About the toyama kasumi tag
toyama kasumi is a character tag that NovelAI Diffusion can use. On Danbooru it has 545 posts, and its best-rated still image scores 282. 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 toyama kasumi
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 toyama kasumi in a prompt
Put the subject first, then this tag, then quality tags.
toyama kasumi, solo, best quality, masterpiecewlop, toyama kasumi, 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
Show the wiki text ▾Hide ▴
The guitarist and vocalist of the band Poppin'Party, and main protagonist of BanG Dream!. She is an energetic and optimistic girl who was inspired by a starlit night to begin playing music.
She has brown hair with double cone hair buns meant to resemble a star (how they work are a mystery, even to other characters), and purple eyes.
She has a younger sister called Toyama Asuka.
Her birthday is July 14th. Her seiyuu is Aimi.
See also
- POPY - a Yumenokessho/CeVIO/Synthesizer V voicebank based on her
FAQ
Does NovelAI recognize toyama kasumi?
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 toyama kasumi.
How do I write toyama kasumi in a prompt?
Write "toyama kasumi" 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.