---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'LD Art, A black and white drawing of a man sitting on a chair. The man is wearing a short sleeve button down shirt with a black collar. His pants are gray with black stripes on them. He has a black hat on his head. His eyes are closed and his mouth is slightly open. His right hand is resting on his hip. His left hand is raised in the air. The wall behind the man is white.'
  output:
    url: images/1.png
- text: 'LD Art, A cartoon drawing of a woman in a gray shirt and black shorts. The woman has long black hair and is standing in front of a red background. There are black mountains behind the woman. The background is a light beige color.'
  output:
    url: images/2.png
- text: 'LD Art, A cartoon drawing of a woman in a black and white shirt and gray pants. The woman has a black hat on her head and a black belt on her waist. The background is a light beige color.'
  output:
    url: images/3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: LD Art
license: creativeml-openrail-m
---
![FSDfsdf.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/DY8BsVYR_J3FryFBwfhx2.png)

<Gallery />

# Model description for Ld-Art

Image Processing Parameters 

| Parameter                 | Value  | Parameter                 | Value  |
|---------------------------|--------|---------------------------|--------|
| LR Scheduler              | constant | Noise Offset              | 0.03   |
| Optimizer                 | AdamW  | Multires Noise Discount   | 0.1    |
| Network Dim               | 64     | Multires Noise Iterations | 10     |
| Network Alpha             | 32     | Repeat & Steps           | 29 & 2970 |
| Epoch                     |  17   | Save Every N Epochs       | 1    |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 28

## Best Dimensions & Inference

| **Dimensions** | **Aspect Ratio** | **Recommendation**       |
|-----------------|------------------|---------------------------|
| 1280 x 832      | 3:2              | Best                     |
| 1024 x 1024     | 1:1              | Default                  |

### Inference Range

- **Recommended Inference Steps:** 30–35

## Setting Up
```python
import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Ld-Art"
trigger_word = "LD Art"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)
```
## Trigger words

You should use `LD Art` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Ld-Art/tree/main) them in the Files & versions tab.