Midjourney releases new unified AI image editor on the web

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More


Amid intensifying competition in the AI image generation space from the likes of Elon Musk’s permissive Grok-2 (powered by Black Forest Labs’ open source Flux.1 model), one of the leaders is stepping up its game.

Midjourney, which is hailed by many AI artists and designers as the preeminent and highest quality AI image generator, last night unveiled a new, updated version of its website containing a new editor interface that unifies various existing features such as inpainting (repainting parts of an image with new AI generated visuals using text prompts), outpaining/canvas extension (stretching the boundaries of the image in different directions and filling the new space with new AI visuals), and more into a single view.

Watch a video of how to use the new menu from Midjourney below:

Furthermore, the new web editor contains a new virtual “brush”-like tool for inpainting, replacing the previous square selector and lasso tools and allowing for more precision when it comes to using AI to edit parts of a prior generated image.

Screenshot of Midjourney’s new more precise inpainting brush tool. Credit: VentureBeat/screenshot by author

The new web editor is now live and available to all users who have created at least 10 images on the platform. Users can access this tool by visiting midjourney.com/imagine.

Previously, these features were accessible to Midjourney users on the web nested under more disparate menus. The goal, according to a Discord message sent from Midjourney CEO David Holz, is to make editing AI generations easier and more seamless.

As Holz stated: “We think this makes editing your MJ images way more seamless than before and is a huge step forward.”

Indeed, early reactions from users are largely positive:

More platform updates

In addition to the web editor, Midjourney has introduced another feature aimed at improving communication between its web and Discord communities. Messages sent in certain Web Rooms are now mirrored in corresponding Discord channels and vice versa. This integration ensures that users across both platforms can stay in sync, regardless of where they choose to interact. The rooms with message mirroring include prompt-craft, general-1, and a special superuser room for those who have created more than 1,000 images.

Coming at a contentious time for Midjourney and AI art generally

The release of the new web editor and the message mirroring feature highlights Midjourney’s commitment to continually enhancing the tools and community experiences it offers to its users, even as it faces down a class-action lawsuit from a group of artists accusing the startup of copyright violations for allegedly training en masse on their (and many other) copyrighted images without permission.

Last week, the judge in that case denied Midjourney and other AI generator company defendants’ bids to have the case dismissed and it is now proceeding toward discovery, which should allow lawyers for the artist plaintiffs who are suing to be able to peer through internal documents of the AI companies and reveal more about their training practices and datasets to the public.

Holz also expressed gratitude for the community’s patience during the development process and encouraged users to explore the new capabilities provided by the editor.

As Midjourney continues to innovate and expand its platform, users can expect more updates and features aimed at improving the overall creative process and fostering a more connected community.



Source link