About the mary cochran tag
mary cochran is a character tag that NovelAI Diffusion can use. On Danbooru it has 263 posts, and its best-rated still image scores 195. 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 mary cochran
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 mary cochran in a prompt
Put the subject first, then this tag, then quality tags.
mary cochran, solo, best quality, masterpiecewlop, mary cochran, 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
An iDOLM@STER Cinderella Girls character in the Passion (Yellow Sun) category. She is an 11 year old foreigner from San Francisco who moved to Japan due to family circumstances. Tries to act grown up. Mary is a young American fashionista. She left her home in San Francisco to become an idol in Japan. She likes to be treated as a noble lady and to be the center of attention. However she still feels lonely, as she often calls out for her mother when asleep. Mary likes to eat, but only the best of foods.
Appearance
External links
FAQ
Does NovelAI recognize mary cochran?
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 mary cochran.
How do I write mary cochran in a prompt?
Write "mary cochran" 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.