Download
1 variant available
1890 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
00 1 2 3 4 5 6 7 8 9
(32)
Aug 26, 2026
🎬 Anime and movie screenshots with official art support
This LoRA was trained using a mix of anime screenshots, movie screenshots, and Megami Magazine scans. The movie screenshots received some color correction to keep them closer to the rest of the dataset, while some magazine images were adjusted to remove surrounding objects and text that were not useful for the character.👗 Two supported school outfit variations
This LoRA was trained with two outfit variations: her blue sweater and her pinafore dress.
Both outfits are represented directly in the dataset, giving the LoRA some separation between the two instead of treating the entire school uniform as a single fixed combination.💄 Mole stability was reinforced in the dataset
Her mole is a very small facial detail, so some of the source images were adjusted to make it more noticeable and consistent during training.
This makes the mole considerably more stable during normal generation, although very small details like this can still become inconsistent depending on the camera distance, generation settings, and hires fix.💇 Hairstyle flexibility with some remaining bias
This version was intentionally trained with hairstyle flexibility in mind, and the showcase images demonstrate that her hair can be changed beyond its usual appearance to some extent.
The original hairstyle can still influence certain generations, especially from particular camera angles, so complete hairstyle separation should not be expected in every situation.🐰 School emblem prioritizes flexibility
Her uniform has a small bunny-like logo, but the feature has poor coverage and is too small to reproduce consistently.
Instead of focusing too much on accurately reproducing such a tiny detail, I prioritized preventing the emblem from becoming heavily baked into the character and appearing on every other outfit.As usual, the final result can still depend on your checkpoint, prompt, LoRA strength, CFG scale, camera angle, and generation settings.
Show more

3220 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
80.9K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
33.5K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

Created on Civitai
License:
Illustrious License
💥 Kitashirakawa Tamako from Tamako Market
— She is a cheerful and warmhearted girl who grew up surrounded by the lively atmosphere of her family's mochi shop and the Usagiyama shopping district. She has an easygoing, friendly personality and genuinely cares about the people around her, which makes her feel right at home in such a close-knit community. Even when strange things suddenly enter her otherwise ordinary life, Tamako tends to face them with the same bright curiosity and kindness that define her.
>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
💄 Troubleshooting the mole
The mole should generally be fairly stable, but small facial details can still behave strangely depending on the generation or hires fix.
If you start getting extra moles, try:
🚫 Negative prompt: multiple_moles
Multiple moles can also occasionally appear after hires fix. If that happens, try keeping the hires denoising strength at 0.1 or lower. I personally recommend values around 0.05–0.1 when preserving tiny facial details is important.
If you simply do not want to deal with the mole at all, you can instead use:
✅ Positive prompt: no_mole
This intentionally removes the feature and avoids most mole-related inconsistencies entirely.
💇 Suppressing unwanted sidelocks
From some specific camera angles, the LoRA can occasionally generate sidelocks even when you are not asking for them.
If that happens, try:
🚫 Negative prompt: sidelocks
This is especially useful when testing alternative hairstyles where those extra strands interfere with the intended hair shape.
🐰 Preventing the school emblem from leaking
Her uniform has a small bunny-like school logo, but the source coverage for it is not good enough for reliable fine details. This version instead focuses more on preventing the emblem from appearing automatically on unrelated outfits.
If it still appears on another outfit, try using:
🚫 Negative prompt: school_emblem
The emblem itself may also look inconsistent when you intentionally prompt it, simply because it is a very small feature with limited dataset coverage.
⚖️ LoRA strength and outfit flexibility
The dataset is still biased toward the character’s usual outfit, so completely different outfits may need clearer prompting to work reliably.
A LoRA weight of 1 can still work well for alternate outfits, especially when the new clothing is clearly defined in the prompt.
Only lower the LoRA weight gradually if default outfit details keep leaking even after using clear outfit tags and negative prompts. Lowering it too much can also weaken the character’s face, hair, and overall 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

