
✨ Oyabin from Oyabin Hypnotism
— She is a tomboyish little boss who acts tough, talks big, and somehow still ends up taking care of her followers. She has that fun “annoyed but secretly kind” energy, like she will call your idea stupid while still checking it out just because you asked. Of course, that also makes her the perfect victim for a suspicious hypnosis app she should have ignored from the start. A cute, bratty boss-girl type with plenty of attitude, smug faces, and a softer side buried under all the yelling.
560514
If you know, you know~
One of my favorite doujin character. She is tomboy while still looking cute and girly, bossy while still care about her followers. How can I not like her?!?
Sadly I don't know what is her name. Not sure if it's even stated.
>Doujinshi COLLECTION<
⚠️Turn off your R/X/XXX Filter to see hidden JUICY Loras in >HERE<

🖼️ 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.
🔞 NSFW gallery (18+)
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.
🖤 Manga-like result
For a result closer to the original doujin’s greyscale manga appearance, avoid positive tags that strongly push anime coloring, vivid colors, or an anime screenshot style. It is also better to avoid character or outfit color tags, since they may encourage the checkpoint to colorize the image.
Recommended:
✅ Positive prompt: greyscale
🎓 Suppressing school-uniform bias details
Because her default outfit has a school-like look, the blazer may sometimes generate with extra details such as a logo, emblem, badge, or pocket even when they are not intended.
To reduce that effect, try:
🚫 Negative prompt: logo, emblem, badge, pocket
This is mainly useful when the checkpoint keeps adding school-uniform style decorations on its own.
🌈 Changing garment colors
Since the dataset is greyscale-only, color control works best when you directly attach the color to the clothing item you want to affect.
Recommended format:
✅ Positive prompt: [color]_[garment_name]
For example, instead of only writing:
hooded_jacket
try using:
white_hooded_jacket
This gives the model a clearer instruction and usually works better than mentioning a color separately without tying it to the clothing piece.
You can apply the same idea to other parts of the outfit as well, depending on what you want to recolor.
🧥 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 plaid details on her skirt appearing when you do not want it:
🚫 Negative prompt: plaid_skirt
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
⚫ Greyscale-only dataset
This LoRA was trained using greyscale images only. There are no colored images in the dataset.
Because of that, the colors shown in my showcase are based on my own taste rather than strict source accuracy. In other words, this version is not trained to preserve any canon color palette, since the dataset simply does not contain that information.🧷 Appearance and outfit pieces are fully tagged
The individual parts of her appearance and outfit were tagged separately.
That gives you more control when prompting, and you can treat those tags as anchors when you want to change specific colors or clothing details. This is especially useful for a greyscale-trained LoRA, since the structure of the outfit is learned more reliably than any fixed color scheme.🧥 Limited outfit and hairstyle coverage
The dataset only contains her default outfit: a jacket + blazer combination with a plaid skirt.
It also only includes her side-ponytail hairstyle. Any other variation shown in my showcase is not part of the original dataset coverage, but rather an example of how flexible the LoRA can still be when prompted properly.
Because of that, the most stable result will still be her default outfit and side-ponytail look.🖤 Stable mole detail
The mole detail turned out fairly stable in this version.
Compared to some other characters with small facial details, this one should need fewer retries to keep the mole in place. Based on my testing, it also handles my usual hi-res settings without causing the mole to fall apart too easily.As usual, the result can still depend on your checkpoint, prompt, LoRA strength, CFG scale, and generation settings.









