---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'ep sketch, a medium-sized sketch of a mans face is depicted in a vibrant shade of blue. The mans eyes are a piercing blue, and he has a slight smile on his face. His hair is a dark shade of black, and his eyebrows are a lighter shade of brown. He has a black mustache and beard, and a black necklace around his neck. The background is a solid white, and the sketch is done in a simple, cartoon-like style.'
  output:
    url: images/1.png
- text: 'ep sketch, a black and white sketch of a woman with curly hair. The womans face is white and her eyes are blue. Her hair is black and wavy. She is wearing a white dress with a pink shirt underneath. Her dress has a white collar. The background is a solid white color.'
  output:
    url: images/2.png
- text: 'ep sketch, a medium-sized sketch of a mans face is drawn in a simple, cartoon-like fashion. The mans head is adorned with a blue beard and mustache, and he is wearing a pair of black framed glasses. His eyes are open, and his lips are slightly parted, as if he is smiling. His hair is a dark shade of blue, while his eyebrows are a lighter shade of black. The background is a solid white, and the sketch is done in shades of blue and yellow.'
  output:
    url: images/3.png
- text: 'ep sketch, a drawing of a woman with curly hair. The womans face is white and her mouth is open. Her hair is a vibrant shade of green. Her eyes are a piercing blue. Her eyebrows are a darker shade of brown. Her lips are a lighter shade of white. Her mouth is slightly open. She has a smile on her face. She is wearing a white shirt with a black collar around her neck. Her jacket is black. The background is a solid white.'
  output:
    url: images/4.png
- text: 'ep sketch, a detailed sketch of Elon Musk wearing a suit and tie. He has a confident smile, and his hair is styled neatly. His posture is relaxed, but there’s a hint of determination in his expression. The background is a soft gray, and the lines are smooth, with subtle shading on his face to give depth to the features. The sketch is realistic yet simplified, with focus on his charismatic personality.'
  output:
    url: images/5.png
- text: 'ep sketch, a medium-sized sketch of a sleek black car, drawn in a simple, minimalist style. The car has smooth curves and a futuristic design, with tinted windows and sharp headlights. The background is a solid white, allowing the cars details, such as its smooth body and glossy surface, to stand out. The lines are clean and sharp, with no excessive shading, focusing on the cars streamlined appearance.'
  output:
    url: images/6.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: ep sketch
license: creativeml-openrail-m
---
![zxzxzxzx.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/F5AK9bp6GjW4onpxzgZ-h.png)

<Gallery />

# Model description for Flux-Sketch-Ep-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 & 2950 |
| Epoch                     | 20   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 22

## 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-Ep-LoRA"
trigger_word = "ep sketch"  
pipe.load_lora_weights(lora_repo)

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

You should use `ep sketch` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

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