💥 Kitashirakawa Anko from Tamako Market
— She Kitashirakawa Anko is Tamako’s younger sister, a fashion-conscious girl who often tries to act a little more mature than her age. She can get embarrassed by her family’s mochi shop and has a more reserved attitude than Tamako, but she still has plenty of cute and childish moments underneath it. Her different casual outfits and expressive reactions make her a surprisingly fun character to work with.
>Tamako Market 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 controlling the outfit separation and dealing with the most common outfit bleed issues.
😏Body proportion
If you want to generate her figure looks to be similar like the canon then just use those Forbidden tags combination
🧥 Suppressing the jacket outfit logo bleed
The jacket outfit can sometimes leak its crown logo detail into other outfits.
To reduce that behavior, try:
🚫 Negative prompt: school_emblem
This can help suppress the logo-like crown detail when it starts showing up where it should not.
🩳 Suppressing blue suspender shorts bleed
The blue suspender shorts outfit may leak some of its details into other outfits, especially shorts-based ones. The most common leaked details are:
buttons
yellow pockets
blue shorts structure
To reduce that behavior, try:
🚫 Negative prompt: (qadruxe:1.3), (buttons:1.5), (pocket:1.5), (blue_shorts:1.3)
This is especially useful when prompting the overall shorts outfit or other outfit variations that should not inherit those features.
🔕 Using outfit trigger words as negatives
You can also use the outfit trigger words themselves in the negative prompt to suppress a specific outfit from appearing.
For example:
Use
mifzorain negative prompt if you want to reduce the chance of the overall shorts outfit appearingUse
qadruxein negative prompt if you want to reduce the chance of the blue suspender shorts outfit appearing
This is one of the main benefits of using distinct 2-level outfit triggers in the first place.
🎀 Stabilizing the print shirt on blue suspender shorts
In her blue suspender shorts outfit, the shirt has a printed red ribbon / bow shape.
If that detail is hard to stabilize, try:
✅ Positive prompt: ribbon_print_shirt
This can help reinforce the printed shirt detail more clearly.
🎨 Wrong blue color on the suspender shorts outfit
If the blue suspender shorts outfit keeps producing the wrong kind of blue, try suppressing the overall shorts outfit influence:
🚫 Negative prompt: mifzora
This can help reduce cross-outfit interference when the color starts drifting.
📌 Recommended negatives for each outfit
These are the negative prompt combinations I recommend as starting points when prompting specific outfits.
For blue suspender shorts (qadruxe):
🚫 Negative prompt: mifzora, school_emblem
This helps suppress the overall shorts outfit and reduce the jacket outfit’s crown logo bleed.
For overall shorts (mifzora):
🚫 Negative prompt: (qadruxe:1.3), (buttons:1.5), (pocket:1.5), (blue_shorts:1.3), school_emblem
This helps suppress the blue suspender shorts details and also reduces the jacket logo leakage.
⚖️ LoRA strength and outfit flexibility
The raw dataset almost exclusively shows her wearing the same school uniform with an open black cardigan, so completely different outfits may still need stronger prompting.
A weight of 1 can still work with different outfits, especially when the new outfit is clearly defined.
Only lower the LoRA weight gradually when default 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
🎬 Anime screenshots with official art support
This LoRA was trained mainly using anime screenshots, with additional movie screenshots and Megami Magazine images used for extra support.👕 Three outfits with 2-level triggers
This version was trained using a 2-level trigger structure to make the outfits more flexible and reduce outfit bleeding between each other.
It contains three outfit variations:
- vopneli = jacket outfit
- qadruxe = blue suspender shorts outfit
- mifzora = overall shorts outfit
These trigger words do not have any actual meaning. I chose them because they are distinct and unlikely to overlap with normal English words, which helps keep the outfit signals cleaner.🔀 Outfit separation is better, but not perfect
The 2-level trigger setup helps separate the outfits more cleanly, but some leakage can still happen depending on the checkpoint, prompt, and LoRA strength.
The jacket outfit, for example, has a crown logo detail that can sometimes leak into her other outfits. Meanwhile, the blue suspender shorts outfit may also leak some of its own details, especially into other shorts-based outfits.🧷 Tagged outfit pieces for better control
The outfit pieces were tagged with flexibility in mind, so you can use the outfit trigger words as anchors and also suppress specific outfits when needed.
That said, this version still works best when you are mindful about which outfit-specific details may carry over into another look.As usual, the final result can still depend on your checkpoint, prompt, LoRA strength, CFG scale, and generation settings.
FAQ
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.