Midjourney launches a collaborative multiplayer worldbuilding tool named ‘Patchwork.’

VentureBeat with Midjourney

Join our daily and weekday newsletters to receive the latest updates on AI industry coverage. Learn More


Midjourney is expanding beyond AI image creation and editing. The popular AI image generation startup has more than 21,000,000 users on its Discord server.

Patchwork revealed

Max Kreminski of Midjourneyโ€™s Storytelling Lab demonstrated the new tool called “Patchwork” in a screenshare livestream on Discord and X through Restream.

Screenshot of a Patchwork world.

He clarified that it would be a stand alone app that would require Midjourney accounts to log into, and that the URL would be available as a โ€œresearch previewโ€ in the Midjourney Discord serverโ€™s โ€œupdatesโ€ channel. Users will need to connect their Midjourney Discord account to their Google Account to access Patchworkโ€™s research preview. The company posted instructions for doing so on its X account.

The tool appears to be a web-based blank white, infinite canvas with a โ€œtoolboxโ€ on the left side of the browser screen, showing a variety of buttons labeled for โ€œcharacter,โ€ โ€œevent,โ€ โ€œfaction,โ€ โ€œplace,โ€ โ€œprop,โ€ and โ€œrandom,โ€ as well as tools such as โ€œnote,โ€ โ€œimage,โ€ โ€œportal,โ€ โ€œsaveโ€ and โ€œshare.โ€ โ€œSaveโ€ downloads a JSON file with links to all the Midjourney images created in the canvas. Midjourney considers each canvas a separate digital โ€œworld.โ€

To switch between worlds, the user creates a โ€œportal,โ€ a small black circular button.

To generate a new world, the user enters a text prompt into an editor bar at the top of the โ€œcreateโ€ screen and selects one or more of a set of 10 different image styles.

This then produces a new whiteboard with a bunch of new still image assets and text boxes or entities known as โ€œscrapsโ€, including input boxes that allow the user to prompt new images or settings that fit the initial world description, even whole new AI generated character descriptions.

In the demo livestream, the character name automatically populated with Marcus โ€œDizzyโ€ Gillespie, echoing the name of the famous jazz musician. Dragging the description into a new character image creator box produces four new AI-generated images.

Adding new character boxes, the user can then prompt to create names and characteristics, as well as motivations that can spur a conflict for the basis of a story.

The user can then link characters together with lines that denote connections between them. They can also write action sequences and scene descriptions that each narrate a story. Each character can be used in multiple images and these images gathered together with a single option.

The user can โ€œshareโ€ the board with other Midjourney users who can collaborate, purportedly in real-time, with multiple cursors moving across the same shared canvas. A single world can support dozens, even up to 100 users, according to Kreminski. However, he noted that the more users, the more chaotic the experience would be.

Kreminski said only users who are logged in can view boards (for now), but in the future, boards may be viewable by non-users. He mentioned that tabletop roleplaying groups were already using the feature to chart their campaigns.

He also said that Midjourney version 7 (V7) would include a setting to allow multiple character consistency across different and new images.

Moving towards immersive 3D worlds

Kreminski revealed that the application was powered by at least three different large language models, including one that was fine-tuned and unique to Midjourney.

It appears to be an innovative, complex, powerful and somewhat overwhelming tool for storyboarding. I could see it being used by film directors, comic book creators, writers, and even live theatre directors and writers.

Kreminski said that in the long run, there was a “very obvious path” in terms of escalation in the details and interactions of the worlds, including fully immersive virtual reality scenes. But this was still years away.

Other AI researchers, startups like Fei-Fei Liโ€™s World Labs and big tech companies like Google are working to develop AI which can create 3D immersive worlds online using simple prompts or pictures.

More Midjourney updates are coming soon

David Holz, the creator of Midjourney, also joined the livestream announcement to announce that the startup will launch multiple model customization modes in the next few days.

Midjourney currently allows users to rate pictures to personalize what visuals they would like to see in future generations and fine-tune their model to suit personal preferences. The startup will now allow users to toggle between multiple personalized versions.

Holz also shared that Midjourney will allow users to upload multiple images and reference them to boards in order to guide future generations.

Midjourney is also planning to introduce video models and an AI image generator, the Midjourney V7, after Christmas (December 25,) that will have increased prompt understanding.

Holz revealed that Midjourney was working on three or four new hardware projects. He said the startup is “trying to become a research lab…it could take us six months before we announce all six things.”

VB Daily provides daily insights on business use-cases

Want to impress your boss? VB Daily can help. We provide you with the inside scoop on what companies do with generative AI. From regulatory shifts to practical implementations, we give you the insights you need to maximize ROI.

Read our privacy policy

Thank you for subscribing. Click here to view more VB Newsletters.

An error occured.


Read More

More from this stream

Recomended


Notice: ob_end_flush(): Failed to send buffer of zlib output compression (0) in /home2/mflzrxmy/public_html/website_18d00083/wp-includes/functions.php on line 5464