Midjourney Release Notes

Hi everyone, lots more changes on alpha.midjourney.com! Same goal as before: make the site easier and more intuitive without taking away any of the control you have today. Some things will still be broken, but we're shipping often, so tell us if you find bugs.

KOREAN!

Speak/read Korean? This is the update for you. Interested in helping bring Midjourney to more languages? Sign up here.

EDITING

Lots of fixes on the v8.2 editor. The prompt bar now asks "What would you like to change?" when you attach an image. Draft batches show their source images in a grid with a hover preview, and offer Enhance, replacing a previously useless Upscale button.. The “Add to Folder" option now works from the editor even if you have no folders yet.

MOBILE/TABLET

A starter pass here. Pages use the full width, nothing hides behind the bottom bar, and rotating your phone or Safari's toolbar no longer leaves a blank strip. Menus and sheets stay on screen. Uploads get a 3-dot menu so you can finally delete them. Search opens the keyboard right away. More to come, but we still recommend using prod instead of Alpha on mobile.

PROMPT BAR & PILLS

Typing a single backtick no longer freezes the tab. Typing --no a, b now reads the whole list. Long text wraps instead of clipping. What you type in a pill stays even when a preview pops up. The search drawer shows your Frequent and Recent srefs, click one to filter. The "what persists between prompts and sessions" question is still open. Default parameters are the next step.

ORGANIZE

Dragging images to a folder works with the sidebar collapsed. Folder links survive a rename. Adding to a moodboard by link works for external sites. Organize is top-level, and hovering a collapsed icon opens a flyout. Change Style now matches the Styles panel.

POLISH & BUGS

Animate now works (sorry for breaking it). Things should feel snappier. Grids and profiles fill the width. Escape closes just the menu, not the whole image. PageUp/Down and Home/End scroll the feed while the search drawer is open.

UP NEXT

Setting default parameters. Previewing an sref with your prompt. Archive keeps your search when you open an image and go back. Scratchpad reachable from Archive. Drag-and-drop targets that make more sense.

Please keep the feedback coming in #alpha-ideas-and-bugs!

Thank you for being part of our community :heart:

Love,
Midjourney

Thank you for all of your dedicated testing, feedback, and bug reports over the last two weeks! We pushed a huge update to alpha.midjourney.com, stacked on a lot of other changes in the past couple of weeks. Reminder: what we’re trying to do on alpha is to make the magic of Midjourney accessible to more people, by making it feel easier and more intuitive to control the model, without sacrificing any of the control people have now. Some things are going to be broken, but we’re shipping frequently enough that most things shouldn’t remain broken for long (especially if you tell us about it).

EDIT-LIGHTBOX

The biggest change is that the new v8.2 edit model is on alpha, with a new editor built directly into the lightbox. Open any image in the lightbox, edit with plain instructions, attach up to 4 reference images, and see all your session edits in one place. If the last time you looked was when we launched last week, we’ve fixed a bunch of bugs and glitches.

STYLE EXPLORATION

We’re experimenting with a new Change Style feature on the lightbox, which is part of a broader push towards easier ways of exploring style space. I think this is gonna be a hit once we nail it, this is just an early version of it.

DRAG AND DROP

We’re still working through drag and drop UX. We’re starting to feel better about the current version, but we want it to feel a bit more… jazzy.

PROMPT BAR & PILLS

Lots of bugs and papercuts have gotten fixed. I know this is a major point of contention, but we’re going to get it there. We’re still thinking about the correct behavior for what is kept vs removed between prompts and sessions, and how people can set defaults.

POLISH & BUGS

Things should feel a lot faster. A lot of little fixes: overlaps, data issues, weird combination glitches (Niji 7 + inpainting now works correctly, Pinterest extension button no longer shows up on the sidebar – we can’t test all of these, so your feedback is very helpful for finding them). Also better messaging around errors and some errors get fixed by themselves. 🙂

UP NEXT

Setting default parameters. Previewing an sref with your prompt. Giving more real estate to images. Make the closability of the settings more obvious.

Please keep the feedback coming in #alpha-ideas-and-bugs!

Thank you for being part of our community ❤️

Love,

Midjourney

Hey everyone! Today we’re gonna start letting everyone test our first V8.2 image edit model!

This model supports:

1. Editing images with instructions
2. Generating images with other images (replacing omni-reference) with up to 4 image references at once
3. Changing specific areas of your images (inpainting) or expand your canvas (outpainting)
4. Using personalization, moodboards and srefs (moodboards/srefs may work best with some extra prompt direction in this version)

Ways to use the model:

• Drag images into the prompt bar under "attach to prompt”
• Click ‘edit’ in the lower right in the lightbox
• Click the ‘edit’ tab on the left and upload an image
• Type --edit url... on Discord

We’ve updated UIs on both the main midjourney.com website and alpha.midjourney.com, alpha will be changing rapidly with lots of experiments on how to remake the interfaces for this model.

