CivArchive
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Videl – Dragon Ball Z | Krea 2 LoRA

    A Krea 2 LoRA dedicated to Videl from Dragon Ball Z, designed to reproduce her original DBZ appearance while remaining flexible enough for new outfits, poses, environments, and situations.

    The LoRA focuses on keeping Videl recognizable and faithful to the original character, including her facial features, vivid blue eyes, athletic build, black hair, and iconic hairstyles.

    It can reproduce different versions of Videl, including her long black hair with low twintails and gold cylindrical hair clips, as well as her short spiky haircut.

    The model is intended for more than just recreating scenes from the anime. Feel free to experiment with casual clothes, combat scenes, different expressions, original outfits, modern settings, or completely new situations.

    Long-haired Videl:
    Videl, long black hair, low twintails, gold cylindrical hair clips, vivid blue eyes

    Short-haired Videl:
    Videl, short spiky black pixie cut, vivid blue eyes

    For better results, describe the hairstyle you want directly in the prompt, especially when switching between her different appearances.

    Description

    Videl V7.2 focuses on expanding the variety and flexibility of the LoRA.

    This version introduces:

    - New outfits and alternate clothing styles

    - More diverse backgrounds and environments

    - New situations, poses, and scene compositions

    - Improved atmosphere and visual storytelling

    - Better adaptability for cinematic and dynamic prompts

    The goal of this update was to keep Videl recognizable while giving the model more creative freedom and scene diversity.

    Please note that some results may still appear imperfect or inconsistent due to the limited amount of high-quality reference images available for certain outfits, expressions, or situations.

    Captions were generated using WD14 tagging, and due to the large amount of images in the dataset, not every tagging mistake or captioning error was manually corrected. (probably al ot of mistake)

    FAQ

    LORA
    Illustrious

    Details

    Downloads
    124
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/9/2026
    Updated
    9/25/2026
    Deleted
    -

    Files

    Videl V7.2 .safetensors

    Mirrors

    CivitAI (1 mirrors)