disco elysium

Introduction

The "Disco Elysium" model is a fine-tuned version of the Stable Diffusion model, specifically trained on character portraits from the game Disco Elysium. By using the prompt tokens discoelysium style, users can generate images in the style of the game's character portraits.

Architecture

The model is based on the Stable Diffusion architecture, which is known for its ability to generate high-quality images from text prompts. This particular model has been fine-tuned to capture the unique artistic style of the Disco Elysium game.

Training

The model was trained on character portraits from Disco Elysium. While specific details on the training process, such as dataset size and training duration, are not provided, the model is designed to produce outputs in the distinct style of the game's art.

Guide: Running Locally

1. Set up Environment: Ensure you have Python and the necessary libraries installed. It's recommended to use a virtual environment.
2. Download Model: Clone the repository or download the model files from the Hugging Face model page.
3. Load Model: Use a framework like PyTorch to load the model weights.
4. Generate Images: Input prompts with the discoelysium style token to generate images.

• Cloud GPUs: For efficient processing, especially if running on large datasets or high-resolution outputs, consider using cloud GPU services like AWS EC2, Google Cloud, or Azure.

License

The model is distributed under the CreativeML OpenRAIL-M license. Key points include:

1. The model must not be used for generating illegal or harmful content.
2. The authors do not claim rights over the generated outputs; users are responsible for ensuring compliance with the license terms.
3. Redistribution of the model is permitted, including commercial use, provided that the same license terms are applied and the CreativeML OpenRAIL-M license is shared with users. Read the full license here.