CivArchive
    Ass SLIDER - v3.0
    NSFW
    Preview 149481800

    Overview

    This is a generic size‑adjustment LoRA for the Moss-image model, designed to increase or decrease buttock size based on the prompt. Because Moss-image already accepts extensive textual information and generates high‑quality images without difficulty, it does not require specialized bypass or detail LoRAs. This slider acts as a simple, prompt‑controlled dial.

    The model provides four experimental versions (v1–v4), all trained with the Fizgig application. They are not fully tested; each version is unique and produces slightly different final results.


    • Recommended range: -3 to +3

    • Exceeding this range may cause drastic image changes or unexpected artifacts
      *v4 can handle larger range values

    Negative (-) values reduce buttocks size 
    Positive (+) values increase buttocks size


    Experimental Versions

    • v1: Attempted specific description of buttocks, waist, and legs

    • v2: Additionally attempted to correct lighting and hand size

    • v3: Experimented with stop, change prompt, and start (per epoch)

    • v4: Focused solely on the buttocks, without expanding into anatomy

    All versions are experiments - results vary


    Notes

    • This is a slider LoRA, not a detail or pose LoRA

    • All versions were trained purely from prompts, without any input images

    • Use natural language prompts to guide the adjustment (e.g. “larger buttocks”, “smaller buttocks”)

    • Combine with other LoRAs only if you need additional stylistic control; not required for basic use


    License & Usage

    • You are free to use this model in your projects, including merging or mixing it with other models.

    • If you include this LoRA in any merge or mix, please give proper credit.


    Support the Creator

    If you enjoy my work and want to help cover the electricity costs required to train and refine these models, please consider supporting me:

    Address: https://ko-fi.com/weirddreamer (Donations are always appreciated!)

    Description

    v3: Experimented with stop, change prompt, and start (per epoch), and additionally tried to lock the pose, orientation, and facial expression, ensuring the subject poses directly facing the camera rather than with her back turned

    FAQ

    LORA
    MOSS Image

    Details

    Downloads
    9
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/19/2026
    Updated
    11/19/2026
    Deleted
    -

    Files

    WeirdDreamer_ass-slider_moss-v3.safetensors