---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Qc-Sketch, A black and white sketch of a mans face is shown. He is wearing a black baseball cap with a white letter A on the front of it. He has a black beard and glasses on his face. His mouth is slightly open and he is speaking. His ears are sticking out of the cap. His eyes are blue and he has a slight smile on his lips.'
  output:
    url: images/1.png
- text: 'Qc-Sketch, An eye-level sketch of a mans face is depicted in a stark white background. The mans eyes are covered with a red tint, adding a pop of color to the otherwise monochromatic image. The hat he is wearing is adorned with the letters AS on the side of the hat, and a black band around the brim. His mouth is slightly open, as if he is about to go to the right of the image. He is wearing a black collar around his neck, with a black belt loop looped around the collar. His ears are slender, and he has a slight smile on his face. The background is a solid white, creating a stark contrast to the sketch.'
  output:
    url: images/2.png
- text: 'Qc-Sketch, A medium-sized portrait of a baseball player is depicted in a vibrant blue and white color scheme. The players head is adorned with a blue baseball cap, adorned with an orange star, adding a pop of color to the scene. He is wearing a white baseball uniform, with a black collar and a blue t-shirt underneath. His mouth is slightly open, as if he is about to go to the right. His eyes are open, and he is smiling. His hair is neatly trimmed, and his beard is neatly neatly trimmed. The background is a stark white, creating a stark contrast to the portrait.'
  output:
    url: images/3.png
- text: 'Qc-Sketch, A monochromatic sketch of a young woman with curly hair tied in a bun. She is wearing round glasses and a scarf around her neck. Her lips are slightly parted, revealing a hint of her teeth. The background is a simple white, and her eyes convey a sense of curiosity. Her sweater has faint stripes, adding subtle texture to the image.'
  output:
    url: images/4.png
- text: 'Qc-Sketch, A colorful sketch of a musician playing a saxophone. The musician is wearing a purple hat tilted to one side and a bright green scarf. His eyes are closed, and his cheeks are puffed as he blows into the instrument. Musical notes and swirls of blue are depicted around him against a white background.'
  output:
    url: images/5.png
- text: 'Qc-Sketch, A rugged sketch of a mountain climber at the summit. The climber is wearing a heavy coat with a hood, and his backpack is outlined with bold strokes. He is holding a flagpole with a triangular flag flapping in the wind. The background is minimal, with faint outlines of mountains below.'
  output:
    url: images/6.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Qc-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
---
![xxxxxxxxxxxxxxxxxxx.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/Jz6tu97RBtvL_SZTnEgJ1.png)

<Gallery />
# Model description for Qc-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/Qc-Sketch"
trigger_word = "Qc-Sketch"  
pipe.load_lora_weights(lora_repo)

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

## Trigger words

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

## Download model

Weights for this model are available in Safetensors format.

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