IDK Body type Pear Silhouette

세부 정보

파일 다운로드 (1)

모델 설명

# IDK Pear Female Silhouette V2

## About

Renders pear body shapes with accuracy — wider hips, heavier lower body, and proper proportions. A body type the base model often ignores entirely.

PT-BR: LoRA focada no conceito 'Pear Female Silhouette' para modelos SDXL baseados em Illustrious. Reforca a geracao de small breasts.

## Trigger words

### Primary triggers

```

small breasts, very wide hips, pear shaped, bottom heavy, wide pelvis

```

### Supporting tags

Frequent thematic tags from the training set - combine them with the primary triggers to steer the concept:

```

long hair, nipples, short hair, nude, underwear, panties, red eyes, pussy, blue eyes, blonde hair, brown hair, twintails, black hair, brown eyes

```

Also works with the V1 triggers: very wide hips, pear shaped, bottom heavy, wide pelvis

## Example prompts

```

masterpiece, best quality, absurdres, pear shaped beautiful woman, wide hips and thick thighs, flowy skirt, casual summer look, soft lighting, <lora:IDK_pear-female-silhouette_V2:0.9>

```

```

masterpiece, best quality, absurdres, pear shaped beautiful woman, full bottom heavy figure, nude from behind emphasizing curves, sensual bedroom pose, soft lighting, <lora:IDK_pear-female-silhouette_V2:0.9>

```

## Preview generation settings

| Setting | Value |

| --- | --- |

| Checkpoint | IDN_Illustrious_V10_T |

| Size | 1280x720 + hires 1.5x RealESRGAN 4x+) = 1920x1080 |

| Sampler | Euler a |

| Steps | 28 (+14 hires) |

| CFG scale | 5.5 |

| Denoising strength | 0.4 |

| Seeds | 1000-1009 |

Negative prompt: worst quality, low quality, bad anatomy, bad hands, extra digits, fewer digits, missing fingers, jpeg artifacts, signature, watermark, username, blurry, lowres, bad proportions, deformed, mutated

## Recommended weight

Use 0.8-1.1. This file is a V1+V2 merge (rank concatenation), which slightly dilutes each source - it tolerates and often benefits from weights a bit above 1.0.

## Changelog V2

- New, larger and more diverse training dataset.

- 1080p preview images.

- Merged with the V1 LoRA, so V1 behavior is preserved.

Base model: Illustrious SDXL IDN_Illustrious_V10_T)

Training pipeline: [IDK-Trainer](https://github.com/NOTcisLol/IDK-Trainer)

File: IDK_pear-female-silhouette_V2.safetensors

이 모델로 만든 이미지