IDK Hair Dynamics

# IDK Hair Dynamics V2

## About

Adds realistic hair physics — wind-blown strands, wet/soaked hair, floating zero-gravity effects, and light halos. Turns static hair into something alive.

PT-BR: LoRA focada no conceito 'Hair Dynamics' para modelos SDXL baseados em Illustrious. Reforca a geracao de floating hair, wet hair.

## Trigger words

### Primary triggers

```

floating hair, wet hair

```

### Supporting tags

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

```

long hair, wet, black hair, brown hair, short hair, blonde hair, very long hair, photo (medium), realistic, nude, lips, water, photorealistic, nipples

```

Also works with the V1 triggers: floating hair, zero gravity hair, windblown hair, soaked hair, wet hair, hair light halo

## Example prompts

```

masterpiece, best quality, absurdres, dynamic hair in motion, windblown flowing hair, running through field, summer dress, cinematic, <lora:IDK_hair-dynamics_V2:0.9>

```

```

masterpiece, best quality, absurdres, dynamic hair in motion, hair dramatically swirling around, passionate embrace, nude with hair as only covering, cinematic, <lora:IDK_hair-dynamics_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_hair-dynamics_V2.safetensors