What's New in Midjourney

A short refresher on the latest Midjourney updates

What this course covers

The course runs across 7 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

New edit model changes images from plain instructions — What's different: Midjourney opened a new image edit model to everyone that changes an image from written instructions, can mix in several reference images, and can redo one area or widen the canvas. Why it matters for your work: You can fix or adjust an image by saying what to change instead of starting over with a new prompt. Try it (about 2 minutes): Open one of your images, choose Edit, type a short change such as "make it night time with street lights on," and submit. No access? Here's what you'd see: An Edit button appears when opening an image, leading to an interface for written instructions and reference images.
Omni Reference replaced by image references — What's different: Image references in the new edit model now replace Omni Reference and Character Reference for putting a person or object from your images into a new image. Why it matters for your work: If you used Omni Reference to keep a character or product consistent, you now attach those images as references instead. Try it (about 2 minutes): In the Imagine bar, open the images panel, attach a photo of your subject, type a prompt that places it in a new scene, and compare the result. No access? Here's what you'd see: Omni Reference and Character Reference are gone; you attach your images as references in the edit model instead.
Targeted edits now change only the area you pick — What's different: Inpainting and outpainting with the edit model now change only the pixels you select, so repeat edits no longer wear down image quality. Why it matters for your work: You can fix small details, like a hand or a sign, several times without the rest of the image getting worse. Try it (about 2 minutes): Open an image in the Editor, select one small area, describe a change, submit, and then make a second edit to a different spot. No access? Here's what you'd see: The Editor displays a selection tool to highlight an area and a text box to describe changes.
Rerun with Thinking to fix missed details (Alpha site) — What's different: The Alpha test site added a "Rerun (Thinking)" option that checks where an image missed your prompt, such as wrong objects, layout or text, and makes it again. Why it matters for your work: It may help when Midjourney keeps getting words, counts or layout wrong, but it is an early test. Try it (about 2 minutes): If you can use alpha.midjourney.com, open an image whose text came out wrong and choose Rerun (Thinking) to compare. No access? Here's what you'd see: Opening an image on the Alpha test site displays a menu with the Rerun (Thinking) option.
Shared folders for team projects (Alpha site) — What's different: On the Alpha test site, folders can now be shared by username or link, with Collaborators who can create in the folder and Viewers who can only look. Why it matters for your work: Your team can gather images for one project in one place, but sharing a folder does not make its images private. Try it (about 2 minutes): If you can use alpha.midjourney.com, open a folder's sharing options, invite a coworker as a Viewer, and check the link setting. No access? Here's what you'd see: The folder sharing options display settings to invite collaborators by username or link as Collaborators or Viewers.
Also new — - Preview your prompt across styles (Alpha site): The Alpha test site added live prompt previews in the Styles sidebar. - Save default settings for every prompt (Alpha site): The Alpha test site allows saving default prompt bar and folder settings. - Seamless tiles for repeating patterns: The tile setting now creates seamless repeating patterns on current models. - Midjourney website now available in Korean: The Midjourney website is now available in Korean. - Ideas page to suggest and vote on features: Midjourney launched an ideas page for members to suggest and vote on features.
Try one on your own work — Pick the one main change from this course that is most useful to your job. Try it in your own Midjourney on a real task, then paste or describe what you got. The coach gives short, specific feedback. No access to the app or plan it needs? Describe how you would use it on a real task this week. That counts too. There is no score and no pass or fail: finishing this completes the course.

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick.

Who it is for

The material is pitched at intermediate level, and takes roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Tool: Image Generation track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive. There is no video to sit through and no slide deck to click past.

Understanding is checked with a lab assessment, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

AI Image Tools: Core — The middle rung between first images and production pipelines: making image generation a dependable part of real work. Learners develop repeatable prompt styles, edit and iterate with intent, and build a small personal library of looks that match their brand. They finish producing consistent, usable images on demand rather than happy accidents.
AI Image Tools: Essentials — A practical, responsible introduction to AI image generation across leading tools. Learners practice prompting for images, compare tools, edit and create variations, and explore styles - while understanding rights and usage. They finish able to produce usable visuals on their own.
Midjourney: Essentials — A hands-on introduction to Midjourney, the most widely used dedicated image tool. Learners master its prompt syntax, parameters, and variation workflow, and understand usage rights for commercial work.
AI Image Tools: Advanced — This course covers the techniques that separate casual image generation from production work: consistency across images, editing pipelines, and brand-safe style systems. Learners produce a coherent multi-image set to production standards.

Frequently asked questions

How long does this course take?

It runs roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code what-s-new-in-midjourney-e874c9b8.