Flux Xmas Isometric Kit Lo R A

Introduction

The Flux-Xmas-Isometric-Kit-LoRA is a text-to-image model designed to generate 3D isometric Christmas-themed images. Utilizing the diffusion model and LoRA (Low-Rank Adaptation), it is optimized for creating festive graphics based on textual descriptions.

Architecture

The model is based on the diffusion pipeline and operates using the LoRA technique. It integrates with the "black-forest-labs/FLUX.1-dev" base model and uses specific parameters such as AdamW optimizer, multi-resolution noise, and constant learning rate scheduler to enhance image generation.

Training

The model was trained using 14 images, configured with parameters like a network dimension of 64 and an alpha of 32. The training involved repeating steps over 2100 iterations across 14 epochs, with a noise offset of 0.03 and a multi-resolution noise discount of 0.1.

Guide: Running Locally

1. Setup Environment: Ensure you have Python and PyTorch installed.
2. Import Required Libraries:

   import torch
   from pipelines import DiffusionPipeline
   

3. Load Base Model:

   base_model = "black-forest-labs/FLUX.1-dev"
   pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
   

4. Load LoRA Weights:

   lora_repo = "strangerzonehf/Flux-Xmas-Isometric-Kit-LoRA"
   trigger_word = "Xmas Isometric Kit"  
   pipe.load_lora_weights(lora_repo)
   

5. Setup Device:

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

6. Recommended Hardware: Utilize cloud GPUs from providers like AWS, Google Cloud, or Azure for optimal performance.

License

The model is licensed under creativeml-openrail-m, which allows for open use with some restrictions as defined by the license terms.