Mean & Towering Dragon LoRA for Flux

Mean & Towering Dragon LoRA for Flux.1-dev

Model Description

This LoRA is fine-tuned for Flux.1-dev to generate meaner, more menacing, and physically larger dragons, towering over people or landscapes. It addresses the challenge of capturing scale and attitude in Flux.1-dev.

Caption style

A photo-realistic shoot from a profile camera angle about a young girl with long, flowing blonde hair standing in front of a large, menacing dragon. the girl, who appears to be in her early twenties, is facing away from the camera, with her back to the viewer. she is wearing a red dress with ruffled sleeves, and her hair is styled in a braid. the dragon, with its sharp teeth and orange scales, has a menacing expression, and its eyes are focused intently on the girl. the background is blurred, with rocks and greenery visible, and the lighting is dramatic, casting shadows on the dragon's face and body. the overall mood is dark and moody, with a focus on the character and the dragon.

1girl, long hair, dress, hair ornament, standing, white hair, frills, indoors, from behind, red dress, monster, sharp teeth, dragon

Usage

1. Activation: No trigger word needed. Use prompts like:

massive menacing red dragon towering over a tiny knight
colossal black dragon atop a mountain peak

2. Recommended Epochs: Use epochs 12-15 (files provided). Start with 14 or 15.

3. LoRA Strength: Clip & Model, Set between 0.8 and 1.0.

4. Resolution: Vertical resolutions (e.g., 768x1344) recommended for scale.

Key Training Parameters

| Parameter | Value |

|---------------------|------------------------|

| Engine | kohya |

| Epochs | 17 |

| Num Repeats | 6 |

| Steps | 1887 |

| Resolution | 1024 |

| Unet LR | 0.00020 |

| LR Scheduler | cosine_with_restarts |

| Optimizer | AdamW8bit |

| Network Dim (Rank) | 64 |

| Network Alpha | 32 |

License

Released under the MIT License. Use, modify, and distribute freely with credit appreciated.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.