There’s gonna be a lot of edge cases here so we’ll need your help finding situations that don’t work as expected. If an image doesn’t work well try clicking the sad face emoji on the right side of the lightbox or give us the jobid/url for the image while it's opened in the lightbox.

We’d also love your thoughts on how we can improve our user interfaces for this model from here. Drop your thoughts or model edge-cases in #ideas-and-features.

If you want to share what you’re doing with the new model, feel free to chat or share in #edit-showcase.

There will be a lot of fast-follow updates from here, but we’re ready to start testing as a larger community and hope you have fun!

❤️

Two weeks ago, we launched a very rough draft of some big changes to alpha.midjourney.com. Since then, thousands of you have been testing and hundreds have given us thoughtful feedback, both positive and negative (Thank you! Yes, even the brutal stuff.). That's the deal with alpha: you see it early, we get to pressure test it together. We've spent the past two weeks shipping UX improvements and bug fixes, and we'll keep updating the changelog as the site gets better or you can visit #alpha-news for the latest updates.

Folders and organizing

• You can now organize your projects into groups in the sidebar: a collapsible tree where you can rename a group with a double-click and file new folders straight into it
• The sidebar got a big cleanup: one folders tree with your recent folders up top and a “Show all” toggle, a New Project button, Styles grouped into a dropdown, and the nav stays open on large screens
• Fixed folder grouping and Scratchpad behavior, and folder controls stay hidden until you have folders
• Saved Searches are back in the search drawer on Organize
• Fixed a crash when creating a project or workspace

Upscale, Zoom, and Vary

• Upscale, Zoom, and Vary are back, and Vary now respects your settings instead of quietly running in HD
• Older V8.2 images got their Upscale buttons back too
• Fixed HD selection on V8.2, and removing the HD bubble no longer silently changes your speed

Settings

• Settings now stick: values no longer reset on their own, and Relax no longer flips back to Fast
• Personalization no longer applies while the toggle says off

Performance

• Fixed the lag across the site: prompt input typing, settings sliders, and the slowdown after scrolling deep into your gallery

Editor

• Editor menus no longer cover the Submit button
• Retexture prompts are no longer wrongly rejected
• The inline editor no longer shows the wrong sidebar

Prompt bar and pills

• Removing the version pill now switches the model
• "Use Subject" no longer errors out
• Submitting a prompt now keeps your pills and image references in the bar for the next run, only the text clears
• Fixed prompt paste corruption, double submits, and custom option lists and permutations
• Fixed sref pill parsing, including repeated random srefs collapsing into one
• Right-click on prompt pills now gives a real context menu, and pills have hover cards explaining each flag
• Pills got a visual refresh to match the feed, cmd/ctrl-click navigation on them works again, and a bare personalization pill now reads "Personalization On"
• Stylize settings now explain themselves in context, and House style works without Raw
• Shift+Enter makes a newline again, and the down arrow returns to your written prompt
• Dragging an image now opens the Images sidebar with drop targets for each reference role, floating over the page instead of pushing it
• Video mode: dropping images on the Start and End Frame pills now works correctly

Gallery and lightbox

• Redesigned the gallery filters as toggle chips
• Sidebar tabs stay visible in the lightbox, and sidebar scrolling no longer flips to the next image
• The right sidebar is slimmer based on screen size, with consistent steppers across settings
• Downloads save with proper filenames and extensions again
• When an image is blocked by the output filter, the error message accurately reflects what happened

Explore

• Rating on Explore now works past the first grid
• Fixed a crash on Explore
• Top Week and Top Month now show V8.2 images
• Search shows V8.2 images

Moodboards and profiles

• You can copy a moodboard pill to copy its code
• "Use Moodboard in Prompt" is one-shot again instead of setting your default
• Fixed the moodboard card buttons: copy and select do what they say, and removed the confusing "Set as Default"
• Profile copy button copies the code again

Fair warning: fixing this many things this fast means we almost certainly introduced some new bugs along the way. When you find them, tell us. Please keep the alpha feedback coming in #alpha-ideas-and-bugs. And thank you for being a part of our community ❤️

Hi everyone!

We are launching our V8.2 image model today. This update focuses on aesthetics and image quality and personalization.

• Images should be more creative, bold, sophisticated, edgy and fresh
• Random situations where you'd get a low quality image should be dramatically reduced
• Personalization will "understand" your personal taste much better. Especially if you have a ton of ratings under your profiles
• Creating personalization profiles for V8.2 now has a much larger and improved pool of images to choose from

Thanks for your help rating images to make this possible!

