---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'C7 Sketch, A medium-sized sketch of a womans face is depicted in a close-up fashion. Her eyes are wide open, and her lips are slightly parted. Her hair is long and cascades over her shoulders, framing her face. She is wearing a long-sleeved shirt with a collar around the neck. The shirt is a vibrant orange, and the background is a brownish-brown color.'
  output:
    url: images/4.png
- text: 'C7 Sketch, a medium-sized portrait of a mans face is depicted in vibrant orange tones, set against a deep navy blue backdrop. The man has short, spiked hair highlighted with streaks of yellow, adding contrast to the composition. His eyebrows are thick and black, his eyes are half-closed, and his lips are slightly pursed. He is wearing a white turtleneck sweater with intricate gray patterns, creating a balance between simplicity and detail.'
  output:
    url: images/5.png
- text: 'C7 Sketch: A medium-sized close-up sketch of a mans face is drawn in dark green tones. He has thick, bushy eyebrows and a neatly trimmed goatee. His hair is styled in a messy, windswept fashion, and he is wearing a high-neck leather jacket in a lighter shade of green. His lips are slightly parted, and his eyes are shaded with hints of gray, giving him a mysterious aura. The background is a soft beige with faint green accents.'
  output:
    url: images/6.png
- text: 'C7 Sketch, a medium-sized portrait of a mans face is depicted in a vibrant purple hue. The mans head is adorned with a black curly wig, adding a pop of color to the otherwise monochromatic image. His eyes are adorned with small black dots, adding depth to the composition. His lips, mustache, and earrings are a darker shade of purple, while his shirt is a lighter shade of pink. The backdrop is a light blue, creating a stark contrast to the mans features.'
  output:
    url: images/1.png
- text: 'C7 Sketch, A medium-sized cartoon drawing of a man with long, wavy hair, a red pinstripe suit jacket, and a gray tie. The mans face is adorned with a red collar, and the jacket has three black buttons on the right side of the jacket. His eyes are squinted, and his lips are slightly parted. His hair is a vibrant shade of red, adding a pop of color to the otherwise monochromatic image'
  output:
    url: images/2.png
- text: 'C7 Sketch, A medium-sized sketch of a womans face is depicted in a vibrant shade of red against a dark brown background. The womans head is tilted slightly to the left, her eyes are slightly open, and her lips are slightly parted. Her hair is pulled back, cascading down to her right side. She has long, dark brown hair that is pulled up in a ponytail, adding a pop of color to her face. Her upper body is adorned with a low-sleeved shirt that is draped over her right shoulder. Her left ear is encased in a pair of silver earrings. Her eyes are closed, and she has a slight smile on her lips.'
  output:
    url: images/3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: C7 Sketch
license: creativeml-openrail-m
---
![aaaaaaaa.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/_JqlskuFdIpjulnJwq4HJ.png)

<Gallery />

# Model description for Flux-C7-Sketch-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           | 20 & 2400 |
| Epoch                     | 15   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 19 [ Flat HD ]

## 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-C7-Sketch-LoRA"
trigger_word = "C7 Sketch"  
pipe.load_lora_weights(lora_repo)

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

You should use `C7 Sketch` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Flux-C7-Sketch-LoRA/tree/main) them in the Files & versions tab.