About the hagakure toru tag
hagakure toru is a character tag that NovelAI Diffusion can use. On Danbooru it has 745 posts, and its best-rated still image scores 1,321. 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 hagakure toru
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 hagakure toru in a prompt
Put the subject first, then this tag, then quality tags.
hagakure toru, solo, best quality, masterpiecewlop, hagakure toru, 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
Character from Boku no Hero Academia. She is invisible due to her quirk, which allows her body to refract and redirect light. However, her clothes remain visible, as her quirk only affects her actual body.
Her likeness was finally revealed when she was shown unusually visible in an illustration (post #6220990) drawn for the series' 34th volume, depicting her with messy green hair and thick eyelashes. Due to this, it is made clear that her "hero outfit" is simply her being nude save for her gloves and shoes.
See also
FAQ
Does NovelAI recognize hagakure toru?
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 hagakure toru.
How do I write hagakure toru in a prompt?
Write "hagakure toru" 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.