---
tags:
- image-to-text
- image-captioning
- endpoints-template
license: bsd-3-clause
library_name: generic
---

# Image captioning
For deployment as an inference endpoint, using a Custom task type – a fixed version of [this repo](https://huggingface.co/florentgbelidji/blip_captioning) (updated to decode the base64 image strings)

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

## Response payload
```json
{
  "captions": ["inferred caption for image"]
}
```