Get all your news in one place.
100’s of premium titles.
One app.
Start reading
Tom’s Guide
Tom’s Guide
Technology
Ryan Morrison

I just tried Midjourney's new random style feature — here's the results

MidJourney website.

Midjourney has finally updated its random style feature so that it works with the current version of the artificial intelligence image generation model. 

Added as a parameter at the end of your prompt, it effectively leaves the look and feel of the image entirely up to the AI to determine. 

During testing I had the same prompt create everything from anime and action figures to full on film noir and greyscale. Its an easy way to test the possible.

If you haven't used Midjourney before and want to get a better feel for the powerful AI image generator we have a guide to using Midjourney and a selection of prompts to try out.

How does Midjourney random style work?

(Image credit: Midjourney)

You can randomize the style of an image by typing --sref random at the end of your prompt. If you repeat the prompt multiple times with the same parameter you’ll get a range of images in a variety of styles. It didn't duplicate once in a dozen tests.

This is a great way to get started with Midjourney if you’re new to the AI image generator as it gives you an idea of what is possible, how styles can vary and inspiration for your next image.

If you like a particular style you can then type --sref and the url of the image you liked after another prompt to keep that style across future images.

Putting Midjourney random style to the test

I came up with a simple prompt that AI image models sometimes struggle with — a cat in a spacesuit on the moon — and then added the –sref random parameter.

David Holz, Midjourney CEO said that this change was part of a test of new algorithms for "exploring the latent space of visual styles." He described --sref random as a "fun tool for everyone play with."

"This is meant to be a test of a underlying algorithm that we make more advanced tools for in the future," he declared.

I ran each generated image through Midjourney Describe to get an idea of how the AI model interpreted the style it referenced. What I'd like as a future upgrade is a way for Midjourney to also offer up a description of the style when you use random.

1. Grumpy Cat (photorealism)

(Image credit: Midjourney/Future AI image)

Midjourney describes this image as: "A Persian cat in an astronaut suit on the moon, photo realistic, high resolution photography."

This captivated me the moment in generated but certainly isn't a style I'd bother to replicate as its basically a generic photorealism, albeit with an element of tilt shift.

2. Duke Cat-em (Sci-fi)

(Image credit: Midjourney/Future AI image)

Midjourney describes this as: " A cat astronaut in space, holding an energy weapon and wearing full protective gear with glowing eyes against the backdrop of Earth, space background, detailed character design in the style of space punk, high resolution, high quality artwork."

This one feels like something out of a game adaptation of a dark sci-fi comic book called something like Space Cats and the Battle for Planet Earth. I would definitely try this style again.

3. Puzzled Cat (3D render)

(Image credit: Midjourney/Future AI image)

Midjourney says: "A Bengal cat in an astronaut suit on the moon, in the digital art style, a full body portrait, a hyper realistic illustration, with detailed background elements, cinematic lighting, vibrant colors, with elements of fantasy and surrealism, high resolution, high detail, an octane render, created in 3D using the Unreal engine."

My first impression of the image was of something out of a classic sci-fi show that had been colorized. The retro-futuristic space suit and slightly vacant stare are my favorite parts of the image. There is something enchanting about this style.

4. Menacing Cat (Ink Wash)

(Image credit: Midjourney/Future AI image)

Midjourney described this image as: "A black and white drawing of an astronaut cat on the moon, full body, with a detailed background, hyperrealistic illustrations in the style of detailed character designs, ink wash paintings in the fantasy art style."

This is an image I'd like hanging from my office wall but isn't necessary a style I'd try again. Its a bit intense for my taste. But I'd consider trying the style on a different topic.

5. Surprised Cat (Meme)

(Image credit: Midjourney/Future AI image)

Midjourney described this as: "A white cat on the moon looking at earth in space, screencap from a YouTube video about cats that went to space in the style of cats that go to space."

While it does have something of a YouTube thumbnail about it, this image screams meme to me. There's even space for the text. I'd put something like "how much did I have to drink last night" in the top left corner. I'd use the style again to make a meme.

6. Cat-astrophy (Glitch)

(Image credit: Midjourney/Future AI image)

Midjourney didn't have much to say about this one, simply describing it as: "A cat in an astronaut suit on the moon, black and white photography, glitch art."

I love the intensity of this image. Not only does the picture feel broken but there is a pain in the face of the cat as if it is pondering the meaning of life. I'd use this style again in a heartbeat. 

7. Cute Cate (Kawaii)

(Image credit: Midjourney/Future AI image)

Finally Midjourney writes: "A 3d render of an orange and white calico cat in space suit on the moon, cute cartoon character design with little details, walking towards camera with astronaut hangar in background, cute kawaii."

One word — adorable! This is a fun style that could be used to create images for an eventual stop-motion animation in Runway or Pika Labs.

More from Tom's Guide

Sign up to read this article
Read news from 100’s of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
One subscription that gives you access to news from hundreds of sites
Already a member? Sign in here
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.