---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'smiley portrait, captured at eye-level, a close-up portrait of a young man with dark brown curly hair, smiling and giving a pose into the camera. He is wearing a blue, white, and orange soccer jersey, adorned with a patch that reads "LORD HOME BLAND STICK RLC" in white letters. The backdrop is a vibrant orange, adding a pop of color to the scene.'
  output:
    url: images/1.png
- text: 'smiley portrait, a close-up shot of a woman with long brown hair and a green headband on her head. She is smiling, her eyes are closed, her mouth is slightly open, her teeth are white, and her lips are a vibrant shade of red. The background is blurred, with a hill in the distance. The sky is a clear blue.'
  output:
    url: images/2.png
- text: 'smiley portrait, captured from a high-angle, eye-level perspective, a young woman with blonde hair, wearing a pink, blue, and orange striped sweater, is smiling and giving a pose into the camera. She is wearing a ring on her nose, adding a pop of color to her face. Her lips are painted pink, her teeth are white, and her fingernails are painted a light pink shade. Her hands are positioned in front of her face, adding texture to the composition. The background is a stark white, creating a stark contrast to the womans outfit.'
  output:
    url: images/3.png
- text: 'smiley portrait, a young Asian woman with dark brown hair, wearing a gray jacket with a red, blue, and green accents. She is wearing a green, maroon, and yellow knitted scarf around her neck. The jacket has two black buttons on the left side of the jacket. The backdrop is a light gray wall.'
  output:
    url: images/4.png
- text: '    Smiley Portrait, captured from a close-up perspective, a young man with short blonde hair is smiling broadly into the camera. He is wearing a navy blue turtleneck sweater with a silver watch on his wrist, which is slightly visible as he rests his chin on his hand. The background is a vibrant green, enhancing the freshness of the scene.'
  output:
    url: images/5.png
- text: 'Smiley Portrait, captured at eye-level, a young man with dark brown wavy hair and stubble is smiling warmly into the camera. He is wearing a light gray hoodie layered under a black leather jacket. His hands are tucked into his pockets, and a silver ring is visible on his index finger. The background is a vibrant blue wall with a few white graffiti patterns.'
  output:
    url: images/6.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: smiley portrait
license: creativeml-openrail-m
---
![dasda.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/gQrXNJ6suHvu76N8SjkKi.png)

<Gallery />

# **Model description for Flux-Smiley-Portrait-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           | 28 & 3880 |
| Epoch                     | 20   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 45

## Best Dimensions & Inference

| **Dimensions** | **Aspect Ratio** | **Recommendation**       |
|-----------------|------------------|---------------------------|
| 1280 x 832      | 3:1              | Compatible                     |
| 1024 x 1024     | 1:1              | Default                  |


## 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-Smiley-Portrait-LoRA"
trigger_word = "smiley portrait"  
pipe.load_lora_weights(lora_repo)

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

You should use `smiley portrait` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

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