Flux Mexican C Punk Lo R A

Introduction

Flux-Mexican-CPunk-LoRA is a text-to-image model designed to generate images with a "Mexican Cyberpunk" theme. It utilizes the Diffusers library and is enhanced through LoRA (Low-Rank Adaptation) techniques.

Architecture

The model is based on the "black-forest-labs/FLUX.1-dev" architecture, incorporating DiffusionPipeline with LoRA weights. It optimizes using the AdamW optimizer and employs a constant learning rate scheduler.

Training

The model was trained with 14 images using the following parameters:

• LR Scheduler: constant
• Optimizer: AdamW
• Network Dimensions: 64
• Epochs: 15
• Inference Steps: Recommended between 30–35

Guide: Running Locally

To run the model locally, follow these steps:

1. Install Dependencies: Ensure Python and PyTorch are installed. Install the Diffusers package via pip.

   pip install diffusers
   

2. Load the Model:

   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-Mexican-CPunk-LoRA"
   pipe.load_lora_weights(lora_repo)
   
   device = torch.device("cuda")
   pipe.to(device)
   

3. Generate Images: Use the trigger word "Mexican Cyberpunk" to produce images.

   prompt = "Mexican Cyberpunk"
   output = pipe(prompt)
   

For optimal performance, consider using cloud GPUs such as those provided by AWS, Google Cloud, or Azure.

License

The model is released under the CreativeML OpenRAIL-M license, which allows for open and free usage with certain conditions.