Class ImageTextModel (1.71.1)

ImageTextModel(model_id: str, endpoint_name: typing.Optional[str] = None)

Generates text from images.

Examples::

model = ImageTextModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")

captions = model.get_captions(
    image=image,
    # Optional:
    number_of_results=1,
    language="en",
)

answers = model.ask_question(
    image=image,
    question="What color is the car in this image?",
    # Optional:
    number_of_results=1,
)

Methods

ImageTextModel

ImageTextModel(model_id: str, endpoint_name: typing.Optional[str] = None)

Creates a _ModelGardenModel.

This constructor should not be called directly. Use {model_class}.from_pretrained(model_name=...) instead.

ask_question

ask_question(
    image: vertexai.vision_models.Image, question: str, *, number_of_results: int = 1
) -> typing.List[str]

Answers questions about an image.

from_pretrained

from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.T

Loads a _ModelGardenModel.

Exceptions
Type Description
ValueError If model_name is unknown.
ValueError If model does not support this class.

get_captions

get_captions(
    image: vertexai.vision_models.Image,
    *,
    number_of_results: int = 1,
    language: str = "en",
    output_gcs_uri: typing.Optional[str] = None
) -> typing.List[str]

Generates captions for a given image.