AI art tool Midjourney has all the answers to ‘what if’

Inspired by the just lately launched photographs of the universe by NASA, the first immediate I fed into the Artificial Intelligence (AI) tool of analysis lab Midjourney was “a spaceship surrounded by galaxies”. The consequence, as pictured beneath, was a picture of a vessel suspended in area that appears to replicate the cosmos round it – just about true to the immediate.
A spaceship surrounded by galaxies (Credit: Midjourney)
For Midjourney’s founder David Holz, a robust side of generative AI is its “skill to unify with language”, the place we will “use language as a tool to create issues”. In easy phrases, generative AI makes use of instructions from the consumer to create novel photographs based mostly on the dataset it has learnt from completely different sources over time.
The rise of text-to-image technology has additionally raised philosophical questions over the definition of an ‘artist’.
British mathematician Marcus du Sautoy argues in his ebook, The Creativity Code (Art and Innovation in the Age of AI), 2019, “Art is finally an expression of human free will and till computer systems have their very own model of this, art created by a pc will at all times be traceable again to a human want to create.” He states that if we had been to create a “thoughts” in a machine, it might maybe provide a glimpse into its ideas. “But we’re nonetheless a good distance from creating aware code,” du Sautoy concludes.
Similarly, Holz notes, “It’s necessary that we don’t consider this as an AI ‘artist’. We consider it extra like utilizing AI to increase our creativeness. It’s not essentially about art however about imagining. We are asking, ‘what if’. The AI kind of will increase the energy of our creativeness.”
Midjourney permits its customers to feed of their prompts on its Discord server after which generates 4 photographs akin to the textual content. The consumer can select to discover extra variations and upscale the good match to the next high quality picture. The bot entered open beta final month, giving customers a sure variety of free trials to deliver their imaginations to life. The photographs generated may also be minted into NFTs, for which, till just lately, Midjourney charged royalties.
“It’s a large group of virtually one million people who find themselves all making photographs collectively, dreaming and riffing off one another. All of the prompts are public and all people can see one another’s photographs… that’s fairly distinctive,” Holz tells
Holz co-founded Leap Motion, a hand-tracking movement seize user-interface firm, in 2010, and was featured in the Forbes 30 below 30 listing of 2014. He now runs a small self-funded analysis and design lab, Midjourney, which is exploring a bunch of numerous initiatives, together with the AI visualisation tool, with 10 different colleagues.
Elaborating on the response obtained by the AI bot, Holz says, “Lots of people are very blissful and discover utilizing the product a deeply emotional expertise. People use it for all the things from a challenge to art remedy. There are individuals who have at all times had issues of their thoughts however had been unable to specific it earlier than. Some folks have circumstances like aphantasia, the place the thoughts can’t visualise issues, and they’re now utilizing the bot to visualise for the first time of their life. There’s quite a lot of lovely stuff taking place.”
The bot additionally takes care to stop the misuse of the platform to generate offensive photographs. The group tips urge customers to chorus from utilizing prompts which can be “inherently disrespectful, aggressive, or in any other case abusive” in addition to generate “grownup content material or gore”. Midjourney additionally makes use of moderators who be careful for folks violating the insurance policies and provides them a warning or ban them. It additionally has automated content material moderation the place sure phrases are banned on the server. The AI, too, learns from consumer knowledge, Holz explains. “If folks don’t like one thing, it generates much less of that.”
I chanced upon the Midjourney bot throughout a cursory look via my Twitter feed, the place I noticed consumer psychedelhic’s renditions of a considerably post-apocalyptic Delhi.

Having beforehand dabbled with AI bots like Disco Diffusion and Craiyon, an attention-grabbing side of discovering Midjourney was how completely different AIs would reply to the similar texts. The photos beneath present the outcomes generated with the similar immediate, ‘metropolis throughout monsoon rains’, by Midjourney, Disco Diffusion, a free-to-use AI tool hosted by Google Colab, and Craiyon, previously generally known as DALL-E mini.
A metropolis throughout monsoon rains (Credit: Craiyon)
A metropolis throughout monsoon rains (Credit: Disco Diffusion)
A metropolis throughout monsoon rains (Credit: Midjourney)
While Craiyon throws up comparatively sensible photographs, Disco Diffusion exhibits surreal, impressionistic outcomes, and Midjourney sits considerably in the center of the two.
According to Holz, Midjourney might be understood as a “playful, imaginative sandbox”. “The purpose is to give all people entry to that sandbox, so that everybody can perceive what’s potential and the place we’re as a civilisation. What can we do? What does this imply for the future?”
Holz dismisses fears that AI is right here to “change” people or their jobs. “When pc graphics was invented, there have been related questions — will this change artists? And it hasn’t. If something, pc graphics makes artists extra highly effective,” he says.
Holz provides, “Whenever we see one thing new, there’s a temptation to try to determine if it’s harmful and we deal with it like a tiger. AI isn’t a tiger. It’s really extra like a giant river of water. A tiger is harmful in a really completely different manner than water. Water is one thing that you could construct a ship for, you’ll be able to be taught to swim, or you’ll be able to create dams that make electrical energy. It’s not making an attempt to eat us, it’s not offended at us. It doesn’t have any emotion or emotions or ideas. It’s identical to a robust drive. It is a chance.”

Recommended For You