💥 Selena from Majo no Tabitabi
— She is one of those Majo no Tabitabi characters where the cute first impression comes with a very heavy warning label. She looks soft, fragile, and innocent at first, but her story carries one of the darker and more unsettling turns in the series. That contrast between sweet appearance and tragic horror is what makes her memorable despite her limited screen time. A small but impactful character for anyone who likes the darker side of Wandering Witch
>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.
🔞 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.
😏Body proportion
If you want to generate her figure looks to be similar like the canon then just use those Forbidden tags combination.
🧥 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 buttoned collar details appearing when you do not want it:
🚫 Negative prompt: button-down_collar
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
🎬 Anime screenshot dataset
This LoRA was trained using anime screenshots only. Selena’s source scenes are all evening-based, so the original dataset naturally has a warm lighting condition.
I processed the dataset to reduce that bias, so she should still work outside evening prompts. However, some warm tint may still appear depending on your checkpoint and settings.👗 Outfit flexibility
The dataset only contains one main dress design, so her default outfit can be a bit persistent. This is useful for generating her canon look, but changing outfits may need more control than usual.
For outfit changes, lowering the LoRA strength and adding her default outfit details to the negative prompt should help reduce unwanted dress leakage.⚠️ Prompt safety note
Selena has a petite form that can technically be recreated with certain tag combinations, but those prompts can easily move into platform-sensitive territory.
I will not provide a direct prompt setup for that form here. Please keep your prompts safe and within the platform rules.Results can still vary depending on checkpoint, prompt, LoRA strength, and generation settings.