We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
moondream is a computer-vision model can answer real-world questions about images. It's tiny by today's models, with only 1.6B parameters. That enables it to run on a variety of devices, including mobile phones and edge devices.
moondream is great at answering questions about images. Since it's tiny, it can run everywhere, even on mobile devices or Raspberry Pi's, for example. It's quick and can process images quickly.
Apache 2.0. You can use moondream for commercial purposes.
It's purposefully built to answer questions about images, and does not do well with theoretical or abstract questions (e.g., "why would a cat do that?"). Because images are sampled down to 378x378, it may not be able to answer questions about very small details in the image. This also limits its ability to perform OCR. It's also not great at counting items beyond 2 or 3.
You can file issues at our github repository. For other inquiries, you can reach out to us at contact@moondream.ai.