Computer Vision Toolbox Model for Moondream Vision Language Model

Moondream is a small footprint vision language model, with image captioning capability.

Al momento, stai seguendo questo contributo

The Moondream 2 model is a lightweight Vision-Language Model (Vision-LLM) capable of image captioning. Due to its small size, it can be run efficiently on most local workstations.

Add the first tag.

Compatibilità della release di MATLAB

  • Compatibile con R2026a

Compatibilità della piattaforma

  • Windows
  • macOS (Apple Silicon)
  • macOS (Intel)
  • Linux