We're excited to share florence2-sharp, a C# library implementing the Florence-2-model for advanced image understanding tasks. Florence-2 uses a prompt-based approach to a variety of vision tasks, and provides great zero-shot performance across many vision tasks.<p>Our C# library supports:<p>- Image captioning (from concise to detailed)<p>- Optical Character Recognition (OCR)<p>- Region-based OCR<p>- Object detection<p>- Optional phrase grounding<p>The library is a C# port of Microsoft's Florence-2 model (from <a href="https://huggingface.co/microsoft/Florence-2-base" rel="nofollow">https://huggingface.co/microsoft/Florence-2-base</a>), based on the original model and the JS port by Frank Krueger (<a href="https://github.com/praeclarum/transformers-js">https://github.com/praeclarum/transformers-js</a>).<p>Repo: <a href="https://github.com/curiosity-ai/florence2-sharp">https://github.com/curiosity-ai/florence2-sharp</a><p>NuGet: <a href="https://www.nuget.org/packages/Florence2" rel="nofollow">https://www.nuget.org/packages/Florence2</a>