Tutorials¶

Learning-oriented walkthroughs that take you from nothing to a working result. Each one runs the published checkpoint, thaitea/laya-vision, on a real photo.

For task-focused recipes ("how do I do X?") see the How-to guides; for how the model works see Concepts. To run the Python tutorial, install the package first; the demo needs nothing installed.

Available tutorials¶

• Your first prediction: load the checkpoint in Python, ask three typed questions about a photo, and read the answers, including one the model gets wrong.
• Try the demo: the published checkpoint in a Hugging Face Space, with your own image and questions, nothing installed.