We hope you all have fun and we strongly encourage you to try both new and old personalization profiles with the latest release.

Hi everyone - a few updates today!

Draft mode for V8.1

• Each draft mode generation creates 24 images at a lower resolution and quality.
• Click "Vary" on images you'd like to render at full-quality and full-resolution
• Draft jobs use half as many fast hours as V8.1 SD jobs (even though they generate 24 images!)
• Turn on draft mode by clicking the ⚡ button in the menubar

Use --preview to test new features

• We're trying something new today to let you test early versions of new models. Use --preview in your prompt to test the latest. Images that you create with --preview might be a little unpolished and the jobs are not guaranteed to run consistently over time.
• In this first test, you'll notice differences across all images, especially those with personalization and moodboards.

We'd love to hear what you think in #ideas-and-features

Hi everyone,

After your testing and feedback, we've updated the default model from V7 to V8.1!

A reminder of what's new in V8.1:

• The model is smarter, more coherent, better adheres to detailed prompts, and renders text better than ever
• With HD mode enabled, V8.1 renders at twice the size and 4x the resolution of V7 images
• V8.1 is incredibly fast. Your images appear in only 4 seconds in SD, and 12 seconds in HD
• Style references, personalization, and aesthetics remain consistent between V7 and V8.1

Note:

• V7 omni-reference is available to use while we finish training the improved version for V8
• Now that V8.1 is the default, we will be deprecating our V8.0 alpha model in two weeks

Conversational mode has been improved across text and voice input

• When a voice session starts, it has access to your Image Prompts, Style References, sidebar settings, and recent jobs.
• Image Prompts now work from the tray and sidebar.
• Tray images persist across voice submissions until you remove them.
• You can add references without exiting voice.

A new Rerun as HD button makes it easy to rerun any V8.1 image generated in Standard Definition (SD) as High Definition (HD).

Folder views on the Create and Organize pages now show a hidden-item count so you can see how much is filtered out. The filter reset button has moved from the bottom to the top of the filter bar.

On mobile web, the settings menu now groups Profiles, Moodboards, and Liked Styles together. The More Options panel is available in the mobile lightbox.

Improvements and bug fixes

• Search on the Create and Organize pages now works for signed-in members without an active subscription.
• Upload error message now shows the correct 20 MB limit.
• Failed jobs no longer show Vary or Upscale buttons that can't run.
• Rate-limit message now appears when an upload is throttled.
• Prompt scrolling on the Create page no longer traps the scroll wheel.
• Subscribe button no longer gets stuck after navigating back.
• Activating a Niji 6 or V6 Personalization profile no longer immediately deselects it.
• Copy confirmation now waits for the clipboard write to finish.
• Corrections for inaccuracies in the Account Settings subscription status panel.

Hi everyone, we have a few V8.1 related updates today:

1. V8.1 is now available on Discord as well as midjourney.com
2. We've improved sharpness and image quality for V8.1! This is most noticeable for SREFs and Moodboards but you should notice across all images (especially HD)
3. To save compute during a server transition, we're making SD default for a bit. You can still switch to HD under settings panel or add --hd after your prompt.
4. The rating data you've giving us is continuing to help us improve quality for V8.2. If you want to keep helping us do ranking we've updated the images here: midjourney.com/rank-v8-1

Thank you and have fun! ❤️

Examples of the image quality improvements in crops taken from HD images

Thanks for testing our V8.0 model over the last month! Today we're releasing our next version of V8 - V8.1

What’s new in V8.1?

• V8.1 has a consistent and familiar aesthetic in the spirit of V7. Moodboards and srefs are now super stable and will be everything you love.
• HD mode is now 3x faster and 3x cheaper. It’s so cheap we’re making it default for V8.1
• Standard resolution is now 50% faster and 25% cheaper. Standard resolution in V8.1 at full quality is as fast as V7 draft mode! It’s great for exploring and iterating fast. We’ve also added a button called “Run as HD” which will rerun any SD job as HD.

We’ve also brought back some community favorite features

• Image prompts and even image weights are now available in V8.1
• New Prompt Shortener, which will kick in anytime you go over the prompt length limits
• Updated Describe that gives longer more detailed prompts and matches the prompting style of V8

Please Note:

Our V8 series of models are still only available on alpha.midjourney.com and are in an early testing phase. Things will change! Perhaps without notice! But good stuff is on the way.

It is likely that we will decommission our V8.0 model after V8.1 has been out for a few weeks. If you find something the old model did better than the new one please let us know in #ideas-and-features

What’s next?

We’re going to try to give a quick shot for some V8 upscalers and then we’re moving onto our V8 edit, inpainting, and outpainting model upgrades.

