---
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: "maccinft"
    output:
      url: samples/sample_000.jpg
instance_prompt: "maccinft"
training_steps: 4000
network_type: lora
library_name: ai-toolkit
---

# maccinft

The maccinft LoRA model enables the generation of images in a unique custom style, characterized by vibrant colors and intricate detail. This model is ideal for artists and creators looking to infuse their work with a distinctive visual flair.

**Trigger word:** `maccinft`

## Sample Outputs

| | |
|:---:|:---:|
| ![Sample 1](samples/sample_000.jpg) | ![Sample 2](samples/sample_001.jpg) |
| *Sample 1* | *Sample 2* |
| ![Sample 3](samples/sample_002.jpg) | ![Sample 4](samples/sample_003.jpg) |
| *Sample 3* | *Sample 4* |

## 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 `maccinft` 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/maccinft")
pipe.to("cuda")

image = pipe(
    prompt="maccinft 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

- `maccinft portrait, soft lighting, detailed`
- `maccinft in a scenic environment`

## Training Details

- **Base model:** black-forest-labs/FLUX.1-dev
- **Training steps:** 4000
- **Trigger word:** `maccinft`
- **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>