Today, we return to the topic that's been on every AI artist’s mind and screen since the beginning of the text-to-image neuro-revolution—turning an AI generated digital art piece into a physical high resolution print.

In my artistic career as a photographer, upscaling was a rare necessity: thanks to modern digital sensors, printing was straightforward, almost out-of-the-box. But for our Midjourney masterpieces—for postcards, posters, books, or large-format high-quality fine-art prints—isn't just an option, it's almost a requirement!

The latest model of Midjourney—V6—has two built-in upscalers: Subtle and Creative, which we covered in-depth in a dedicated guide↗︎.

However, they both have their limitations, and here are the main ones:

  • no fine-tuning/extra options for subject-specific upscaling;
  • long processing time per picture (and a considerable amount of fast hours consumed by each upscale in Fast mode),
  • no batch image processing,
  • only work with Midjourney generations,
  • and, of course, maximum upscaling factor of just 2x.

So in this guide, we will be reviewing popular AI upscalers that eliminate all (or most) of these limitations. Of course, there are too many such tools to cover in one go, so let’s start with spotlighting five standout solutions; including online services and downloadable apps—each tested on four different samples of Midjourney generations.

How we tested

First, let’s meet our test subjects—all artworks created with Midjourney AI V6, and initially upscaled with Midjourney’s Subtle or Creative upscalers to maximize the original’s quality and size.

Where possible, we used the standard or the most general upscaling options and the model’s default or recommended settings.

All test are done on MacBook Air 13.6" Apple M2 (8C CPU/GPU), 8 Gb.

1. Gigapixel AI

Platforms
Mac OS, Windows
Form
Stand-alone app + Adobe Lightroom, Photoshop plugins
Models
8
Max upscale
6x (recommended)
10x (without guaranteed result)
Performance
1215 seconds per image
Price
$99.99 for Buy Once, Own Forever license + 1 year of AI models updates

The reigning champion from our last study, and Midlibrary's top pick, is none other than Gigapixel AI. This powerhouse of an upscaler operates on a one-time purchase license and keeps itself fresh with regular model updates.

Gigapixel AI has a sleek, minimalist interface, where every control is intuitively placed, making learning quick and easy, and the user experience smooth.

Gigapixel’s Auto mode intelligently selects the best model and settings for your images, but manual control is just a click away, including options like Face Recovery, De-noise and De-blur, Fix Compression, and Gamma Correction to fix color/gamma issues.

Gigapixel AI features eight different upscaling models for a range of general and specific applications: from magnifying extremely low-resolution, compressed images to upscaling line-art, text, AI-generated art, and even ultra HD photographs, multiplying the size of already large pictures.

Pick sample to compare:

Notably, Standard and High Fidelity modes proved to be very versatile and in 9 out of 10 cases enough for most AI-generated pictures: from landscapes to line-art.

Pros
Cons
Exceptional AI image upscaling quality up to 600% (even more in ”experimental“ mode).
Hefty price-tag (however, unlike with many other contestants on our list, it is a one-time payment instead of subscription fee).
8 various subject-specific models: from Low Resolution and Very Compressed to Lines, Art/CG, and High Fidelity upscaling.
Extra features, like Face Recovery, Fix Compression, De-noise, De-blur, etc.
Export to professional image formats: TIFF, DNG.
Lightning-fast upscaling.

Conclusion

Super-large upscales across all models, highest quality, lighting fast.
Learn more at Gigapixel AI official website↗︎

2. ON1 Resize AI

Platforms
Mac OS, Windows
Form
Stand-alone app + Adobe Elements, Lightroom, Photoshop plugins + Capture One plugin
Models
4 (2)
Max upscale
6x (recommended)
28x+ (without guaranteed result)
Performance
1518 seconds per image
Price
€66.76 for Buy Once, Own Forever license or €5.72 per month as a part of ON1 Everything subscription

ON1 Resize AI is a powerful tool designed for image upscaling and enchancement, with strong focus on final media.

ON1 Resize AI’s interface is elegant and—with a very small learning curve—intuitive and straightforward. Although at the beginning, the number of options might occasionally stun an inexperienced user.

There are four models to choose from for your upscale: Resize AI 2023 (Smooth), Resize AI 2023 (Faithful), Genuine Fractals, and Bicubic, each with a specific set of controls (or absence of any in the case of Bicubic).

