README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
    Pixel Background, An eye-level view of a mountain range, the mountain range
    is adorned with a vibrant shade of pink and purple. The mountains are set
    against a backdrop of a light blue sky, dotted with fluffy white clouds. In
    the foreground of the image, a field of wildflowers, a few houses, and a few
    trees are visible. The field is a vibrant green, and the houses are a
    reddish-brown color. The sky is a muted blue, with a few wispy clouds in the
    air.
  output:
    url: images/1.png
- text: >-
    Pixel Background, An animated image of a hamburger on a green field. The
    hamburger has a bun that has a lot of seeds on top of it. The bun is a light
    brown color. There are lettuce and tomato slices on the bun. There is a
    yellow cheese on the burger. The burger is sitting on a grassy field that is
    in front of a blue sky with white clouds.
  output:
    url: images/2.png
- text: >-
    Pixel Background, a silhouette of a surfer is seen riding a wave on a red
    surfboard. The surfers shadow is cast on the left side of the image, adding
    a touch of depth to the composition. The background is a vibrant orange,
    pink, and blue, with a sun setting in the upper right corner of the frame.
    The silhouette of the surfer, a palm tree casts a shadow onto the wave,
    adding depth and contrast to the scene.
  output:
    url: images/3.png
- text: >-
    Pixel Background, An eye-level pixelated image of a tree in the middle of
    the frame. The tree is the focal point of the image, with a vibrant shade of
    purple at the base and a darker shade at the top of the tree. The background
    is a combination of yellow, green, pink, and purple. There are mountains in
    the background, and the trees are outlined in shades of purple. The trees
    are standing in front of a pink sunset, and there is a small red building in
    the bottom left corner of the picture.
  output:
    url: images/4.png
- text: >-
    Pixel Background, A serene beach scene viewed from an eye-level perspective.
    The sandy shore is a warm, light tan with subtle wave patterns. The ocean
    stretches out in shades of blue and teal, meeting a gradient sky
    transitioning from orange to pink with a glowing sun setting on the horizon.
    A small wooden boat floats near the shore, and palm trees sway in the gentle
    breeze on the left.
  output:
    url: images/5.png
- text: >-
    Pixel Background: A cozy, snow-covered village with charming wooden houses
    topped with thick white roofs. Smoke rises from chimneys, blending into a
    cool blue sky speckled with falling snowflakes. In the foreground, a frozen
    pond reflects the soft glow of lanterns strung along the nearby trees.
  output:
    url: images/6.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Pixel Background
license: creativeml-openrail-m
---
![zsdvsdvsv.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/06YuYGWFZOfxsiijacHPw.png)

<Gallery />

# Model description for Pixel Background

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 & 3100 |
| Epoch                     | 17   | Save Every N Epochs       | 1     |
    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 17 [ 8bit pixel ] 

## 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-Pixel-Background-LoRA"
trigger_word = "Pixel Background"  
pipe.load_lora_weights(lora_repo)

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

## Trigger words

You should use `Pixel Background` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

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