About the yokoyama chika tag
yokoyama chika is a character tag that NovelAI Diffusion can use. On Danbooru it has 395 posts, and its best-rated still image scores 263. 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 yokoyama chika
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 yokoyama chika in a prompt
Put the subject first, then this tag, then quality tags.
yokoyama chika, solo, best quality, masterpiecewlop, yokoyama chika, 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
Idolmaster Cinderella Girls character.
Chika has a love of magical girls and boundless energy. She finds the stage theatrics and the costumes of idols similarly flashy and cute, and wishes to experience the magic for herself. Chika owns a wide variety of toys based on the Trinkets from other magical girl shows. In fact, everything from her toys to her first Idol outfit to her overall appearance is evocative of Sailor Moon-like shows. She may make mistakes occasionally, but she responds to them all with a smile.
Appearance
External links
FAQ
Does NovelAI recognize yokoyama chika?
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 yokoyama chika.
How do I write yokoyama chika in a prompt?
Write "yokoyama chika" 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.