Download
1 variant available
2010 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
40 1 2 3 4 5 6 7 8 9
10 1 2 3 4 5 6 7 8 9
(36)
Jul 24, 2026
🎬 Limited source coverage
This LoRA was trained using anime screenshots and a small number of generated images for additional support.
Estelle only appears in one episode, so the available source material and outfit coverage are fairly limited. Because of that, uncommon poses and extreme camera angles may be less stable and could require a few retries.🧥 Outfit pieces are individually tagged
The individual parts of her default outfit were tagged separately to provide better prompt control.
However, you should still be mindful when prompting her from angles where some outfit pieces would normally be hidden. Forcing too many clothing tags at once can make the model display details that should not be visible from that perspective.🧣 The cloak design is somewhat baked in
The cloak design appears to be more strongly baked into this version than I originally intended. It may still produce collar-like variations even after lowering the LoRA weight or changing her outfit.
I intentionally chose this epoch because her other character details looked more pronounced and consistent compared to the alternatives. For me, that improvement was worth the cloak-related trade-off.
You may be able to fight this behavior with stronger negative prompting or by combining the model with another clothing LoRA.👁️ Eye color limitation
Estelle’s eyes look yellow with a subtle green accent in the original anime, at least to my eyes.
In this version, they usually appear as plain yellow without much of the original green tint. Yellow covers a fairly broad and familiar color range for the model, while Estelle’s limited source material did not provide enough consistent examples to preserve that more specific color balance reliably.As usual, results can still vary depending on the checkpoint, prompt, LoRA strength, CFG scale, and generation settings.
Show more

3120 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
77.7K0 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
32.9K0 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

Created on Civitai
License:
Illustrious License
💥 Estelle from Majo no Tabitabi
— She is one of the more tragic witches in Majo no Tabitabi, tied to one of the anime’s darkest stories. At first, she feels composed and determined, carrying herself like someone who has already made up her mind no matter the cost. But behind that calm attitude is grief, desperation, and a painful hope that things can still be fixed. She is a memorable pick for anyone who likes elegant witch characters with a much heavier emotional edge.
>Majo no Tabitabi 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 some of this version’s more noticeable behaviors. The best combination may still depend on your checkpoint and prompt.
🔘 Too many buttons on the outer clothing
For some reason, her black outer garment tends to generate with more buttons than it should.
To reduce this behavior, try adding:
🚫 Negative prompt: buttons
You can also increase its weight slightly if the extra buttons continue appearing.
🧥 Suppressing the default outfit
Some parts of her default outfit, especially the cloak and collar structure, may remain visible even when you prompt a different outfit.
When changing her clothes, place the unwanted default outfit tags in the negative prompt.
Example:
🚫 Negative prompt: (collared_cloak:1.5), blazer, necktie, cross_tie
Adjust the list based on which pieces keep returning. You do not always need to suppress every part of the outfit at once.
⚙️ LoRA weight and CFG
This version does not seem to have one perfect setting for every prompt, so experimenting with the balance between CFG and LoRA strength is recommended.
Suggested starting ranges:
CFG scale:
4–6LoRA weight:
0.7–1
Sometimes CFG 5 may produce a cleaner result, while another prompt may work better at CFG 6. The same applies to LoRA strength: lowering it can improve outfit flexibility, while raising it may help preserve her face and other character details.
Treat these values as a mix-and-match starting point rather than strict requirements.
⚖️ 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

