Midjourney releases new, unified AI image editor on the web

Midjourney releases new, unified AI image editor on the web


Sign up for our daily and weekly newsletters to stay up to date with the latest updates and exclusive content on industry-leading AI coverage. More information


Amid increasing competition in the field of AI image generation from companies such as Elon Musk's permissive Grok-2 (powered by Open source Flux.1 model from Black Forest Labs), one of the leaders is going to step it up a notch.

Halfway through the journeywhich is hailed by many AI artists and designers as the most prominent and high-quality AI image generator, unveiled a new, updated version of its website last night with a new editor interface that combines several existing features such as inpainting (recoloring parts of an image with new AI-generated images using text prompts), outpainting/canvas extension (stretching the boundaries of the image in different directions and filling the new space with new AI images), and more into a single view.

Watch a video below on how to use Midjourney's new menu:

Additionally, the new web editor includes a new virtual 'brush'-like tool for coloring, replacing the previous square selector and lasso tools, and allows for greater precision when using AI to edit parts of a previously 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 going to midjourney.com/imagine.

Previously, these features were accessible to Midjourney users on the web, nestled under various menus. The goal, according to one Discord message sent by Midjourney CEO David Holzis to make editing AI generations easier and smoother.

As Holz said, “We think this will make editing your MJ images much smoother than before and is a huge step forward.”

The first reactions from users are indeed predominantly positive:

More platform updates

In addition to the web editor, Midjourney has introduced another feature aimed at improving communication between the web and Discord communities. Messages sent in certain webrooms will now be mirrored in their corresponding Discord channels, and vice versa. This integration ensures that users on both platforms can stay in sync, no matter where they choose to communicate. 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.

This comes at a controversial time for Midjourney and AI art in general

The release of the new web editor and post mirroring feature underscores Midjourney's commitment to continually improving the tools and community experiences it offers its users, even as it is facing a class action lawsuit from a group of artists who are accusing the startup of copyright infringement, alleging that they have been giving mass and unauthorized training sessions on their (and many other) copyrighted images.

Last week, the judge in that case denied requests by Midjourney and other AI generator company defendants to dismiss the case, and it is now on the way to discoveryallowing lawyers for the artists bringing the case to review internal documents from the AI ​​companies and reveal more about their training practices and data sets to the public.

Holz also expressed his gratitude for the patience the community has shown during the development process and encouraged users to explore the editor's new capabilities.

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