---
license: wtfpl
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
tags:
  - text-to-image
  - lora
  - diffusers
  - flux
  - stationthis
library_name: diffusers
---

# b0throps

This LoRA model generates digital anime-style illustrations of young female characters, emphasizing unique features like light brown braided hair and striking red eyes. The characters are styled in edgy, tattered outfits, including black crop tops and witch hats, enhancing their playful yet mysterious appearance.

**Trigger word:** `b0throps`

## Sample Outputs

| | |
|:---:|:---:|
| ![Sample 1](samples/sample_000.jpg) | ![Sample 2](samples/sample_001.jpg) |
| *This digital anime-style drawing features a young female cha...* | *This is a digital anime-style illustration featuring a young...* |
| ![Sample 3](samples/sample_002.jpg) | ![Sample 4](samples/sample_003.jpg) |
| *This is a vibrant digital illustration in an anime style, re...* | *This digital illustration features a fantasy character named...* |

## Usage

### ComfyUI

1. Download the `.safetensors` file from the Files tab
2. Place in `ComfyUI/models/loras/`
3. Use the **Load LoRA** node with strength `0.8-1.0`
4. Include `b0throps` in your prompt

### Diffusers

```python
import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    torch_dtype=torch.bfloat16
)
pipe.load_lora_weights("ms2stationthis/b0throps")
pipe.to("cuda")

image = pipe(
    prompt="b0throps portrait, soft lighting, detailed",
    guidance_scale=3.5-4.0,
    num_inference_steps=20-30,
    generator=torch.Generator("cuda").manual_seed(42)
).images[0]

image.save("output.png")
```

## Recommended Settings

| Parameter | Value |
|-----------|-------|
| LoRA Strength | 0.8-1.0 |
| Guidance Scale | 3.5-4.0 |
| Inference Steps | 20-30 |
| Resolution | 1024x1024 |

## Example Prompts

- `b0throps wearing a black`
- `b0throps exposing her midriff. she has red eyes`
- `b0throps pale skin`
- `b0throps and is dressed in a short`

## Training Details

- **Base model:** black-forest-labs/FLUX.1-dev
- **Training steps:** 4000
- **Trigger word:** `b0throps`
- **Resolution:** 512, 768, 1024 (multi-res)
- **Network:** LoRA rank 16

## About

Trained using [StationThis](https://miladystation2.net) — an AI creative platform powered by $MS2. Train your own LoRAs via [@stationthisbot](https://t.me/stationthisbot) on Telegram.

---

<sub>Generated by StationThis Training Pipeline</sub>