Halfway through the journeythe successful AI image generation startup, founded and run by former Magic Leap engineer David Holz, is delighting users with a latest feature unveiled last night: AI image editing.
As many of Midjourney’s 20 million-plus users (including some of us at VentureBeat) probably know, Midjourney previously allowed users to upload their very own photos collected off-site to its alpha web interface and/or a Discord server to function a reference point for the AI image generator’s diffusion models – the latest being Midjourney 6.1. After receiving the uploaded reference image, Midjourney’s AI model is able to generate latest images based on the file provided by the user.
However, this reference function didn’t actually make any changes to the source image – it just used it as a form of loose place to begin.
Now, with Midjourney’s latest “Edit” feature, users can upload any image of their selecting and edit sections of it using AI, or change its style and texture from the source to something completely different, reminiscent of transforming an old photo into an anime – while retaining most of the themes and objects of the image and spatial relations.
It even works on user-submitted doodles and hand-drawn drawings, turning your doodles into full artistic endeavors in seconds.
Midjourney has released a video demonstration showing how to use the latest features, which we have embedded below:
VentureBeat uses Midjourney and other AI tools to create content for our website, social channels and other formats.
Please note that despite its popularity, Midjourney is one of several artificial intelligence firms that have been sued in a class motion lawsuit filed by human artists for alleged copyright infringement by scraping human-made works without express consent, authorization, consent or remuneration for training their models. The case stays in court for now.
The Midjourney image editor appears to be limited to only the latest AI model, Midjourney 6.1, which makes sense.
In message to the Midjourney Discord communityHolz wrote that: “All of this is very new and we want to give the community and moderation staff time to gently get used to it…”
As a result, the latest Midjourney Editor feature is currently only available to users who have generated greater than 10,000 photos with the service, those with an annual paid membership, and those that have subscribed to the service for a 12 months or more.
However, if you meet these criteria, you need to use the latest Midjourney image editor by following the instructions below.
How to find and start using the Midjourney image editor
The latest Midjourney image editor is available exclusively on the alpha web interface, available at alfa.midjourney.com.
Once logged in, an eligible user should see a latest button along the menu on the left, about halfway down, with an icon of a small pencil on a pad. Hovering your cursor will show it reads “Edit” (or the text will robotically be permanently displayed if your browser window is wide enough).
Clicking on this could bring up a latest Editor screen which should present the user with two essential options: “Edit from URL” and “Edit Uploaded Image”.
The latter requires the user to have the file saved on their computer, while the former can accept a big selection of images hosted on various web sites reminiscent of Wikimedia Commons if the user simply pastes the correct link to the image hosted on the web. For the purposes of this text, I provided the URL of the file concept automotive image below from Wikimedia Commons.
After uploading a copy of the file to Midjourney via the URL or the user’s own file repository, the image should appear in the center of the latest editor screen as follows:
You’ll notice that in the menu on the left side of the internal sidebar there is a big selection of options and different buttons that users can select to modify an image in Midjourney 6.1, including “1. Erase”, which allows the user to erase and paint over parts of the image using artificial intelligence using a brush and text prompt, “2. Move/Resize,” which allows the user to move an image around the virtual canvas and expand its edges with latest, matching AI images, and “3. Restore”, which is the opposite of Erase and allows the user to keep any portions of the source image that they by accident painted over with the Erase brush.
The user can control the size of the brush using the slider in the left sidebar, in addition to the “scale” of the image, zoom in and out, and the aspect ratio itself, using more presets below.
There is also a “Suggest a Prompt” button, which Midjourney explains when you hover over the text. It is intended to help the user generate a tooltip for the image they only uploaded – in case they need to change the tooltip or use it to generate the whole image. latest similar image. Suggested tooltip text should robotically appear in the tooltip box/bar at the top of the screen.
Looking at our concept automotive example, I went ahead and used the Erase brush tool on the driver and the text input bar at the top of the Midjourney web interface to replace the driver with a “flaming skeleton.” After entering the text prompt in the top input bar/box, I hit the button labeled “Submit Edit” or type on the keyboard to apply the changes.
Similar to Midjourney’s raw image generator, the Editor robotically creates 4 versions for each text prompt – visible in the right sidebar under the “Send” button.
Here is the best results of my experiment:
The user can then select to proceed making latest changes to the resulting image, scale it using Midjourney’s built-in scaling module using the button below, or download it as is.
Retexturing turns images into latest adaptations in different styles
Additionally, astute readers and Midjourney users will notice that when you click the “Retexture” tab in the left sidebar, one other set of Editor options is also available.
As Midjourney itself explains in the left sidebar when you click this feature:
As you will see in the screenshot I posted above, there’s a lot less going on on the Rexture screen than on the regular edit screen. Basically your only option is to use the tooltip text entry bar/box at the top of the screen to specify what sort of retexturing you would like to do to the source image you/user provided.
Once this is entered, the user can click “Upload Rexture” and viola, Midjourney will use AI to apply the latest texture and adjust the image according to the user’s instructions, again generating 4 versions for him to select from.
In my case, I attempted many different styles including but not limited to anime, cave painting, coloured sand, grotesque slime, and cyberpunk styles. See some of the retexturing examples I received below. One note on my limited testing so far – the retexturing feature seems to warp and remove some detail from the resulting source image, in addition to gender-swap subjects and add latest, extraneous details. But that is a part of the fun of using Midjourney or other generative AI creative tools – see what the model spits out based on your input!
Warm reception among AI imagers on X
The AI image and art community on social network X has applauded the latest editor of Midjourney – something that has been rumored for several weeks. Some of the leading AI developers have already tried it and published their examples, many of which are impressive. Here is a sample:
If you are a Midjourney user and meet the criteria above, log in and try it out! Let me know what you think: [email protected]. Midjourney has also been open about its plans to launch a 3D or video editor, which could arrive later this 12 months.