---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Dls Sketch, A cartoon drawing of a woman with long brown hair. The woman has a white face with black eyes. The background is plain white. The drawing is done in black lines.'
  output:
    url: images/1.png
- text: 'Dls Sketch, A cartoon drawing of a woman with a purple tie. The background is a solid white color. The womans face is white. Her hair is black. Her eyes are purple. Her nose is black as well as her mouth is open. Her mouth is slightly open. She is wearing a pair of purple earrings. Her tie is purple.'
  output:
    url: images/2.png
- text: 'Dls Sketch, A cartoon drawing of a boy with a red coat on a white background. The boy has short brown hair and black eyes. He is wearing a black collar around his neck. He has a black belt around his waist.'
  output:
    url: images/3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Dls Art
license: creativeml-openrail-m
---

![ASCFSDVCC.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/mmQJq5_dBMqXr0w1euVi1.png)


<Gallery />

# Model description for Dls-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           | 20 & 2900 |
| Epoch                     |  25  | Save Every N Epochs       | 1    |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 24

## 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/Dls-ART"
trigger_word = "Dls-ART"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)
```

## Trigger words

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

## Download model

Weights for this model are available in Safetensors format.

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