About the piranha plant tag
piranha plant is a character tag that NovelAI Diffusion can use. On Danbooru it has 622 posts, and its best-rated still image scores 305. 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 piranha plant
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 piranha plant in a prompt
Put the subject first, then this tag, then quality tags.
piranha plant, solo, best quality, masterpiecewlop, piranha plant, 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
The Piranha Plant is a common plant enemy from the Mario series found in Warp Pipes or flower pots. Known as Pakkun Flower in Japan. A potted Piranha Plant appears as a playable fighter in the Super Smash Bros. series, debuting in an Super Smash Bros. Ultimate update after the game's release.
Piranha Plants have sharp teeth and no eyes, somewhat similar to a venus flytrap. Most Piranha Plants appear as red with white spots, though many other variants of the Piranha Plant appear throughout the series.
Official art
FAQ
Does NovelAI recognize piranha plant?
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 piranha plant.
How do I write piranha plant in a prompt?
Write "piranha plant" 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.