About the miyoshi sana tag
miyoshi sana is a character tag that NovelAI Diffusion can use. On Danbooru it has 309 posts, and its best-rated still image scores 114. 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 miyoshi sana
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 miyoshi sana in a prompt
Put the subject first, then this tag, then quality tags.
miyoshi sana, solo, best quality, masterpiecewlop, miyoshi sana, 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
An iDOLM@STER Cinderella Girls character in the Passion (Yellow Sun) category. Sana is a fanatical arcade, console, and handheld gamer. She's never without a gaming device immediately available and quite competitive when it comes to them. The gaming devices she's shown with on her Rare cards are clearly the Nintendo DS and the Sony PSP. Most of her clothes depict symbols from many Namco Bandai video games, ranging from Pac-Man, to Galaga, to the Tales series, to THE iDOLM@STER itself. She can often be found visiting arcade centers when street shopping.
Appearance
External links
FAQ
Does NovelAI recognize miyoshi sana?
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 miyoshi sana.
How do I write miyoshi sana in a prompt?
Write "miyoshi sana" 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.