đ Mean & Towering Dragon LoRA for Flux
This LoRA model is fine - tuned for Flux.1 - dev, aiming to generate meaner, more menacing, and physically larger dragons that tower over people or landscapes. It effectively solves the problem of capturing scale and attitude in Flux.1 - dev.
đ Quick Start
Activation
No trigger word is needed. You can use prompts like:
- massive menacing red dragon towering over a tiny knight
- colossal black dragon atop a mountain peak
Recommended Epochs
Use epochs 12 - 15 (files provided). It's recommended to start with 14 or 15.
LoRA Strength
Set the strength of both Clip and Model between 0.8 and 1.0.
Resolution
Vertical resolutions (e.g., 768x1344) are recommended to better present the scale.
⨠Features
This LoRA is specifically fine - tuned for Flux.1 - dev to generate dragons with the following characteristics:
- Meaner and More Menacing: The generated dragons have a fierce and intimidating appearance.
- Physically Larger: They tower over people or landscapes, effectively capturing the sense of scale.
đĻ Installation
The README does not provide installation steps, so this section is skipped.
đģ Usage Examples
Basic Usage
The basic way to use this LoRA is to input prompts as described above without a trigger word. For example:
massive menacing red dragon towering over a tiny knight
Advanced Usage
You can adjust the LoRA strength, epochs, and resolution according to your specific needs. For instance, if you want a more prominent dragon effect, you can set the LoRA strength closer to 1.0 and choose an appropriate epoch number.
đ Documentation
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.
Here are some sample captions:
1girl, long hair, dress, hair ornament, standing, white hair, frills, indoors, from behind, red dress, monster, sharp teeth, dragon
Key Training Parameters
| Property |
Details |
| 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 |
đ§ Technical Details
The README does not provide in - depth technical details, so this section is skipped.
đ License
This model is released under the MIT License. You can use, modify, and distribute it freely, and it's appreciated if you give credit.
Download model
The weights for this model are available in Safetensors format. You can Download them in the Files & versions tab.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)