Haniwa refers to a distinctive type of terracotta clay sculpture that was created in ancient Japan during the Kofun period (3rd to 6th centuries). These sculptures served as burial objects and were placed in and around burial mounds (kofun) to accompany the deceased into the afterlife. Haniwa figures were crafted in various forms, including humanoid figures, animals, houses, and more, and they offer valuable insights into the religious and funerary practices of ancient Japan. Midjourney plays with this style rather well, creating different shapes of terracotta figurines to respond to the prompts. The Midlibrary score is 8/9. We will not reduce the score for Francis D. this time. Let’s believe he is an archeologist who discovered the Haniwa figures! But we take half-points off for the cyberpunk character and the peonies. They are altered by this style, but not exactly right.
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 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!
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 community@midlibrary.io.
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 →
Midlibrary Benchmark is a test comprised of nine standardized prompts designed to test how Midjounrey styles (AKA artistic styles, reference styles, or style modifiers) work with different subjects in a variety of contexts.
Depending on how a style manifested itself with each prompt, we add 1, 0.5, or 0 points to its total score.
The prompt produced a generic results with no unique style features: this test adds nothing (0) to the overall score.
This generation inherits more elements from the referenced style, but they are scarce and dilluted. Which adds 0.5 to the style's score.
In this case, the Midjourney style showed a distinct and unique result, well aligned with the style's real-world prototype. A firm 1.