Midjourney may have just solved a big problem with AI image generators

AI image generators continue to make new advances almost by the day. Last week, it was the launch of Ideogram with its improved text rendering. Now it seems Midjourney may have just solved one of the biggest problems holding back text-to-image AI: consistency across images.

Specifically, Midjourney has added a tag that's intended to create more consistent characters. Since diffusion-based AI image generators create new images every time, even when using the same prompt, it can be very difficult to create two (or more) images in which a character looks like the same person. This has made it hard to use AI for storyboards or anything that requires that consistency, but the long-requested new feature tells the AI when to try to respect the appearance of the character in a reference image.

Thank you for reading 5 articles this month* Join now for unlimited access

Enjoy your first month for just £1 / $1 / €1

*Read 5 free articles per month without a subscription

Join now for unlimited access

Try first month for just £1 / $1 / €1

TOPICS
Joe Foley

Joe is a regular freelance journalist and editor at Creative Bloq. He writes news, features and buying guides and keeps track of the best equipment and software for creatives, from video editing programs to monitors and accessories. A veteran news writer and photographer, he now works as a project manager at the London and Buenos Aires-based design, production and branding agency Hermana Creatives. There he manages a team of designers, photographers and video editors who specialise in producing visual content and design assets for the hospitality sector. He also dances Argentine tango.

Read more
An image from Venngen, and AI image generator in the shape of a Venn diagram
This Venn diagram-inspired AI image generator is strangely satisfying
AI control era; Adobe logo made from paint
Lazy AI prompts are dead - we're on the threshold of the "Controls Era" says Adobe
A photo of a saxophonist and a conversion to ASCII art
I'm obsessed with an OpenAI o3-generated image to ASCII art converter
An image from Tencent's Hunyuan3D 2 AI 3D generator
Tencent's open-source AI 3D generator could reshape game development
Images from an AI video generator developed by researchers including from Netflix
Netflix-linked AI video model may look janky, but it's a groundbreaking advance
Faces generated with Microsoft VASA-1
The 10 most read AI art stories of 2024
Latest in AI Art
AI-generated art on sale at a stall in India
AI art stall generates furious response
An AI-generated image of a hand with lots of fingers and a chicken nugget. Text reads 'love you AI'
KFC finds a positive side to AI art fails
A screenshot from a video on Autodesk 3D AI model
3D artists are furious with Autodesk over its new generative AI model
An image of a brain among computer circuitry
How generative AI is influencing the creator economy
An AI-generated fashion image
Absolut vodka's attempt to fix AI is kind of weird
Images generated in Google Imagen 2 AI image generator
Artists accuse Google of “massive copyright infringement” with Imagen AI
Latest in News
A billboard advert at GDC 2025 for Revenge of Savage Planet
Savage GDC 2025 billboard ad is revenge for Google Stadia layoffs
Da Vinci Resolve interface
Get free beginners' guide to Da Vinci Resolve 19 from Blackmagic (our favourite free video editing software)
camera phone deals Best Buy
Huge Samsung, Google Pixel and Motorola deals at Best Buy right now – phones from $299.99
Umbro logo
Umbro’s logo design dispute knows no end
An image from teaser animation for ARK: Survival Ascended expansion ARK: Lost Colony
GDC 2025: Lost Colony anime teaser shows ARK: Survival Ascended is the game that has everything
Roblox Cube 3D AI 3D object generation
GDC 2025: Roblox says its new AI generator will go beyond 3D models to allow groundbreaking '4D creation'