The capabilities of artificial intelligence (AI) image creation tools have grown at a breakneck pace – here’s a look at some of the best available on the market.
If there’s a definitive buzz phrase in 2023, it should be “Generative Artificial Intelligence.”
The explosion of interest in OpenAI’s chatbot ChatGPT set the stage for a year in which millions of people started using the generative AI tool for the first time.
While entire articles or examination papers can be generated by a simple text prompt, text prompts can also be used to generate images. Many platforms have emerged that allow users to create artwork, posters, logos, presentations, and photorealistic images with just a few words.
They can do this thanks to machine learning. Neural networks are trained on massive datasets, learning to identify patterns and features in images. The algorithm then uses this learned knowledge to guess what the text prompt is looking for.
We’re taking a look at some of the most popular image creation tools available today. Before diving in and using the platform, it’s worth paying attention to the copyright situation around AI-generated images. There are already several lawsuits underway, in which artists are claiming damages from companies whose AI platforms were trained on their copyrighted material.
Let’s take a look at the five best image generators available today.
Ready: “A powerful magician is casting a spell”
One of the first AI image generators to go large, MidJourney attracted millions of users to its platform as users were amazed by its capabilities, and tempted by its free trial. That free trial no longer exists, so you’ll now have to pay for a subscription to try it yourself, with prices starting at $8 (€9.33) per month.
The process can be tricky, as it works through Discord rather than a standalone platform. With some trial and error, or by taking lessons from the many inspiring guides available online, you will quickly see how powerful MidJourney is in creating photorealistic images, art, cartoons or sketches as you desire.
No wonder it already has over 15 million users.
DALL E 2
Ready: “Painting of a plane flying at dusk in the style of Vincent Van Gogh.”
From the company behind the hugely popular ChatGPT, OpenAI’s DALL·E 2 is another popular image creation tool.
Users can generate multiple images on the free plan and to do so in bulk they will have to sign up for a paid plan. This platform has millions of users, although it doesn’t do as well as MidJourney for photorealistic-style images. With a habit of imitating the style of famous painters, he excelled in artwork.
And just as OpenAI’s GPT-4 powers the Microsoft Bing search engine’s AI chatbot, DALL·E 2 also powers Bing’s image generation tools.
DreamStudio (Stable Spread)
Ready: “Steaming mug of tea on a rustic wooden table. Trees are visible through a window in the background.”
One of the early big hitters, Stable Diffusion is a popular image creation model, with a free tool available on web browsers. DreamStudio uses the Stable Diffusion Model and has many options and a professional user interface.
You get a certain amount of free credits when you sign up, and then you have to pay to top them up. The results are impressive, especially when creating human faces – although like all these image generators, there seems to be a particular problem with human hands.
DREAM BY WOMBO
Ready: “Alien Space Station”
Geared towards art creation, like other platforms, you just put in a simple text prompt and it will deliver images dreamed up by the algorithm. As the name suggests, the images it creates are somewhat dreamlike, with results that are abstract and often scary.
With dozens of art styles to choose from (including things like ‘bad trip’ or ‘steampunk’) it’s a real playground for art creation. It is available as a web app and a mobile app.
Ready: “A man driving a supercar on the road with the Eiffel Tower in the background.”
The popular graphic design platform that is largely used to create social media posts and presentations has jumped into generative AI with both feet.
We’re including it as a special mention because its capabilities in generating the above media types are really impressive. It also has a free image generation AI that is perhaps a little less sophisticated right now.
It has quite strict rules about the type of images it can create. For example, it refused to depict Emmanuel Macron driving a Ferrari down the Champs-Élysées, so we had to settle for “a man driving a supercar on the road with the Eiffel Tower in the background” instead. Looks like it’s still a work-in-progress.