CivArchive
    Umamusume All in One LoRA - illustrious-v0.1-4th
    NSFW
    Preview 1
    Preview 2
    Preview 3
    Preview 4
    Preview 5
    Preview 6
    Preview 7
    Preview 8
    Preview 9
    Preview 10

    Umamusume All in One LoRA

    This is an All-in-One LoRA designed to generate a wide variety of characters from the popular game Umamusume: Pretty Derby with a single model. Without the hassle of managing individual character LoRAs, you can easily bring numerous Umamusume to life, including Stay Gold, Almond Eye, Loves Only You, and many more, with just this one file.

    Notice

    This model is a re-upload. The previous model page was accidentally deleted during a version update process. My apologies for the inconvenience!

    ✨ Features

    • Extensive Character Library: Capable of generating most of the main characters from the game with high fidelity.

    • Versatile Costume Support: Faithfully reproduces each character's unique racing outfits, as well as school uniforms, casual wear, and other styles.

    • Easy to Use: Achieve your desired images simply by inputting character names or feature tags, without the need for complex prompts.

    🌟 Character & Prompt Information

    For detailed prompt information regarding the characters, costumes, and features included in this LoRA, please refer to the Hugging Face link. Find the precise tags for the character you wish to create and utilize them in your prompts.

    Description

    Training Details

    • Dataset: Trained on ~140,000 images sourced exclusively from Danbooru (knowledge cutoff: June 1st, 2025).

    • Data Pipeline: Utilized a fully automated pipeline for data filtering and curation.

    • Captioning Method:

      • Image captions were generated using a variety of Vision Language Models (VLMs).

      • A custom-trained YOLO model was used to create precise, object-aware natural language prompts to guide the VLMs.

      • Images with natural language captions were processed by at least 3 different VLMs, with one caption being randomly selected during training for diversity.

    • Training Strategy:

      • Employed an adaptive training method.

      • Character tag repeats (up to a maximum of 15) were applied inversely to their frequency in the dataset for a more balanced character representation.

    • Base Model:

      • This LoRA was trained based on illustrious v0.1.

      • It might be compatible with other models derived from illustrious v0.1, but this has not been formally tested.

    • Metadata: For more specific training details, please consult the LoRA's metadata.

    FAQ

    LoCon
    Illustrious

    Details

    Downloads
    4,467
    Platform
    SeaArt
    Platform Status
    Available
    Created
    6/23/2025
    Updated
    6/23/2025
    Deleted
    -

    Files

    Available On (1 platform)

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