CivArchive
    Lovely pear style XL - V1
    NSFW
    Preview 86830462
    Preview 86830486
    Preview 86830479
    Preview 86830480
    Preview 86830481
    Preview 86830483
    Preview 86830517
    Preview 86838759
    Preview 86830482
    Preview 86830534
    Preview 86830536
    Preview 86830535
    Preview 86830551
    Preview 86830552
    Preview 86830553
    Preview 86830555
    Preview 86830563
    Preview 86830564
    Preview 86830566
    Preview 90595511

    Lovely pear style XL


    Description:

    "Where brushstrokes speak and silence paints—emotions take shape in between."

    Lovely pear style XL is a LoRA that captures the poetic, contemplative harmony of traditional calligraphy and expressive portrait painting.
    Inspired by the aesthetic spirit of contemporary Japanese artist Airi Hara, this model seeks to translate the flow of ink, movement of the brush, and the beauty of empty space into visual storytelling.

    Here is her original site.

    Just as Hara fuses the power of handwritten characters with figural beauty, this LoRA channels a similar elegance—where emotions are not shouted but whispered through line, contrast, and composition.

    The result is a tool that helps you create portraits rich in subtle emotion, soft rhythm, and evocative stillness. Whether you’re aiming for serenity, mystery, or inner conflict, the visual poetry this model brings will serve as your brush.


    Best used for:

    • Hair and clothing that flow like brush calligraphy

    • Portraits with ink-like gradients and expressive textures

    • Minimalist compositions with emotional depth

    • Scenes evoking nature—water, wind, cherry blossoms, handmade paper

    • Imagery that leaves “resonance” in the viewer’s heart


    Lovely pear style XL is more than a model—it’s a way of composing poetry with images.
    For those who want their art to echo in the silence after it’s seen, this LoRA is your perfect companion.

    Recommended weight:around 0.5~1.0

    basic idea is to decide based on balance with other basemodel.

    for strong pre-trained basemodel like Animagine4.0, recommend around 1.0 incl.over 1.0.

    for basemodel like SDXL or weak pre-trained basemodel, i recommend around 0.5.

    Reference:LoRA weight from 0.1 to 1.0 (Basemodel:Animagine4.0opt)

    Description

    FAQ

    LORA
    SDXL 1.0

    Looks like we don't have an active mirror for this file right now.

    CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    243
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    7/6/2025
    Updated
    4/21/2026
    Deleted
    4/13/2026
    Trigger Words:
    lovelypearstyle
    (ink-style, ink_wash_painting)
    made of kanji
    made of multi colored kanji
    ink wash painting theme
    ink wash painting concept
    kanji

    Files

    lovelypearstyle.safetensors

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.