✨ Unga-chan from OtakuVS

— An unnamed girl from a prehistoric-themed skit featuring Peepo-chan. Peepo offers her a strange fruit that looks a bit like a blueberry, which she happily eats before promptly passing out. Her appearance is extremely short, but the ridiculous outcome of their interaction makes her one of the more memorable one-off characters.

>OtakuVS COLLECTION<

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.

😏Body proportion

If you not satisfied with her proportion, then you can always use those Forbidden tags combination in positive prompt.

⚖️ LoRA strength and design flexibility

This LoRA is still influenced by its limited source coverage, so features that are not clearly defined in the prompt may fall back toward the learned default interpretation.

A LoRA weight of 1 can still work well, especially when the design details you want are clearly described.

Only lower the LoRA weight gradually if default details keep leaking even after using clear positive and negative tags. 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

Description

🎬 Trained from a very small source set with AI-assisted extension

This LoRA was trained from just 4 usable reference images taken from the YouTube video series, which were then extended with AI assistance to make the dataset more practical for training.

Because the original source coverage is very limited, this version is built around those few references rather than a large variety of scenes or poses.

🪵 Wooden weapon is not a training focus

The character is originally shown with a wooden weapon, but this LoRA was not specifically optimized to reproduce it accurately or consistently.

I prioritized the character herself instead of spending the limited dataset capacity on learning that prop in detail.

As usual, the final result can still depend on your checkpoint, prompt, LoRA strength, CFG scale, camera angle, and generation settings.

LORA

Illustrious

by zetsubou

Download (Beta) View on CivitAI