About the ta-class battleship tag
ta-class battleship is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,191 posts, and its best-rated still image scores 238. 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 ta-class battleship
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 ta-class battleship in a prompt
Put the subject first, then this tag, then quality tags.
ta-class battleship, solo, best quality, masterpiecewlop, ta-class battleship, 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
Common abyssal ship found in the middle difficulty maps of Kantai Collection. Most often portrayed as the most feminine of the ships, due to taller stature than most of the ships, the human-like appearance combined with white hair, and wearing little clothing other than a sailor shirt and black panties.
Notoriously hard to kill for both newer and older admirals. While not extremely powerful when compared to those such as wo-class aircraft carrier and the newer re-class battleship, they make up in numbers, sometimes coming in pairs and often seen with bosses and the stronger relatives, sometimes both.
FAQ
Does NovelAI recognize ta-class battleship?
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 ta-class battleship.
How do I write ta-class battleship in a prompt?
Write "ta-class battleship" 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.
