US 12,340,557 B1
Systems and methods for contextual machine learning prompt generation
Elham Saraee, Medford, MA (US); Jehan Hamedi, Wellesley, MA (US); and Zachary Halloran, Franklin, MA (US)
Assigned to VIZIT LABS, INC., Boston, MA (US)
Filed by VIZIT LABS, INC., Boston, MA (US)
Filed on Mar. 24, 2025, as Appl. No. 19/088,853.
Application 19/088,853 is a continuation of application No. 18/948,435, filed on Nov. 14, 2024, granted, now 12,260,611.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/438 (2019.01); G06N 3/045 (2023.01); G06V 10/40 (2022.01); G06V 10/74 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/761 (2022.01) [G06F 16/438 (2019.01); G06N 3/045 (2023.01); G06V 10/40 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
11. A system, comprising:
one or more processors configured by machine-readable instructions to:
receive, from a client device, a request to generate an image;
execute a text generation machine learning model based on the request to generate a candidate generated text string identifying one or more features, the text generation machine learning model trained based on images each corresponding to an image performance score exceeding a threshold;
execute an image generation machine learning model using the candidate generated text string to generate one or more images each according to the one or more features identified in the candidate generated text string; and
transmit the one or more images to the client device.