I’ll quote the developers here:

  • Resize AI 2023 (Standard) is the default (and preferred) option when resizing images. Ideal combination of noise reduction, and micro-contrast. The best results for most photos.
  • Resize AI 2023 (Faithful) provides slightly less noise reduction and microcontrast than Standard, although the differences will be subtle.
  • Genuine Fractals is the classic, patented, fractal-based algorithm used in Perfect Resize (included solely for backward compatibility with previous versions of ON1 Resize).
  • Bicubic. This option is for downsizing images. It has no settings.

There are plenty of options for you to choose from when it comes to the desired output size: from longest side size to magnification in percents. The recommended multiplier is 600%, however you can set this counter much, much higher. It reacts to the size of the initial image, and for our samples allowed to go as high as to 2853%, with an output picture of a gargantuan 83049x36544 size. I didn’t want to risk saving such an enormous file as PNG, but even with a 100% quality JPEG was estimated to be 28.8 Gb.

Pick sample to compare:

One of ON1’s standout features is its set of Printing tools:

  • A ton of presets for a number of paper brands, types and sizes. With those, you can choose your final printing media and let the app take care of all the settings optimal for your choice.
  • Gallery Wrap feature creates extended margins for wrapping an image around wooden stretcher bars for canvas prints.
  • Tiling Feature divides an image into tiles or strips to make it easier to print a mural.

As a cherry on top, ON1 Resize AI features batch processing, advanced export dialog, and highly customizable Export Presets allowing to have multiple version of upscales with different settings in the same export. And it only comes natural that you can export to JPG and PNG, and more professional image fomats: like TIFF, DNG, and even Adobe Photoshop PSD/PSB.

Pros
Cons
Extra tools—like Tiling and Gallery wrap — and presets for printing.
The interface is elegant and intuitive, can be somewhat overwhelming for first-time users. Requires some learning/experimenting.
Machine-learning Face Recovery model that detects small faces and enhances them with realistic detail (for instance, when upscaling group portraits).
Additional options for Noise reduction, Sharpening, and even Adding film grain.
Export to professional image fomats: like TIFF and DNG, etc.
Great export capabilities.

Conclusion

Extremely large upscales, very high quality, lighting fast + additional tools specifically for printing. Learn more at ON1 official website↗︎

3. LetsEnhance.io

Platforms
Web
Form
Web app
Models
5
Max upscale
From 2x to 16x
Depending on the model
Performance
2030 seconds per image
Subscription price
From $9/month, which amounts to 100 monthly credits (each credit is one processed image).
You can also use Pay as you go format, but in that case, the same $9 will get you only 20 credits.

LetsEnhance.io is the most versatile online-only app on our list, suited for reviving old photos, improving low-resolution pictures for marketing or product photography, or enlarging AI-generated images for printing. Its features include fixing blurry or pixelated images, noise removal, and color correction, making images vibrant and lifelike.

LetsEnhance features a number of models designed for different applications: like Photo (with Enhance Face Details option), Digital art (for illustrations, paintings, anime, etc.), Smart Enhance (for low resolution images for the web), Smart resize (recommended for images with text).

Pick sample to compare:

The fifth model is now in beta stage and is called Creative — a trendy (see Magnific.AI, Leonardo AI, and Midjourney’s Upscale (Creative)) mode that not only upscales an image, but also adds new details to the enlarged picture.

LetsEnhance.io also offers three presets to quickly activate a specific set of parameters: Printing (that optimizes images for printing in highest quality), E-commerce, and Real Estate.

Looking at presets, one can assume that Letsenhance specifically targets ecommerce applications, rather than fine-art printing projects.

Pros
Cons
Easy-to-use web interface with decent number of fine-tuning options.
No universal (Standard) mode.
Additional features like Remove background, Light AI (helps enhance your scene’s lighting), Tone enhance, and Color enhance.
Different models have different upscaling capabilities. For instance, only Photo allows up to 16x upscaling, whereas Smart Enhance only goes up to 2x, and Digital art model has only 4x option.

Conclusion

High quality, easy to use, and fairly advanced online upscaler. Learn more at  LetsEnhance.io official website↗︎

4. Nero AI

Platforms
Web, Microsoft Windows (for desktop app), iOS, Android (for Nero Lens mobile upscaler).
Form
Online, Stand-alone app, Mobile app
Models
5
Max upscale
4x
Performance
1+ minute per image
Subscription price
From $9.95/month, which amounts to 100 monthly credits (an upscale cost ranges from 1 to 10 credits, depending on the model).

