公开(公告)号：US20250095227A1

公开(公告)日：2025-03-20

申请号：US18886452

申请日：2024-09-16

Applicant: ADOBE INC.

Inventor： Adrian-Stefan Ungureanu-Contes ,  Marian Lupascu ,  Vlad-Constantin Lungu-Stan ,  Ionuţ Mironica ,  Vineet Batra

IPC: G06T11/00 ,  G06T3/4053

Abstract: A method, apparatus, non-transitory computer readable medium, and system for training a text-guided vector image synthesis include obtaining training data including a vectorizable image and a caption describing the vectorizable image and generating, using an image generation model, a predicted image with a first level of high frequency detail. Then, the training data and the predicted image are used to tune the image generation model to generate a synthetic vectorizable image based on the caption, where the synthetic vectorizable image has a second level of high frequency detail that is lower than the first level of high frequency detail of the predicted image.