Understand a picture
Ask questions about a picture, or find every object in it.
What runs here
Every model below is downloaded to this device once and then runs on it. Nothing you type, record, or upload is sent to a server, and there is no account or cost.
- Describe it (MIT, 221 MB). Writes a few sentences about the picture. Good for alt text.
- Find objects (MIT, 221 MB). Boxes and labels everything it recognises.
- Read the text (MIT, 221 MB). Pulls out any writing in the image.
- Ask a question (Apache 2.0, 635 MB). Ask anything about the picture in your own words. A bigger download than the fixed jobs above.