We now know that AI art generators are not created equal. Many of the free AI art generators produce strange blurry results that look like a random image captured on one of the first camera phones, while more powerful tools can create convincing photorealistic images and recreate artistic styles. Now, an artist using the tools has done a head-to-head comparison of three of the best AI art generators available, and the results are fascinating.
The experiment shows very different results from each tool, offering insight into how each interprets the prompts. If we didn’t know better, we’d almost think that each AI art generator has its own personality and style like a human artist. What’s clear is that each tool has its strengths and weaknesses, and sometimes even a recognizable look based on its algorithms and the image database it’s fed, and that’s something artists can draw from. take advantage (see our guide on how to use DALL-E 2 if you want some tips).
DALL-E 2 vs Midjourney vs StableDiffusion mega thread: photography, illustration, artists, abstract these image synthesizers are like tools – it’s amazing we’ll get so many of them, each with a unique “sound” 🤯rules: same prompt, 1 : 1 ratio, no living artists pic.twitter.com/47syy7uPJJAugust 20, 2022
Based in Berlin Fabian Stelzer (opens in new tab), who describes himself on Twitter as a “fast intern” working on three AI-based projects, performed the image comparison experiment using the Midjourney, DALL-E 2, and Stable Diffusion AI text-to-image art generators. He entered the same guidelines for each tool and used a 1:1 ratio for the resulting images.
With prompts ranging from “low poly game asset, Cthulhu monster, 2000 video game, isometric view” to “1990 image of a laughing crazy fax machine, Windows 3.1, MS-DOS, early computer art” , the results Stelzer shared in his Twitter thread allows us to compare how the tools handle different types of requests.
Image 1 on 6
Midjourney’s creations often seem very dark – almost apocalyptic. After all, it’s the tool that was used to create the “last selfie on Earth” images that have been circulating recently (see our review of the weirdest AI art). We think this AI art generator definitely needs a consultation, but it also seems to often produce the most natural results when it comes to artistic styles, especially with textural details. All the artifacts look natural, while in DALL-E 2 the artifacts often look like obviously digital problems.
DALL-E 2 has a tendency to randomly throw in made-up words, but it seems to be the best tool for creating photorealistic images and for processing facial expressions. Stable Diffusion, meanwhile, often seems to produce the cleanest results—Stelzer notes that it can also produce amazing photos, but you have to be careful not to “overload” the scene. It is also good for recreating the artistic styles of certain artists.
Stelzer says he sees these and other AI art generators much like musical instruments, each with its own range and timbre. The Midjourney is like an analogue Moog – beautiful but with limited range, while the DALL–E 2 has a huge range but a more obviously digital output “These imaging synths are like instruments – it’s amazing. We’re going to get so many of them, each with a unique “sound,” Stelzer says, adding, “You want to play ‘n’ prompt DALL-E / Midjourney / StableDiffusion individually to your own strengths.”
Image 1 on 5
The three tools have other differences beyond the initial results of how they handle prompts. DALL-E 2 offers a powerful drawing function that allows you to edit part of an image, while Midjourney has a large, active community of users for support and inspiration.
Stelzer believes that AI art generators will revolutionize creative work in ways we haven’t seen since the advent of photography—”what photography was to painting, image synthesizers are to photography,” he says, and he predicts that soon everyone will can create movie content by typing it. It uses AI to create a 70s sci-fi movie narrated by the community SALT (opens in new tab) and the experimental game on Twitter @battleprompts (opens in new tab)in which players summon monsters through prompts, is a fascinating look at the creative possibilities that could emerge through AI-generated art and AI-generated video.