About the master asia tag
master asia is a character tag that NovelAI Diffusion can use. On Danbooru it has 206 posts, and its best-rated still image scores 95. The samples above put the tag at the front of a fixed base prompt with seed 1234, so the differences between tags come from the tag alone.
How each model draws master asia
Follows composition and expression instructions closely, so the effect shows in a tidy form.
Reacts to the tag more strongly, so its effect is easier to see.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing master asia in a prompt
Put the subject first, then this tag, then quality tags.
master asia, solo, best quality, masterpiecewlop, master asia, soloThe negative prompt and the full settings are on the terms page.
How these samples were made
Every image uses 832×1216, seed 1234, 23 steps and the k_euler_ancestral sampler. The base prompt and negative prompt stay the same for every tag, and only the tag under test changes. Images flagged by the NSFW check are regenerated with a new seed or hidden.
From the Danbooru wiki
Also known as the Undefeated of the East, he is Domon Kasshu's teacher in the martial arts. His real name is Shuuji Kurosu (which is not mentioned in-series).
First appeared in Episode 15 of Mobile Fighter G Gundam.
The most manly character in the Gundam multiverse, he pilots the Master Gundam and formerly piloted the Kowloon Gundam and Yamato Gundam. Was the previous holder of the King of Hearts title before passing it onto his (foolish) apprentice, Domon Kasshu.
Note: Images with this tag either depict him or his trademark martial arts pose.
FAQ
Does NovelAI recognize master asia?
Compare the samples on this page. Every tag on this site shares the same seed and base prompt, so any change you see comes from master asia.
How do I write master asia in a prompt?
Write "master asia" near the front of the prompt and separate it from other tags with commas.
Should I use V5 or V4.5?
V4.5 shows the tag's effect more strongly. V5 gives steadier images with fewer artifacts.