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

nvlabs/prismer:ef479e09

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
input_image
string
Input image, only .png, .jpg, and .jpeg files are supported
task
string (enum)
caption

Options:

vqa, caption

Choose between Visual Question Answering and Image Captioning
use_experts
boolean
True
Load the experts if set to True
output_expert_labels
boolean
True
Return the experts output (when use_experts) if set to True
question
string
Provide your question for Visual Question Answering task

Output schema

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

Schema
{'properties': {'answer': {'title': 'Answer', 'type': 'string'},
                'depth': {'format': 'uri', 'title': 'Depth', 'type': 'string'},
                'edge': {'format': 'uri', 'title': 'Edge', 'type': 'string'},
                'object_labels': {'title': 'Object Labels'},
                'object_png': {'format': 'uri',
                               'title': 'Object Png',
                               'type': 'string'},
                'ocr_png': {'format': 'uri',
                            'title': 'Ocr Png',
                            'type': 'string'},
                'ocr_pt': {'format': 'uri',
                           'title': 'Ocr Pt',
                           'type': 'string'},
                'segmentation': {'format': 'uri',
                                 'title': 'Segmentation',
                                 'type': 'string'},
                'surface_normal': {'format': 'uri',
                                   'title': 'Surface Normal',
                                   'type': 'string'}},
 'required': ['answer'],
 'title': 'ModelOutput',
 'type': 'object'}