Nero AI is a web-based upscaler (and other tools, like Image Compressor, Photo Restoration, Photo Colorizer, and Image Denoiser). In the scope of this guide, we will be looking only at Nero AI Image Upscaler.

Nero AI Image Upscaler features a range of upscaler models designed for various subjects/image types (I will quote the deveolper here):

  • Standard: For landscapes, cityscapes, and everyday snapshots.
  • Cartoon: For anime, illustrations, paintings, and artistic works.
  • Photo: For improving small, low-quality images across various types.
  • Face Enhancement: For low-resolution or blurry faces.
  • Business: For clarity of pixelated text, real estate images, digital art, and product photos.

Despite its easy-to-use interface, the overall experience might seem uncomfortable due to all the unrelated elements on screen: from seasonal promotions to marketing stats and newsletter promo—making the interface cluttered and distracting.

Pick sample to compare:
Pros
Cons
Easy to use web-version.
Web-interface is cluttered with promotions/marketing materials.
Additional set of tools, like Image Compressor, Photo Restoration, Photo Colorizer, and Image Denoiser, that work with the same credits as the upscaler.
Lack of fine-tuning settings (you can only pick an upscaling model).
Slow compared to other upscalers: more than a minute when using Standard model, and almost five minutes with Business model.
Business model costs 10 credits per image, allowing for only 10 upscales per month with the lowest subscription price.

Conclusion

Fair quality, medium speed, easy to use online upscaler. Learn more at Nero AI official website ↗︎

Finally, let’s talk about an incredibly powerful—and FREE—method of upscaling your art: with the help of a vast number of AI models trained with deep learning methods to reconstruct high-quality images from less detailed originals. There are literally hundreds of openly available models, trained on thousands of various subjects. There are more specific (e.g., trained on video game screenshots, or designed to restore old photographs), and more general ones (for instance, general upscalers, or image sharpeners).

With so many of those models, the question is: how do I apply them to my images. This is where it might get tricky. There are simply too many practical options varying in level of complexity, comfort, and control.

+ Here are just a few of them

Some can be experimented with in Google Colab notebooks↗︎, allowing you to run AI models in the cloud without local setup. But such options require a certain technical savvyness, or some level of patience to learn how they work, if you are a total beginner. Some are available on a model’s website, like Real-ESRGAN XL↗︎. However, prepare for a possible wait—a downside that many free tools have. With Real-ESRGAN XL playground, I stopped counting after 10 minutes of waiting. :)

A way for the technically-advanced readers of this guide is seting up a Python environment on your computer and install libraries like those offered by TensorFlow↗︎ or PyTorch↗︎ to run models locally.

And there are also websites like Hugging Face↗︎ that provide accessible interfaces to various pre-trained models. This is one of the easiest way to use different super-resolution models to enhance your images without deep technical know-how (although this might be much slower or have less options/less control over what you can achieve otherwise). Still, there are some quite powerful options, like Faizan141's Image Upscaler↗︎.

But in this guide, I will share a method that I found the most efficient for myself and that, I believe, strikes a “golden middle” between convenience and the effort/knowledge required.

5. chaiNNerReal-ESRGAN

Platforms
MacOS, WindowsLinux
Form
Stand-alone appdownloadable model(s)
Models
Any available model
Max upscale
Depends on the model
Performance
4050 seconds per image
Price
Free

For this test I picked the famous Real-ESRGAN as my test model. And here is the second part of that combination: chaiNNer.

chaiNNer is a node-based image processing GUI. It’s an app designed for easy customization and ”chaining“ of image processing tasks. Originally developed for AI upscaling, it has now evolved into a versatile and powerful tool for programmatic image processing.

With it, you can design and run complex tasks—handle intricate image processing workflows—through simple (and visual!) node connections. For instance, you can design a workflow to upload a batch of images, rename them in a specific way, upscale them with a select model and pre-set parametres, apply color correction, crop them, and sharpen the result with another AI model. And then save them with various presets to different folders. There are dozens of tools available in chaiNNer as nodes.

But for my setup, I just need four—with self-explanatory names: Load Image, Load Model, Upscale Image, Save Image.

Each node has a set of simple setting, and color-coded output and input ”dots.“ By dragging the “dots” you can connect output of one node to the input of another. Load Image’s yellow output connects into Upscale Image’s input.

