18425335. KNOWLEDGE EDIT IN A TEXT-TO-IMAGE MODEL (ADOBE INC.)
Contents
KNOWLEDGE EDIT IN A TEXT-TO-IMAGE MODEL
Organization Name
Inventor(s)
Varun Manjunatha of Riverdale MD (US)
Vlad Ion Morariu of Potomac MD (US)
Samyadeep Basu of College Park MD (US)
Nanxuan Zhao of San Jose CA (US)
KNOWLEDGE EDIT IN A TEXT-TO-IMAGE MODEL
This abstract first appeared for US patent application 18425335 titled 'KNOWLEDGE EDIT IN A TEXT-TO-IMAGE MODEL
Original Abstract Submitted
Knowledge edit techniques for text-to-image models and other generative machine learning models are described. In an example, a location is identified within a text-to-image model by a model edit system. The location is configured to influence generation of a visual attribute by a text-to-image model as part of a digital image. An edited text-to-image model is formed by editing the text-to-image model based on the location. The edit causes a change to the visual attribute in generating a subsequent digital image by the edited text-to-image model. The subsequent digital image is generated as having the change to the visual attribute by the edited text-to-image model.
