CivArchive
    Nino | Majo no Tabitabi/Wandering Witch: The Journey of Elaina/魔女の旅々 - V1
    NSFW
    Preview 136348263
    Preview 136348277
    Preview 136348273
    Preview 136348281
    Preview 136348265
    Preview 136368727
    Preview 136348266
    Preview 136368723
    Preview 136433583

    💥 Nino from Majo no Tabitabi

    Her appearance in Majo no Tabitabi starts quietly, almost like she is just another gentle maid passing through Elaina’s journey. But the more her situation is revealed, the more that quietness starts to feel painful instead of peaceful. Her story does not rely on a big dramatic speech; it hurts because of how helpless and trapped it feels. She is a brief character, but her episode leaves the kind of sadness that stays around after the scene ends.

    >Majo no Tabitabi COLLECTION<

    ⚠️Turn off your X/XXX Filter to see hidden JUICY Loras

    🖼️ How I Generate My Images

    I made a full article that explains how I generate my images — including my settings, prompting tips, and even my potato PC setup 😅

    👉 Check it out here if you’re curious or want to try the same method.

    Check my account here to see the spicy showcase that I can't show here, if any.

    🎨 Prompt Tips

    These are optional starting points for handling a few behaviors of this version. You may still need some retries depending on the checkpoint, prompt, and LoRA strength.

    🔎 Pink dress seam-like details

    The original dataset does not have seam details on her pink dress, but generations may still add them sometimes. For a cleaner result closer to the source, try this:

    ⚙️ CFG: 6–7
    💪 LoRA weight: 0.9–1

    My usual CFG setting is 5, but raising it a bit can help the prompt follow the outfit more strictly. This should reduce the extra seam-like details, but it may still need a retry sometimes.

    👕 Removing the default layered outfit bias

    Her default dress + shirt combination is somewhat baked in, so when prompting simpler shirt-only looks or other layered outfits, the model may still try to bring back the dress/vest structure.

    To reduce that behavior, try:

    🚫 Negative prompt: (dress:1.5), (sleeveless_dress:1.5), (vest:1.5), (shirt_under_dress:1.5)

    ⚙️ CFG: 7

    💪 LoRA weight: 0.5–0.8

    Lower LoRA weight helps reduce the outfit bias, while higher CFG helps the prompt take control more strongly.

    🎀 Cross-laced chest detail and neck ribbon leakage

    If the cross-laced chest detail or neck ribbon keeps appearing on another outfit, lower the LoRA weight and negative those details directly.

    For example:

    🚫 Negative prompt: neck_ribbon, cross-laced_dress

    Like the other cases, this is controllable, but depending on your checkpoint and settings, it may still need a few retries.

    🧥 Default outfit details appearing on other outfits

    When a default outfit detail keeps appearing in a different outfit, add the exact leaking detail to the negative prompt.

    For example, if the cross-laced details appearing when you do not want it:
    🚫 Negative prompt: cross-laced_dress

    Use the specific leaking tag instead of adding many unrelated negative tags.

    ⚖️ LoRA strength and outfit flexibility

    A weight of 1 can still work with a very different outfit, especially when the new outfit is clearly different from her default one.

    Only lower the LoRA weight gradually when outfit details keep leaking even after using clear outfit tags and negative prompts. Lowering it too much may also weaken her face, hair, and overall character identity

    📊 Lora Project

    If you want to know what characters that I'm covering next you can check these link :
    👉 Personal Project
    👉 Commision Project

    If this model sparked something in you, show some love with a like, review, or buzz.
    Now go—


    Be wild

    Description

    👗 Seam-like dress details

    This version may sometimes generate extra seam-like details on the pink dress, even though those details are not actually present in the dataset. If you want a cleaner result closer to the source, it usually helps to raise the CFG from my usual setting of 5 up to around 6–7, and use a LoRA weight around 0.9–1.
    
    Even with that workaround, it can still need a retry sometimes.

    👕 Dress + shirt baked-in bias

    Her default layered outfit has a bit of baked-in bias. Because the dress + shirt combination appears very consistently in the dataset, the model may try to bring back vest/dress-like layering even when you want a simpler shirt-based outfit.
    
    If you want to push the generation further away from that default layered look, lower the LoRA weight, increase CFG, and use more specific negative tags. I added the exact prompt tips below.

    🎀 Cross-laced + neck detail leakage

    The cross-laced chest detail and neck ribbon can also leak into other outfits sometimes. If that happens, lower the LoRA weight a bit and put the exact leaking details into the negative prompt, such as neck_ribbon and cross-laced_dress.

    As usual, the result can still vary depending on your checkpoint, prompt, LoRA strength, and settings, so a few retries may still be needed.

    LORA
    Illustrious

    Details

    Downloads
    65
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/12/2026
    Updated
    7/12/2026
    Deleted
    -
    Trigger Words:
    n1nomnt
    red_eyes, black_hair, medium_hair, diagonal_bangs, hair_over_one_eye
    headscarf, pink_dress, sleeveless_dress, long_dress, shirt_under_dress, dress_shirt, white_shirt, three-quarter_sleeves, sleeves_rolled_up, neck_ribbon, black_ribbon, cross-laced_dress, waist_apron
    flats, black_footwear

    Files

    V1.safetensors

    Mirrors

    CivitAI (1 mirrors)