✨ Lawman girl from OtakuVS

— An unnamed employee of Lawman, a Lawson-style convenience store parody. She appears in an in-universe TV commercial, complete with the cheerful employee look you'd expect from a convenience store advertisement. It's another very short appearance, but the fake-commercial presentation gives her a fun little identity of her own.

>OtakuVS COLLECTION<

HERE<

🖼️ How I Generate My Images

🔄 UPDATED: This full breakdown covers my exact settings, prompting tricks, and how I survive with my “potato” GTX 1650 setup 😅
The article is kept current whenever my methods change, so you’ll always see my latest setup.
👉 Check it out here if you want to try the same method or copy my setup for your own gens.

🎨 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.

🧥 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 name tag keeps appearing when you do not want it:
🚫 Negative prompt: name_tag

Use the specific leaking tag instead of adding many unrelated negative tags.

⚖️ 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

🎬 YouTube screenshots with additional AI-assisted images

This final version was trained mainly from screenshots taken from the YouTube video series, with additional AI-generated images used to improve dataset variety and coverage.

The dataset was also reprocessed and curated more carefully compared to the previous version.

🎨 Improved colors and facial accuracy

The previous version was already usable, but this update improves several facial details to match her original appearance more closely.

The color balance was also adjusted by reducing the intensity of sunlight and overall brightness, resulting in colors that stay closer to the source.

👗 Better outfit accuracy and flexibility

The outfit tagging was refined to separate its details more clearly, making the default outfit more accurate while also improving control when changing clothing during generation.

This should make alternate outfits easier to prompt without as much interference from the original outfit.

🔧 Smaller and more refined final version

The LoRA file size was reduced to around half of the first version while keeping the improvements from the updated dataset.

The showcase prompts were also refined to produce more controlled and consistent results.

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