alexgenovese/blip-captions

alexgenovese / blip-captions

Create a ZIP file with images (png, jpg, jpeg, webp) to describe the image with BLIP 2. This endpoint provides a fashion training model too.

Public
21 runs

Run with an API

Playground API Examples README Versions

Run alexgenovese/blip-captions with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
images	string		Upload here all images in ZIP format
one_string_for_all	string		Use only this string for all captions
prepend_string	string		prepend (at the start) text. Example: a photo of
append_string	string		append (at the end) text. Example: reica fashion foto style
type	string (enum)	default Options: default, fashion	If default train with base BLIP2 model.
output_filename	string		If none train with base BLIP2 model. Types: fashion
remove_background	boolean	False	Remove background based on object to keep variable

{
  "type": "object",
  "title": "Input",
  "properties": {
    "type": {
      "enum": [
        "default",
        "fashion"
      ],
      "type": "string",
      "title": "type",
      "description": "If default train with base BLIP2 model.",
      "default": "default",
      "x-order": 4
    },
    "images": {
      "type": "string",
      "title": "Images",
      "format": "uri",
      "x-order": 0,
      "description": "Upload here all images in ZIP format"
    },
    "append_string": {
      "type": "string",
      "title": "Append String",
      "default": "",
      "x-order": 3,
      "description": "append (at the end) text. Example: reica fashion foto style"
    },
    "prepend_string": {
      "type": "string",
      "title": "Prepend String",
      "default": "",
      "x-order": 2,
      "description": "prepend (at the start) text. Example: a photo of "
    },
    "output_filename": {
      "type": "string",
      "title": "Output Filename",
      "x-order": 5,
      "description": "If none train with base BLIP2 model. Types: fashion"
    },
    "remove_background": {
      "type": "boolean",
      "title": "Remove Background",
      "default": false,
      "x-order": 6,
      "description": "Remove background based on object to keep variable"
    },
    "one_string_for_all": {
      "type": "string",
      "title": "One String For All",
      "default": "",
      "x-order": 1,
      "description": "Use only this string for all captions"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}