maxxd4240_minimalist Pastel

Introduction

The GLIF-LORADEX-TRAINER model, specifically the MAXXD4240_MINIMALISTPASTEL version, is a text-to-image model trained under the Glif Loradex program. It utilizes AI Toolkit by Ostris for its training, providing outputs in a minimalist pastel style.

Architecture

This model is based on the FLUX.1-dev architecture by Black Forest Labs. It leverages technologies like diffusers and LoRA (Low-Rank Adaptation of Large Models) to generate images from textual prompts.

Training

The model was fine-tuned on the FLUX.1-dev base model using specific prompts and styles, particularly focusing on the minimalist pastel aesthetic. It employs tags like 'text-to-image' and 'template:sd-lora' to guide its training process.

Guide: Running Locally

1. Download the Model: Obtain the weights in Safetensors format from the Files & versions tab on the model's Hugging Face page.
2. Set Up Environment: Ensure you have the required dependencies, including diffusers and Hugging Face libraries.
3. Run the Model: Use a Python script to load the model and input your text prompts. Incorporate the trigger word "minimalistPastel" for optimal results.
4. GPU Recommendation: For efficient computation, consider using cloud GPUs like those offered by AWS, Google Cloud, or Azure.

License

The GLIF-LORADEX-TRAINER model is distributed under the flux-1-dev-non-commercial-license. More details can be found in the license document.