DISCLAIMER
Technically, Remaster makes variations of your prompt while adding --test --creative to it. And although I personally do not use --test mode a lot for initial generations. But it's combination with --v 3—or Remaster—surprises me every time!
.jpg)
.jpg)
MIDJOURNEY AI REMASTER MODE
I want to start this section with a little quote: "This is kind of a crazy and experimental feature."
Remaster is what they say it is—a crazy and experimental feature that (I quote again) "can increase the quality and coherence of the image… or could also make it worse!" Oftentimes, Remaster works like sorcery, taking your images to the next level—especially given enough rerolls. Sometimes it will do the opposite, stripping the outcome of its magic and rendering a bizarre, messed up, or downright dull result.
Remaster is what they say it is—a crazy and experimental feature that (I quote again) "can increase the quality and coherence of the image… or could also make it worse!" Oftentimes, Remaster works like sorcery, taking your images to the next level—especially given enough rerolls. Sometimes it will do the opposite, stripping the outcome of its magic and rendering a bizarre, messed up, or downright dull result.
.jpg)
.jpg)
.jpg)
.jpg)
The bottom line here: there is no manual on Remaster mode. It’s a just-press-the-button-and-see-what-happens kind of feature. However, I will share a few observations that might help you better feel Remaster’s behavior.
.jpg)
.jpg)
.jpg)
.jpg)
From my experience, Remaster works somehow similarly to Image Prompts: instead of building upon the text of your prompt, it works with the visual part, reinterpreting the image itself.
To establish it beyond my instincts, I ran a simple test. First, I asked Midjourney to render a nonsensical prompt: jdshgiusdh sh ss9hs in both --v3 and --test --creative modes.
The results were VERY different, so I knew that my abracadabra was not common knowledge shared between modes. I also saw how --test --creative interprets the words themselves.
The results were VERY different, so I knew that my abracadabra was not common knowledge shared between modes. I also saw how --test --creative interprets the words themselves.
I then upscaled variation #2 from the --v3 result and Remastered it.
Et voila! Remaster ignored the words but rendered the image based on the visual component of the --v3 result.
Now that we have a hypothesis about how Remaster works, let's deduce a few factors that affect Remastering:
1. SIMPLICITY
Remastering primitive images tends to render the closest result to the original. A more abstract and less obvious subject will sometimes lead to unexpected results.
.jpg)
.jpg)
2. RECOGNIZABILITY
The same as #1 goes for easily recognizable subjects.
3. SIZE
The larger your subject is, the more space it takes in the image—the more chances it will be "seen" and make it into the Remastered variant. The smaller the details, the harder it is for Midjourney to spot and reinterpret them. Expect some weird Remasters!
4. REROLLS
Remastering the same --v3 result several times will give you different results each time. Rerolls behave the same way, but each reroll builds upon the image that you are rerolling at the moment instead of the original generation. In both methods, every iteration may change the outcome dramatically.
5. GLITCHES
Finally, Remasters often correct glitches in the original generations. And rerolls may fix those that appear during a previous Remaster iteration.
.jpg)
.jpg)
Instead of conclusion
Remaster is a mystery, difficult to understand and wield. But it is also a powerful tool that requires many trials and errors to learn to feel and use. And if you do, your prompts will undoubtedly lead to some fantastic results.
Happy midjourneys!
— Andrei Kovalev
You can help us maintain and expand Midlibrary and produce more regular educational content of higher quality. And keep it free for all!
Support Midlibrary on Patreon! →
.jpeg)
All samples are produced by Midlibrary team using Midjourney AI (if not stated otherwise). Naturally, they are not representative of real artists' works/real-world prototypes.
Ver. 2.9.1
♡
We do our best to keep this website running as smoothly as possible. However, stuff happens, and we thank you for letting us know!
We're here to help! If you're unable to resolve the issue, please, contact us.
We regularly publish new Midjourney Guides, compile new Style Tops, update the website, and have fun! Want to be the first to get Midlibrary news? Subscribe to our newsletter and never miss a thing!
If you're unable to resolve the issue, please, contact us.
Personal Libraries are available to our Patreon Community
Learn more about the benefits of supporting us by becoming Midlibrary Patron—and start your Personal Library ↗︎
You have just become a Patron, and cannot log in?
Please, allow our team some time (usually not more than 24 hours) to set up your Personal Library.
You may be using different emails for your Patreon and Discord accounts. If that is the case, please, send your Discord email to [email protected].
If the issue perists, or you didn't get a response to your email, please, inform us via Bug Report form
We are currently updating the Personal Libraires' infrastructure
In the nearest future, it will allow you to access your Collections much quicker, add covers to them, tag the styles you save to quickly find them, and—most importantly—save your --sref (numerical) styles!
However, at the moment, logging in to your Library is unavailable. We apologize for the inconvenience. If you are a Midlibrary Patron, please, check this Patreon post ↗︎ for Personal Libraries status updates.
To start creating Collections and save favorite styles:
Log in with Discord →
Learn more about Personal Style Libraries, saving favorite styles, and organizing them into Collections.
Learn more about supporting Midlibrary and the benefits of joining our Patreon community →