Image captioning

For deployment as an inference endpoint, using a Custom task type – a fixed version of this repo (updated to decode the base64 image strings)

Request payload

{
  "inputs": ["/9j/4AAQSkZJRgABAQEBLAEsAAD/2wBDAAMCAgICAgMC...."], // base64-encoded image
}

Response payload

{
  "captions": ["inferred caption for image"]
}