---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Microworld NFT, a miniature model of a snow-covered mountain with a red pickup truck parked on the left side of the mountain. The model is set against a stark white backdrop, creating a stark contrast to the scene. The house, adorned with a blue roof, is adorned with snow, adding a festive touch to the composition. The truck, positioned in the middle of the model, is positioned to the right of the house, adding depth to the focal point.'
  output:
    url: images/4.png
- text: 'Microworld NFT: A miniature model of a serene forest scene, with a tiny log cabin nestled between two tall evergreen trees. The ground is covered in a light dusting of moss and fallen leaves, creating a natural texture. A small, clear stream winds its way in front of the cabin, with a tiny wooden bridge crossing it. The background is a stark white, highlighting the intricate details of the forest diorama.'
  output:
    url: images/5.png
- text: 'Microworld NFT: A tiny model of a bustling street market is displayed on a white surface. The market features colorful stalls with red, yellow, and green awnings, each displaying miniature fruits, vegetables, and handcrafted goods. A few tiny figures of vendors and shoppers are scattered throughout, adding life to the scene. The backdrop is pure white, emphasizing the vibrant colors of the market.'
  output:
    url: images/6.png
- text: 'Microworld NFT, a small model of a rustic wooden house is positioned on a white surface. The house is made of a dark brown wood, with a brown roof and a brown awning on the right side. A brown horse is standing on the ground in front of the house, with its head turned towards the left side of the image. A shadow is cast on the surface behind the house. The background is a stark white, creating a stark contrast to the wood.'
  output:
    url: images/1.png
- text: 'Microworld NFT, a medium-angle view of a small, rustic-colored wooden barn sits atop a large, rectangular, square-shaped structure. The barn is adorned with a black roof, and the barns windows are adorned with white lettering. To the left of the barn, a windmill stands tall, adding a touch of warmth to the scene. The background is a stark white, creating a stark contrast to the barn and barn.'
  output:
    url: images/2.png
- text: 'Microworld NFT, a small scale model of a city is displayed on a white surface. The model is a dark gray concrete block, with two arches on the left side of the block. The building is made up of many tall buildings, with many windows and balconies. The buildings are arranged in a row, with a few cars parked on the right side. A few people are walking on the sidewalk, adding a touch of detail to the scene. The background is a stark white, creating a stark contrast to the model.'
  output:
    url: images/3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Microworld NFT
license: creativeml-openrail-m
---
![svdsxd.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/bSGGNd1YKFYE4lGgTXNe4.png)

<Gallery />

# Model description for Flux-Microworld-NFT-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 & 2460 |
| Epoch                     | 12   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 18 [ 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-Microworld-NFT-LoRA"
trigger_word = "Microworld NFT"  
pipe.load_lora_weights(lora_repo)

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

You should use `Microworld NFT` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

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