Magic Prompt Stable Diffusion

Introduction

MagicPrompt-Stable-Diffusion is a model in the MagicPrompt series, based on GPT-2. It is designed to generate prompt texts specifically for imaging AIs, such as Stable Diffusion.

Architecture

MagicPrompt-Stable-Diffusion leverages the GPT-2 architecture to generate text prompts. It is compatible with various libraries including PyTorch, Core ML, and Safetensors. The model is designed for text generation and inference endpoints.

Training

The model was trained for 150,000 steps using a dataset of approximately 80,000 entries, extracted from Lexica.art. The dataset, used to fine-tune the model, is accessible at the provided link for further exploration.

Guide: Running Locally

1. Clone the repository from Hugging Face.
2. Ensure you have the necessary dependencies installed, including PyTorch and Transformers.
3. Load the model using the Transformers library.
4. Run text generation tasks to create prompts compatible with Stable Diffusion.

To optimize performance, consider using cloud GPUs such as those from AWS, Google Cloud, or Azure.

License

The MagicPrompt-Stable-Diffusion model is released under the MIT License. Users should credit Gustavosta when utilizing this model in their work.