Midjourney has enabled users to generate consistent characters across multiple images to test its new feature.
The challenge of maintaining consistency in AI-generated images prompted Midjourney to develop this tool. This addresses the disparity often encountered in successive AI model runs.
The move aims to enhance storytelling and world-building experiences.
We're testing a new algorithm today to help you have "consistent characters" across your images. Check out our announcement channel for more instructions. It works for both MJ6 and Niji6 models. We hope this helps you play with telling stories and building new worlds <3
— Midjourney (@midjourney) March 11, 2024
The “consistent character” feature empowers users to seamlessly carry over previously crafted characters to new images with customizable variances. It might be ideal with scenarios like storyboarding and comic book creation.
Founder David Holz clarified that the feature is optimized for Midjourney-generated characters. However, some users experimenting with uploading real people’s images might face potential distortions.
Twitter Reacts With Testing New Tool
Despite concerns about potential copyright issues, the feature’s debut has sparked excitement among content creators.
Some think new algorithm is not yet perfect, yet very useful.
It's not perfect (for now), but it's extremely useful, especially for how I use it. pic.twitter.com/qM6NOIQxKD
— MELTEN (@meltenx) March 12, 2024
Others show the implementation of the new feature, such as placing a single character in various circumstances.
Another test with @Midjourney consistent characters. Larry has done it all. Arctic exploration, being a life guard, roaming the streets of NYC as a homeless guy after gettting fire without severance as a corporate executive.
Larry's the man! pic.twitter.com/VWFZ36Fskl
— AI & Design (Marco) (@AIandDesign) March 11, 2024