Have fun everyone! And thank you for being a part of our community ❤️

Hey everyone! We have some quick V8 Alpha related updates to make today

Relax mode is now available!

• V8 Relax is now up for all Standard/Pro/Mega subscribers
• Supports all commands (except using --hd and --q 4 at the same time)
• There is a chance we run out of servers. If we do, we may change availability or speed of relax mode (until we get more servers online hopefully mid-late next week)

Two Versions of SREF / Moodboards now available

• We have a new version of SREF/Moodboards that is less accurate but is 4x faster/cheaper and also supports --hd and works better with --p and --stylize and --exp
• This version is now 'default'
• You can use the old version by putting --sv 6 (style version 6) after your prompt
• Our guides/mods are split between which is 'better' but certainly in my (David's) opinion, this new version is more 'fun' - so please enjoy!

Update on V8 Development

• We REALLY appreciate everyone's feedback so far!
• We are now working on a big training run for a new version of V8 (it might even be called V8.1)
• This new version will (probably) take 1-3 weeks to be ready
• When the next V8 comes out, we will likely remove the 'present' version of V8. So remember everything you're using now is Alpha and temporary.
• The next version we're working on is aiming to have improved default aesthetics, creativity, coherence, image prompts, better moodboards/srefs and possibly 2K default resolution
• Obviously we can't guarantee this but it's a big cool goal and worth our time to give it a shot!

Reminder:

If you want to use MJ V8 go to alpha.midjourney.com and if you want to help us with ratings or feedback, check out Discord

Wish us luck and we hope you continue to have fun playing with the first early version of V8! <3

Release Notes: V8 Alpha

Hi everyone! Today we’re letting the community test an early version of our V8 model on alpha.midjourney.com. We want your feedback and your help. Let’s explore what this new model can do.

V8 is an incredible model. It’s much better at following detailed directions and will still surprise you when you ask. Its ability to understand your aesthetics through personalization, style references (srefs) and moodboards is amazing. Images are more coherent and detailed. Text rendering works better than ever (when specified in “quotes”). And image generation is ~5x faster than before.

We’ve upgraded our web interfaces to support this speed. And more is coming. We have an improved conversation mode so you can just ‘talk’ in flow, a “Grid Mode” so you can focus on a single big set of images, and we’ve moved our settings into ‘sidebars’ so you can tweak settings without blocking your view.

V8 launches with support for multiple aspect ratios, --chaos, --weird, --exp, --raw. We support backwards compatibility with your V7 personalization profiles, moodboards, and srefs.

V8 brings a new --hd mode which natively renders images at 2K resolution and a --q 4 mode if you need a little bit of extra coherence.

Modes and Pricing

Presently, Relax is not yet supported. We are working on a new server cluster for Relax plus cheaper render modes. --hd, --q 4, sref, and Moodboard jobs are 4x as slow as regular jobs and each costs 4x (for now).

The best way to help us improve V8 is to rate images in the lightbox. Click an image in create then click “I like this image” or “I don't like this image” on as many of your V8 images as possible. You can use 1/2/3 hotkeys and arrow keys to rate images quickly.

Other Tips and Tricks

If you’re going for photos or a more ‘plain’ or ‘in control’ look we’d recommend switching to --raw right away or using moodboards or srefs to control your style. We’re still working on the ‘default’ aesthetics of V8, but we strongly encourage you to use your personalization and even crank it to –stylize 1000 asap. V8 is going to shine most right now when you rely heavily on our stylization systems and when you trend towards longer more specific prompting.

Please Note

This is an entirely new model with unique strengths and weaknesses, we want to learn from you what it's good and bad at but keep in mind it may require totally new prompting styles. So play around a bit!

It’s time to play! Show off what you’re making and let us know what you think on Discord. As the model becomes more mature, we’ll do a community-wide roadmap ranking session to help us figure out what to prioritize next.

Thanks again for everyone’s help with the V8 pre-release rating parties, and thank you so much for being a part of Midjourney! Let’s have fun out there and find new wonders on this vast and shared sea of imagination.

Hi everyone, we've got a couple of small announcements today:

1) We've got a new personalization interface on web

• This lets you make personalization profiles by clicking and scrolling through a list of images.
• This should be both faster, more accurate, and more fun
• This lets you also avoid you feeling anxious about 1v1 image comparisons (as before)
• We highly recommend everyone try personalizing Midjourney if you haven't already in the past!
• Go to midjourney.com/personalize to create a new personalization profile or continue building a personalization you started previously

2) We've added Personalization and Moodboards to niji 7 (our anime image model)

3) We're sunsetting rooms on web as we work on our next-generation social features.

• This should noticeably increase the general speed and performance across the entire web experience.
• We recommend people move to Discord for community events and live-chat.