The number of such steps/nodes/connection is unlimited. In our case, the model is connected, i.e. applied to the same Upscale Image node that provides the final result via connection to Save Image’s input. Just press the Play icon on top of the screen, et voila!

Pick sample to compare:
Pros
Cons
chaiNNer's incredible versatility.
Requires some tech-savviness (even though I personally would give it 2.5/10 on the difficulty scale, where one is using a web-browser, and ten is quantum computing integration into an existing cybersecurity framework).
Hundreds of available models, and not necessarily super-resolution ones.
It might require some time to find a model or a set of models, and a combination of nodes to achieve the quality of some commerically available product.
It's free!

Conclusion

Incredibly versatile tool with infinite number of possible chains for any need imaginable—going way beyond just upscaling. Learn more at chaiNNer official website↗︎

Hint

There is a simply wonderful free catalog of available models—OpenModelDB↗︎. It contains searchable information about hundreds of downloadable models with details, and Before-After samples—similar to what we have in this guide—that you can filter by the subjects they were trained on.

To Be Continued

We will continue reviewing different upscalers, both stand-alone apps and online apps. Our next guide will be devoted to “creative upscalers”: Leonardo AI, Magnific AI, and Clarity AI. Stay tuned!

Happy midjourneys,
—Andrei

/discuss

If you're considering acquiring any upscaler from this guide, please, consider doing so using the links in the article. By doing so, not only will you be purchasing an excellent upscaler, but also supporting Midlibrary in the process!

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! →

Style Roulette
Jean-Michel Frank style in Midjourney AI | Midlibrary
Jean-Michel Frank
false
Midlibrary Powerstyle
false
Midlibrary Benchmark
Designers
Designers
Ed Paschke style in Midjourney AI | Midlibrary
Ed Paschke
false
Midlibrary Powerstyle
true
Midlibrary Benchmark
Painters
Painters
Marc Riboud style in Midjourney AI | Midlibrary
Marc Riboud
false
Midlibrary Powerstyle
false
Midlibrary Benchmark
Photographers
Photographers
Victor Nizovtsev style in Midjourney AI | Midlibrary
Victor Nizovtsev
true
Midlibrary Powerstyle
false
Midlibrary Benchmark
Painters
Painters

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.

We'll be grateful for shares and backlinks!

Ver. 2.5.9

Andrei Kovalev's Midlibrary
Midlibrary by
Midlibrary.
Hal Foster
Andrei Kovalev's Midlibrary
Suggest a style

Midlibrary Catalog grows largely through the contributions of our Community.
Thank you for taking time to share your suggestion!

THANK YOU!

Your submission has been received. 

We will now test it and add it to Midlibrary Catalog if Midjourney recognizes the suggested style(s).
In case you left your email, we will notify you when it happens!


Something went wrong while submitting the form. Please, check that you filled all fields.
We're here to help! If you're unable to resolve the issue, please, contact us.
Report a bug

We do our best to keep this website running as smoothly as possible.
However, stuff happens. Thank you for letting us know about it!

THANK YOU!

Midlibrary Groundskeeper has been notified about the issue
and—if you left your email—will come back to you ASAP.


Onward to Midlibrary →
Something went wrong while submitting the form. Please, check if you filled all fields.
We're here to help! If you're unable to resolve the issue, please, contact us.
Subscribe to Midlibrary Newsletter

Every week we publish a new Midjourney study and a new Editor's Pick.
Receive our newsletter to never miss an important Midlibrary update!

After you subscribe, you will receive one email weekly. We never share your email with anyone outside our team and infrastructure. Don't worry, after signing up, you can unsubscribe from our newsletter anytime.

Thank you for subscribing!

IMPORTANT

  • Please, make sure to add [email protected] in your mailer White List.
  • If you don't receive a newsletter by Sunday morning: please, check your Spam folder.
Onward to Midlibrary →
Something went wrong while submitting the form. Please, check that you filled all the fields.
We're here to help! If you're unable to resolve the issue, please, contact us.
Rename Collection
Create new Collection
Personal Libraries
are available to our
Patreon Community
Andrei Kovalev's Midlibrary Patreon Community

Check out the benefits of becoming a Midlibrary Patron ↗︎

You have just became a Patron, and cannot log in?
1. Please, allow our Technical Department up to 24 hours to set up your Personal Library.
2. 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].
3. If you are still having issue, please, inform us via Bug Report form.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.