---
license: wtfpl
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
  - flux
  - flowmatch
  - stationthis
widget:
  - text: "0__11Xx, This is a digital artwork featuring a stylized, surreal composition. At the center, a person with short, light brown hair, wearing a white jacket and black pants, stands on a grassy hill. They face away from the viewer, gazing at a vivid sunset over a coastal cityscape. The sky is a gradient of pink, orange, and purple hues, with scattered clouds and flying birds. A large, circular frame encloses the sunset, contrasting with the deep blue background. Below, palm trees and city lights are visible, adding depth. The artwork uses bold colors and a mix of realistic and abstract styles, creating a dreamlike atmosphere."
    output:
      url: samples/sample_000.jpg
instance_prompt: "0__11Xx"
training_steps: 4000
network_type: lora
library_name: ai-toolkit
---

# 0__11Xx

This LoRA model enhances digital artwork by generating stylized, surreal compositions with a focus on vibrant color gradients and intricate landscapes. It emphasizes character positioning and atmospheric effects, such as vivid sunsets and coastal cityscapes, to create emotionally evocative scenes.

**Trigger word:** `0__11Xx`

## Sample Outputs

| | |
|:---:|:---:|
| ![Sample 1](samples/sample_000.jpg) | ![Sample 2](samples/sample_001.jpg) |
| *0__11Xx, This is a digital artwork featuring a stylized, sur...* | *0__11Xx, This digital artwork depicts a person with shoulder...* |
| ![Sample 3](samples/sample_002.jpg) | ![Sample 4](samples/sample_003.jpg) |
| *0__11Xx, This is a digital illustration featuring a mysterio...* | *0__11Xx, This is a digital anime-style drawing featuring a s...* |

## 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 `0__11Xx` 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/0__11Xx")
pipe.to("cuda")

image = pipe(
    prompt="0__11Xx 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

- `0__11Xx this is a digital artwork featuring a stylized`
- `0__11Xx surreal composition. at the center`
- `0__11Xx a person with short`
- `0__11Xx light brown hair`

## Training Details

- **Base model:** black-forest-labs/FLUX.1-dev
- **Training steps:** 4000
- **Trigger word:** `0__11Xx`
- **Network:** LoRA rank 32, alpha 32
- **Optimizer:** adamw8bit, lr 1e-4
- **Precision:** float16
- **Resolution:** 512, 768, 1024 (multi-res bucketed)

## 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>