---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Qw-Sketch, An eye-level sketch of a young Asian man with dark brown hair. His eyes are squinted and his lips are slightly parted. His head is tilted slightly to the right, and he has a slight smile on his lips. His hair is pulled back in a ponytail, and his bangs are slicked back. He is wearing a collared button-down shirt with a collar and a green tie around his neck. The background is a deep blue, and there are green rays of light shining down on the mans face.'
  output:
    url: images/1.png
- text: 'Qw-Sketch, An eye-level painting of a mans face is depicted in a vibrant orange background. The mans eyes are a piercing blue, while his hair is a darker shade of brown. His eyebrows are a light brown, and he has a slight smile on his face. He is wearing a collared button-down shirt with a collar and a collar around his neck. His hair is cut in a bob, adding a pop of color to the scene. He is wearing a black collar with a silver chain hanging from it. His left ear is visible, and his right ear is slightly open. His eyes are slightly open, as if he is looking to the right. His mouth is slightly closed, and there are a few small white lines on the top of his head, adding depth to the image.'
  output:
    url: images/2.png
- text: 'Qw-Sketch, An abstract painting of a woman with long dark brown hair. The womans face is painted in a vibrant pink shade. Her eyes are a piercing yellow. Her eyebrows are a darker shade of brown. Her lips are a lighter pink. She is wearing a black dress with a silver necklace around her neck. Her earrings are dangling from her ears. The background is a vibrant red with yellow and blue lines.'
  output:
    url: images/3.png
- text: 'Qw-Sketch, An eye-level sketch of a mans face is depicted in a vibrant pink background. The mans eyes are squinted, and he has a mustache and goatee. His hair is a dark shade of purple, and his eyebrows are a lighter shade of brown. His mouth is slightly open, with a smile on its face. He is wearing a collared button-down shirt with a collar and long sleeves. The shirt is adorned with black lines, adding a pop of color to the scene'
  output:
    url: images/4.png
- text: 'Qw-Sketch, An eye-level sketch of a young man with curly dark brown hair and glasses. His eyes are a calm gray, and he has a soft smirk on his lips. His face is framed by a navy-blue hoodie, slightly pulled over his head, and a silver pendant is visible around his neck. The background is a misty gray with faint white lines radiating from the figure, suggesting a subtle glow.'
  output:
    url: images/5.png
- text: 'Qw-Sketch, An abstract painting of a man with spiky, bright teal hair. His face is painted in vibrant shades of orange and yellow, with bold streaks of white and black crossing his cheeks. His eyes are large and glowing white, creating a dramatic effect. He is wearing a black leather jacket adorned with metallic silver studs. The background is a chaotic mix of red, blue, and green paint splatters, adding energy to the composition.'
  output:
    url: images/6.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Qw-Sketch
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
![adad.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/ARfDVouJhpfFAfkXvB_qQ.png)

<Gallery />

# Model description for Qw-Sketch

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           | 16 & 2230 |
| Epoch                     |  17   | Save Every N Epochs       | 1    |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 18

## 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/Qw-Sketch"
trigger_word = "Qw-Sketch"  
pipe.load_lora_weights(lora_repo)

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


## Trigger words

You should use `Qw-Sketch` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

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