About the souza samonji tag
souza samonji is a character tag that NovelAI Diffusion can use. On Danbooru it has 353 posts, and its best-rated still image scores 44. 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 souza samonji
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 souza samonji in a prompt
Put the subject first, then this tag, then quality tags.
souza samonji, solo, best quality, masterpiecewlop, souza samonji, 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
A Touken Ranbu character. Part of the Samonji school along with Sayo Samonji and Kousetsu Samonji.
The actual sword was treated as a treasure by most of its owners, and never saw battle. As a result, Souza Samonji is extremely bitter about it, seeing that he felt like he was in a gilded cage for most of his life. His attitude towards the Saniwa also extends to this resentment, wryly asking them is they're going to treat him the same way. When he is broken, he states that he's finally free of his burdens. Despite this cynical mindset, he says it all with a smile.
FAQ
Does NovelAI recognize souza samonji?
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 souza samonji.
How do I write souza samonji in a prompt?
Write "souza samonji" 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.