Nvidia patents chip that turns text into video using noise reduction


Nvidia describes a processor design that creates video clips from text prompts. It works by starting with random, noisy images and using a neural network to clean them up into clear video frames that match the written description.
In the filing’s own words
Apparatuses, system, and techniques to process resources used to perform a neural network to generate one or more images. In at least one embodiment, a processor comprising circuitry uses one or more neural networks to generate one or more second images based, at least in part, on noise within a first image.
What exactly they claim (claim 1)
1. A processor, comprising: one or more circuits configured to generate a video based on text input, wherein to generate the video the one or more circuits are to: generate a series of correlated noised images, wherein one or more of the correlated noised images contain noise based, at least in part, on noise within one or more earlier images in the series of correlated noised images; generate the video by at least denoising, using one or more diffusion model neural networks, the series of correlated noised images into a corresponding series of denoised video frames according to one or more constraints indicated by the text input.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- NEURAL NETWORK IMAGE GENERATION
- Publication number
- US20260350760A1
- Application number
- 19741705
- Filed
- Jul 14, 2026
- Published
- Nov 5, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06T 5/70 Physics & computingG06T 11/60 Physics & computingG06T 2207/10016 Physics & computingG06T 2207/20081 Physics & computingG06T 2207/20084 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents system that translates specific speakers in group conversations Nov 12, 2026
- Nvidia patents AI that creates 3D medical scans from text prompts Nov 12, 2026
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.