process_image

This method uses the EyeOnIt Large Vision Model to process a single base64-encoded image.

Method: POST

Endpoint: /process_image

Body

{
	"file": "<base64 encoded image string>",
	"regions": [
		{
			"top_left_x": 442,
			"top_left_y": 339,
			"width": 224,
			"height": 224
		}
	],
	"object_size": 224,
	"prompts": [
		{
			"text": "landscape at daytime",
			"background_prompt": false
		},
		{
			"text": "landscape at night",
			"background_prompt": false
		}
	]
}

Body Attribute Descriptions

Name	Type	Description
file	string	the base64 encoding of the image to process
regions	Region[]	the array of regions to use for processing
object_size	int	the object size in pixels for processing
prompts	Prompt[]	the array of object descriptions to use for processing

Response

{
	"message": {
		"landscape at daytime": 99,
		"landscape at night": 0
	}
}

Response Attribute Descriptions

Name	Type	Description
message	object	a map of confidence levels for each object description provided in the body prompts attribute