Prim Fiorire (プリム・フィオリーレ) from H anime "Kuroinu ～The proud saint is stained with white filth～ 黒獣 〜気高き聖女は白濁に染まる〜".
This model offers a mini-sized version of the original art style.
You could use the prompts below to create characters:
mai_primk,very_long_hair,wavy_hair,pink_hair,parted_bangs,blue_eyes,large_breasts,hair_ribbon,tiara,choker,necklace,white_dress,center_opening,detached_sleeves,puffy_sleeves,white_gloves,pink_pantiesRecommend preferred Strength: 0.7~1.
A classic character that needs no further explanation.
Since some characters have already been created, let's continue to make some more. Compared to the excellent models created by other artists in the community, this set of models is a mini version.
This character is also a young-looking adult. Please visit my Pixiv community to view other example illustrations.
PS: Some sample illustrations cannot be posted in the community; you can visit my Pixiv community posts to view them.
https://www.pixiv.net/artworks/143678037
About Anima
This is a derivative model of Cosmos-Predict2-2B-Text2Image, with an architecture more geared towards model engineering, facilitating AI componentization tasks such as LLM model integration.
While its marketing emphasizes natural language understanding capabilities, it's actually still trained on Danbooru-style tags.
For creating favorite anime characters, diffuse methods rely more heavily on the underlying data the model carries.
Like many other models (such as IL), Anima still needs to accumulate more training data and adapt to better VAEs to enhance its performance and expressiveness.
For personal enthusiasts like myself who can't make model engineering our main profession, I'll wait for the Anima model ecosystem to mature before investing further :)
Description
Anima currently requires fine-tuning; LoRA-level adjustments have a very limited impact on the overall model output :)
FAQ
Comments (2)
why did you make custom tags like "parted_bangs" instead of just using "parted bangs" thats basically supported by every checkpoint?
This is actually a pretty complex issue :) In the SDXL series models, what actually connects to pixel patterns is 'parted bangs'; 'parted_bangs' is the label convention used in Danbooru.
Most common training and inference scripts will replace the '_' with a space at runtime.
However, during dataset quality checks, using '_' is visually better for humans than spaces.
So I marked it using the Danbooru label convention in the explanation, but you can remove the '_' when using it, and it shouldn't affect the results.
(^～^;)ゞ