Generative AI .NET Playground
A collection of experimental applications to play around with generative AI tasks (text, images, audio, and more), leveraging .NET, Avalonia and many other open-source toolkits and frameworks.
Introduction
It is an on-going work in progress, built in my spare time for fun.
Getting Started
Project Organization
├── LICENSE
├── README.md <- The top-level README for developers using this project
├── docs <- Project documentation
├── src <- Source code
│ ├── images
│ │ └── stable-diffusion <- Stable Diffusion playground
│ └── text
│ ├── llms <- Local LLMs (Large-Language-Models) playground
│ └── whisper <- Whisper (Speech-To-Text) playground
|
└── ... <- other files
Setup a local copy
Clone the repository and build.
Requirements to run locally:
- Windows 11
- Visual Studio 2022, .NET 8.0
- GPU enabled machine, with CUDA and cuDNN properly configured
This was built on a NVIDIA RTX 3090 and it has not been tested on different devices.
Contribution
The project is constantly evolving and contributions are warmly welcomed.
I'm more than happy to receive any kind of contribution to this experimental project: from helpful feedbacks to bug reports, documentation, usage examples, feature requests, or directly code contribution for bug fixes and new and/or improved features.
Feel free to file issues and pull requests on the repository and I'll address them as much as I can, with a best effort approach during my spare time.
Development is mainly done on Windows, so other platforms are not directly developed, tested or supported.
An help is kindly appreciated in make the application work on other platforms as well.
License
You may find specific license information for third party projects in each project sub-folder.
Where not otherwise specified, everything is licensed under the APACHE 2.0 License.
Copyright (C) 2023-2024 Gianni Rosa Gallina.