IDK Bangs

詳細

ファイルをダウンロード (1)

モデル説明

# IDK_SDXL-specific-bangs — Bangs & Fringe LoRA for SDXL

## Description

All the bangs — blunt, curtain, micro, hime cut, eye-covering, and parted. SDXL tends to default to "generic fringe"; this gives you actual control over bang styles.

---

### Before we start...

Bangs: the only thing that can completely change how a person looks in 0.5 seconds.
Also the only thing that takes 6 months to regret.
This LoRA lets you try every style with zero commitment issues.

> **Disclaimer:** The dark humor above is just a joke to break the ice and does NOT reflect my actual feelings or beliefs. Just vibes. Enjoy the LoRA!

---

## Trigger Words

```
straight bangs, blunt bangs, curtain bangs, micro bangs, hime cut, bangs over eyes, parted bangs
```

## Recommended Settings

| Setting | Recommended |
|---|---|
| **Base Model** | Any SDXL checkpoint |
| **Sampler** | Euler a, DPM++ SDE Karras, DPM++ 2M Karras |
| **Steps** | 25-35 |
| **CFG Scale** | 5-8 |
| **LoRA Weight** | 0.6 - 0.85 (start at 0.7, adjust to taste) |
| **Resolution** | 1024x1024, 896x1152, 832x1216 |
| **VAE** | SDXL default / sdxl-vae-fp16-fix |

## Tips

- Start with LoRA weight around **0.7** and adjust up/down depending on how strong you want the effect.
- Combine with other IDK_ LoRAs from this series for layered results (e.g. body + hair + style).
- Works with both realistic and stylized SDXL checkpoints.
- Use the trigger words in your prompt for best activation.
- If the effect is too subtle, increase weight or repeat the trigger word.
- If the effect is too strong / distorted, lower the weight to 0.5-0.6.

## Part of the IDK Series

This LoRA is part of the **IDK LoRA collection** — a set of specialized SDXL LoRAs that can be used individually or merged together. The merged version (**IDK.safetensors**) combines all of them using hierarchical semantic merging for maximum quality.

---

*Trained on SDXL 1.0 | LoRA Rank 16 | FP16*

---

## Prompt for Batch Generation (infinite mode)

Use this prompt with dynamic wildcards `{A|B}` to generate varied showcase images. 

**Positive:**
```
portrait of a {young woman|girl|elegant woman} with {straight blunt bangs|wispy curtain bangs|micro bangs above eyebrows|hime cut with straight bangs|long bangs over eyes|soft parted bangs}, {black hair|chestnut brown hair|blonde hair|dark red hair}, {looking at viewer|slight head tilt|gazing to the side}, {soft natural lighting|studio beauty lighting|warm indoor light|backlit golden hour}, focus on hair and bangs, detailed hair strands, {close up portrait|upper body shot}, masterpiece, best quality, highly detailed
```

**Negative:**
```
(extra fingers, deformed iris, blurry, lowres, bad anatomy, jpeg artifacts, compression artifacts, noise, grainy, motion blur), (low quality, worst quality:1.2), (compression artifacts, jpeg artifacts:1.4), (blurry, out of focus:1.2), grainy, noise, text, watermark, signature, error, messy lines <lora:IDK_SDXL-isolated-studio-background:1.0>
```

このモデルで生成された画像