README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
    Qd Sketch, An abstract painting of a woman in a green t-shirt and black
    pants. The woman is facing the left side of the frame, her left hand is
    covering her face with her right hand. Her right hand is positioned in front
    of her face. Her hair is a dark shade of black, and her eyes are a light
    brown. Her lips are a darker shade of brown. The background is a peach
    color, and the womans shirt is a vibrant green.
  output:
    url: images/1.png
- text: >-
    Qd Sketch, An animated image of a woman with long black hair, a white shirt,
    and a black skirt. The woman is standing in front of a wall that has brown
    stripes on it. There is a white line running across the womans right side of
    the image. The shadow of the woman is on the wall behind the woman.
  output:
    url: images/2.png
- text: >-
    Qd Sketch, A medium-sized painting of a womans face is depicted in a stark
    contrast of red and white. The womans head is angled towards the left side
    of the frame, her eyes are wide open, and her lips are pursed. Her hair is a
    dark shade of blue, with a few wispy bangs protruding from the top of her
    head. She is wearing a white sleeveless shirt with a red collar and a red
    line running down the center of her chest. The shirt has a white collar with
    three red circles on it. The background is a vibrant red, creating a
    striking contrast with the womans features.
  output:
    url: images/3.png
- text: >-
    Qd Sketch, A medium-sized painting of a woman in a red hooded sweatshirt
    with a black collar and a black belt around her waist is seen on a bright
    yellow background. The woman is holding a white tray with a straw and a
    white cup with yellow writing on it, both of which have the letters "M" and
    "W" written on them. Her eyes are closed and her lips are slightly parted.
    Her hair is a light brown color and she has bangs. She has a serious look on
    her face.
  output:
    url: images/4.png
- text: >-
    Qd Sketch, An abstract painting of a woman wearing a long yellow dress with
    white floral patterns. She is seated on a wooden chair, her head slightly
    tilted to the right, with her left hand resting on her lap. Her short black
    hair is neatly styled, and her eyes are closed as if in thought. The
    background consists of swirling shades of orange and pink, giving the image
    a dreamlike atmosphere.
  output:
    url: images/5.png
- text: >-
    Qd Sketch, An abstract image of a woman in a white sundress with pink polka
    dots, standing on the edge of a wooden dock by a lake. The water reflects
    the soft hues of a sunset, ranging from orange to purple. Her short black
    bob haircut sways slightly in the breeze, and she is looking down at her
    bare feet. In the background, tall trees surround the lake, their dark green
    leaves creating a contrasting frame.
  output:
    url: images/6.png
instance_prompt: Qd-Sketch
license: other
---

<pre align="center">
  
 ______  ______   __       __  __   ______   ______   __  __   ______       __   ______    
/\  == \/\  __ \ /\ \     /\ \_\ \ /\  ___\ /\  == \ /\ \/\ \ /\___  \     /\ \ /\  __ \   
\ \  _-/\ \ \/\ \\ \ \____\ \____ \\ \ \____\ \  __< \ \ \_\ \\/_/  /__    \ \ \\ \ \/\ \  
 \ \_\   \ \_____\\ \_____\\/\_____\\ \_____\\ \_\ \_\\ \_____\ /\_____\    \ \_\\ \_____\ 
  \/_/    \/_____/ \/_____/ \/_____/ \/_____/ \/_/ /_/ \/_____/ \/_____/     \/_/ \/_____/ 
                                                                                                                                                                                                  
</pre>

# sketch-painterly

<Gallery />

---

## Model description for sketch-painterly

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           | 26 & 3830 |
| Epoch                     |  20   | Save Every N Epochs       | 1    |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 23

## 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 = "Polycruz9/sketch-painterly"
trigger_word = "Qd-Sketch"  
pipe.load_lora_weights(lora_repo)

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

## Trigger words

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

## Download model

Weights for this model are available in Safetensors format.

[Download](/Polycruz9/sketch-painterly/tree/main) them in the Files & versions tab.