/Patent Tracker
NvidiaGranted patentAI & softwareInterest 7/10

Nvidia patents AI system that builds image generators from text prompts

Nvidia describes a system where one set of neural networks creates or adjusts another set of neural networks to produce digital images. The process starts with a text description of an object, which guides the creation of the image-generating model.

Why it mattersThis approach could make it easier to create custom image generators tailored to specific descriptions without manually training each model from scratch.

In the filing’s own words

Apparatuses, systems, and techniques to generate a digital representation of one or more objects. In at least one embodiment, one or more first neural networks generate one or more second neural networks to generate a digital representation of one or more objects based, at least in part, on a text description of said one or more objects.

What exactly they claim (claim 1)

1. A processor comprising: one or more circuits to: cause one or more first neural networks to map a text description of one or more objects to one or more modifications to at least a portion of one or more second neural networks to generate, based on a learned neural representation of the one or more objects, a digital representation of the one or more objects; and cause the one or more second neural networks to generate the digital representation of the one or more objects using the one or more modifications.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
Neural network-based digital asset generation
Patent number
US12737621B1
Application number
18137945
Filed
Apr 21, 2023
Granted
Sep 15, 2026
Inventors
4
Claims
20

Classified under

G06N 3/08 Physics & computing

More from Nvidia in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.