” as its CEO explains. There has been a massive influx of new users lately, which kept crashing the site for paid ones. So, if you’ve been using your free trial – sorry, you’re going to have to pay earlier than you thought if you want to continue using the popular text-to-image tool
All images that are created via text-to-image prompts are not protected under US copyright laws, the US Copyright Office (USCO) has stated. That means that anything created via Stable Diffusion, Dall-E or Midjourney cannot be copyrighted, at least in the USA.
The USCO equated the prompt-creator to telling an artist or designer what to make. That is, the idea itself is what is being discussed, and as such, the idea has no value available to be given copyright protection.
To look at Jos Avery‘s Instagram account is to be greeted by a sea of beautiful portrait photographs staring right back at you. The sheer number and variety is staggering, and his 27K+ followers seem to agree, often asking for tips and tricks to emulate the photographer they hold in esteem.
Except that there is one issue. Namely that none of these ‘photos’ were taken with a camera. Avery has recently ‘come out’ and admitted that all of them were created using Midjourney, an AI image generator.