---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Automotive X1, Captured at eye-level on a dark night, a yellow jeep is parked on a dirt road. The jeeps front bumper is adorned with a black grille, and a yellow headlight. A green inflatable raft is on top of the jeep, with the word "Tropor" written in white on the side. The front of the vehicle is covered in dirt, and there are rocks and grass on the ground.'
  output:
    url: images/4.png
- text: 'Automotive X1: A bright yellow jeep with oversized tires is parked in a vast sand dune. The vehicles sides are decorated with black tribal patterns, and its spare tire is mounted on the rear. A surfboard is strapped to the roof rack, and the suns golden rays cast long shadows across the desert landscape. The sky is cloudless, and the scene radiates warmth and adventure.'
  output:
    url: images/5.png
- text: 'Automotive X1, a sleek matte black SUV with chrome accents is parked on a snowy mountain pass. The vehicles roof rack is loaded with camping gear, including a red tent and a green duffle bag. The tires are thick and rugged, perfect for icy conditions. Behind the SUV, tall pine trees dusted with snow frame the scene. The overcast sky is heavy with gray clouds, casting a serene, wintry mood over the image.'
  output:
    url: images/6.png
- text: 'Automotive X1, a vibrant orange jeep is parked against a gray backdrop. The jeeps body is adorned with the words "Drive the Globe" in bold white lettering, and a graphic of an X in a white cross on the side of the jeep. A bicycle is balanced on top of it, adding a pop of color to the otherwise monochromatic image.'
  output:
    url: images/1.png
- text: 'Automotive X1, a blue jeep is parked in a desert-like area. The jeeps body is a vibrant shade of blue, with a black bumper and black tires. The front grill is adorned with three yellow lights, and the headlights of the jeep are turned on. The tires are thick and black, and are mounted on the side of the truck. The truck is parked on a dirt-covered ground, and in the background, a mountain range can be seen. The sky is a light blue, and a few wispy clouds are visible.'
  output:
    url: images/2.png
- text: 'Automotive X1, Captured at eye-level on a low-angle shot, a detailed model of a military vehicle, painted in shades of blue and black. The vehicle is adorned with a yellow emblem, adding a touch of rustic charm to its appearance. The background is a stark black, creating a stark contrast to the vehicles vibrant colors. The scene is set in a desert-like setting, with a dark sky in the background.'
  output:
    url: images/3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Automotive X1
license: creativeml-openrail-m
---
![zsvzsdfv.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/K0kGY5FRPH_bpnxNzc5LX.png)

<Gallery />

# Model description for Flux-Automotive-X1-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           | 25 & 2900 |
| Epoch                     | 15   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 20
    
## 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-Automotive-X1-LoRA"
trigger_word = "Automotive X1"  
pipe.load_lora_weights(lora_repo)

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

You should use `Automotive X1` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Flux-Automotive-X1-LoRA/tree/main) them in the Files & versions tab.