CivArchive
    Azusa Aizawa: [I've Been Killing Slimes for 300 Years and Maxed Out My Level (OVA)] スライム倒して300年、 知らないうちにレベルMAXになってました ~そのに~ アズサ・アイザワ - Anima 0.1
    NSFW
    Preview 131574606

    Azusa Aizawa (アズサ・アイザワ【相沢 梓】) from TV anime "I've Been Killing Slimes for 300 Years and Maxed Out My Level スライム倒して300年、 知らないうちにレベルMAXになってました ~そのに~ (OVA)".

    This model offers a mini-sized version of the character's original art style.

    You can use the prompts below to create her classic clothing:

    mai_azusa300,very_long_hair,low-tied_long_hair,blonde_hair,blue_eyes,witch,witch_hat,ascot,white_tube_top,black_coat,long_sleeves,wide_sleeves,green_skirt,knee_boots

    Recommend preferred Strength: 0.7~1.

    A relaxing, soothing animation that unfolds at a leisurely pace.

    I also want to live a leisurely life.

    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, divergent 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

    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, divergent 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 :)

    FAQ

    LORA
    Anima

    Details

    Downloads
    61
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/23/2026
    Updated
    5/25/2026
    Deleted
    -
    Trigger Words:
    mai_azusa300,very_long_hair,low-tied_long_hair,blonde_hair,blue_eyes,witch,witch_hat,ascot,white_tube_top,black_coat,long_sleeves,wide_sleeves,green_skirt,knee_boots

    Files

    mai_azusa300_anima.safetensors

    Mirrors