About the kyle broflovski tag
kyle broflovski is a character tag that NovelAI Diffusion can use. On Danbooru it has 470 posts, and its best-rated still image scores 194. 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 kyle broflovski
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 kyle broflovski in a prompt
Put the subject first, then this tag, then quality tags.
kyle broflovski, solo, best quality, masterpiecewlop, kyle broflovski, 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
Kyle Broflovski is a fictional character in the adult animated sitcom South Park. He is voiced by and loosely based on series co-creator Matt Stone. Kyle is one of the series' four central characters, along with his friends Stan Marsh, Kenny McCormick, and Eric Cartman. He debuted on television when South Park first aired on August 13, 1997, after having first appeared in The Spirit of Christmas shorts created by Stone and long-time collaborator Trey Parker in 1992 (Jesus vs. Frosty) and 1995 (Jesus vs. Santa).
FAQ
Does NovelAI recognize kyle broflovski?
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 kyle broflovski.
How do I write kyle broflovski in a prompt?
Write "kyle broflovski" 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.