---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Sketch Scribble, A black and white portrait of a mans face. The man has a dark beard and mustache. His eyes are open and he has a serious look on his face. His head is covered in black lines. Behind the mans head is a white background with black lines forming a starburst.'
  output:
    url: images/4.png
- text: 'Sketch Scribble: A black and white pencil sketch of a soaring eagle. The eagles wings are outstretched, drawn with long, bold strokes to emphasize their grandeur. Its sharp beak and focused eyes are detailed with fine scribbles, while its feathers are textured with crosshatched lines. Below the eagle, faint, swirling pencil marks suggest clouds, contrasting with the white background.'
  output:
    url: images/5.png
- text: 'Sketch Scribble: A black and white pencil sketch of a majestic lions face. The lions mane is scribbled with bold, flowing strokes, giving it a wild and textured look. His eyes are intense and piercing, with a sharp contrast between the dark pupils and the lighter fur. His nose and mouth are shaded with finer lines, and his whiskers are drawn as faint, delicate scribbles. The background is solid white, with chaotic pencil marks suggesting the savanna.'
  output:
    url: images/6.png
- text: 'Sketch Scribble, A black and white pencil sketch of a womans face. The womans head is facing the left side of the image. Her eyes are open and her lips are slightly parted. Her hair is long and wavy. Her eyebrows are a darker shade of brown. Her nose is a lighter shade of gray. Her mouth is slightly open and has a slight smile on it. The background is a solid white.'
  output:
    url: images/1.png
- text: 'Sketch Scribble, A black and white pencil sketch of a mans face. The mans eyes are squinted, and his mouth is slightly open. His hair is a mix of black and gray, and he has a thick beard and mustache. His eyebrows and mustache are a darker shade of gray, while his lips are a lighter shade of brown. The background is a solid white, and the sketch is done in black ink.'
  output:
    url: images/2.png
- text: 'Sketch Scribble, A black and white pencil sketch of a mans face. The mans head is covered in black lines, creating a striking contrast against the white background. His eyes are a piercing blue, and his mouth is slightly open. His eyebrows are a darker shade of black, adding a touch of contrast to his face. His hair is a mix of black and gray, adding texture to the sketch. He has a serious expression on his face, with a slight smile.'
  output:
    url: images/3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Sketch Scribble
license: apache-2.0
---
![zdvdfvzfdv.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/r9jUP44WHr63K6gVgNkzx.png)

<Gallery />

# Model description for Flux-Sketch-Scribble-LoRA

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           | 21 & 2790 |
| Epoch                     | 16   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 20
    
## 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/Flux-Sketch-Scribble-LoRA"
trigger_word = "Sketch Scribble"  
pipe.load_lora_weights(lora_repo)

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

You should use `Sketch Scribble` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

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