API Reference

Run inference on the input image/video for a given text prompt

post
https://ai.api.nvidia.com/v1/cv/nvidia/nv-grounding-dino

Runs inference on the specified input file for given text prompt. The input image can be Base64 encoded string in the image URL or it can be specified using the file identifier of an uploaded file.

Body Params
string
required
length ≤ 256

Name of the model used.

messages
array of objects
required
length ≤ 1000000

Requests for inference.

Messages*
number
required
0.1 to 1
Defaults to 0.3

Threshold used for detection.

Headers
uuid
length ≤ 370

String of asset IDs separated by commas. Data is uploaded to AWS S3 using NVCF Asset APIs and associated with these asset IDs.The presigned URL allows for secure and temporary access to the S3 bucket for uploading the video. Once the asset is requested, an asset ID is generated for it. Please include this asset ID in this header and to use the uploaded video in a prompt.

Responses

Updated over 1 year ago

Language
Credentials
Bearer
Response 
Click Try It! to start a request and see the response here! Or choose an example:
application/json
Updated over 1 year ago 













































country_code