WebAI StudioQuickly generate accessibility alt-tags for entire photo libraries locally without consuming immense bandwidth.
This demo requires an On-Device Language Model with vision capabilities. Please ensure you are using a supported browser with the correct experimental flags enabled.
to generate alt-text
Upload an image and hit generate to create a rich, accessible description.
56 demos, all running on-device.
Drop in your photos, and search them by meaning — "food on a table", "someone smiling" — without one pixel leaving your device.
Point your camera at anything, freeze a frame, and ask the on-device model about what it sees.
You sketch, Gemini Nano guesses: the model interprets your doodle after every stroke.