# IDK Mesomorph Body V2
## About
Athletic and muscular body types — defined abs, broad shoulders, V-taper, and toned proportions. Brings anatomical detail that SDXL base often smooths over.
PT-BR: LoRA focada no conceito 'Mesomorph Body' para modelos SDXL baseados em Illustrious. Reforca a geracao de abs, muscular.
## Trigger words
### Primary triggers
```
abs, muscular, athletic, defined muscle, abs, broad shoulders, v shape, fit, toned body
```
### Supporting tags
Frequent thematic tags from the training set - combine them with the primary triggers to steer the concept:
```
muscular male, male focus, nipples, pectorals, bara, realistic, short hair, nude, photo (medium), large pectorals, completely nude, black hair, thighs, penis
```
Also works with the V1 triggers: athletic, muscular, defined muscle, abs, broad shoulders, v shape, fit, toned body
## Example prompts
```
masterpiece, best quality, absurdres, toned mesomorph athletic female, muscular yet feminine physique, sporty activewear, gym aesthetic, dynamic lighting, confident pose, <lora:IDK_mesomorph-body_V2:0.9>
```
```
masterpiece, best quality, absurdres, toned mesomorph athletic female, strong defined abs and curves, nude flexing powerfully, fitness aesthetic, dynamic lighting, seductive stretch, <lora:IDK_mesomorph-body_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_mesomorph-body_V2.safetensors