istolemyownart

Introduction

ISTOLEMYOWNART is a text-to-image model trained using the creator's personal artwork. It leverages the Stable Diffusion framework and aims to generate artistic images. Despite being a personal project, the model's performance can be enhanced by incorporating prompts from real artists.

Architecture

The model utilizes Stable Diffusion through the Diffusers library. It supports Safetensors and is designed for experiments in text-to-image generation. The model is currently structured to work with English language prompts.

Training

The model was trained using 1076 images, including flipped versions, over 10,000 steps with a learning rate of 1e-6. The dataset comprises art collected over ten years. The model's output quality can be inconsistent, often producing a mix of anime and cartoon-style images.

Guide: Running Locally

1. Setup Environment: Ensure you have Python and the necessary libraries installed. Use a virtual environment if preferred.
2. Clone the Repository: Download or clone the model repository locally.
3. Install Dependencies: Install required packages, typically through a requirements.txt file.
4. Run the Model: Load the model and run it with your input prompts to generate images.

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

License

The model is licensed under Creativeml-Openrail-M. It is open for fair use and derivative works, but selling the model is prohibited. The creator emphasizes that all models should remain free and open source.