# IDK Y2k Casual Style V2
## About
LoRA focused on the 'Y2k Casual Style' concept for Illustrious-based SDXL models. It strengthens generation of crop top.
PT-BR: LoRA focada no conceito 'Y2k Casual Style' para modelos SDXL baseados em Illustrious. Reforca a geracao de crop top.
## Trigger words
### Primary triggers
```
crop top
```
### Supporting tags
Frequent thematic tags from the training set - combine them with the primary triggers to steer the concept:
```
tank top, midriff, long hair, brown hair, short hair, shorts, photo (medium), underwear, blue eyes, blonde hair, realistic, thighs, short shorts, ass
```
## Example prompts
```
masterpiece, best quality, absurdres, y2k aesthetic girl, low rise jeans and crop top, playful casual, bright colors, nostalgic, <lora:IDK_y2k-casual-style_V2:0.9>
```
```
masterpiece, best quality, absurdres, y2k aesthetic girl, baby tee and butterfly clips, seductive early 2000s vibe, bright colors, nostalgic, <lora:IDK_y2k-casual-style_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 0.7-1.0. Start at 0.9 and adjust to taste.
## Changelog V2
- New, larger and more diverse training dataset.
- 1080p preview images.
Base model: Illustrious SDXL IDN_Illustrious_V10_T)
Training pipeline: [IDK-Trainer](https://github.com/NOTcisLol/IDK-Trainer)
File: IDK_y2k-casual-style_V2.safetensors








