You're looking at a specific version of this model. Jump to the model overview.

salesforce /blip:2e1dddc8

Input

image
*file

Input image

string

Choose a task.

Default: "image_captioning"

string
Shift + Return to add a new line

Type question for the input image for visual question answering task.

string
Shift + Return to add a new line

Type caption for the input image for image text matching task.

Output

Caption: a woman sitting on the beach with a dog
Generated in

This example was created by a different version, salesforce/blip:5a977fcb.