Fuente: WIPO "tomato" An example method includes determining, by a computing device, one or more specifiable attributes associated with at least one object in an image. The method further includes providing, by the computing device, the image and a prompt to a sequence model, wherein the prompt, upon being provided as input to the sequence model, causes the sequence model to perform an analytical task on the image based on a specifiable attribute of the one or more specifiable attributes. The method also includes receiving, by the computing device and from the sequence model and responsive to the prompt, an output of the analytical task.