POST
/
v1
/
image
/
generate
from PIL import Image
from vlmrun.client import VLMRun

client = VLMRun(api_key="<VLMRUN_API_KEY>")
response = client.image.generate(
    images=[Image.open("<path>.jpg")],
    domain="<domain>"
)
{
  "usage": {
    "elements_processed": 123,
    "element_type": "image",
    "credits_used": 123,
    "steps": 123,
    "message": "<string>",
    "duration_seconds": 0
  },
  "id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "response": "<any>",
  "status": "pending",
  "domain": "<string>"
}
For all supported image domains, see the Hub Catalog.
from PIL import Image
from vlmrun.client import VLMRun

client = VLMRun(api_key="<VLMRUN_API_KEY>")
response = client.image.generate(
    images=[Image.open("<path>.jpg")],
    domain="<domain>"
)

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request to the VLM API (i.e. structured prediction).

images
string[]
required

List of base64 encoded images or URLs to the images.

domain
required

The domain identifier (e.g. image.caption).

Available options:
aerospace.remote-sensing,
document.invoice,
document.markdown,
document.receipt,
document.resume,
image.caption,
experimental.image.object-detection,
experimental.image.person-detection,
retail.product-catalog,
image.tv-news,
video.caption
metadata
object

Optional metadata to pass to the model.

config
object

The VLM generation config to be used for /<dtype>/generate.

id
string

Unique identifier of the request.

created_at
string<date-time>

Date and time when the request was created (in UTC timezone)

callback_url
string<uri> | null

The URL to call when the request is completed.

Minimum length: 1
model
default:vlm-1

The model to use for generating the response.

Allowed value: "vlm-1"
batch
boolean
default:false

Whether to process the image in batch mode (async).

Response

Successful Response

Base prediction response for all API responses.

usage
object

The usage metrics for the request.

id
string

Unique identifier of the response.

created_at
string<date-time>

Date and time when the request was created (in UTC timezone)

completed_at
string<date-time> | null

Date and time when the response was completed (in UTC timezone)

response
any

The response from the model.

status
enum<string>
default:pending

The status of the job.

Available options:
pending,
enqueued,
running,
completed,
failed,
paused
domain
string | null

The domain of the prediction (e.g. document.invoice, image.caption).