OpenAI patents system that turns photos into new AI-generated images
OpenAI has filed a patent for a system that takes a batch of photos, picks out the most interesting ones, and describes them in text. It then uses those descriptions to create new, computer-generated images that look like the original photos.
In the filing’s own words
A method for generating a set of synthetic images corresponding to a subset of images of an image collection may include receiving a collection of captured images captured by an electronic device, providing the collection of captured images as input to an image selection model trained to select, from the collection of captured images, a subset of images that satisfy a salience condition. The method may further include providing the subset of images to an image analysis model, receiving text-based summaries of the images as output from the image analysis model, and generating a prompt for an image generation model. The method may further include receiving, as output from the image generation model, a synthetic image including a computer-generated representation of the image content of the image, and causing the synthetic image to be displayed on an image display device.
What exactly they claim (claim 1)
1. A method for generating a set of synthetic images corresponding to a subset of images of a collection of captured images, comprising: receiving the collection of captured images, the collection of captured images captured by an electronic device, each image of the collection of captured images having image content; providing the collection of captured images as input to an image selection model trained to select, from the collection of captured images, a subset of images that satisfy a salience condition; receiving, as output from the image selection model, respective identifiers of the images of the subset of images that satisfy the salience condition; and for an image of the subset of images that satisfies the salience condition: providing the image as input to an image analysis model; receiving, as output from the image analysis model, a text-based summary of the image content of the image; generating a prompt for an image generation model, the prompt including the text-based summary of the image; receiving, as output from the image generation model, a synthetic image including a computer-generated representation of the image content of the image; and causing the synthetic image to be displayed on an image display device.
Facts
- Company
- OpenAI (OpenAI OpCo, LLC)
- Official title
- SYNTHETIC IMAGE GENERATION SYSTEM
- Publication number
- US20260268535A1
- Application number
- 19556909
- Filed
- Mar 4, 2026
- Published
- Sep 10, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G06T 11/00 Physics & computingG06F 16/532 Physics & computingG06F 16/583 Physics & computingMore from OpenAI in AI & software
- OpenAI patents voice system that detects when you stop talking Sep 22, 2026
- OpenAI patents system to catch AI models cheating on tasks Sep 10, 2026
- OpenAI patents method to check AI thinking for cheating Sep 10, 2026
- OpenAI patents AI that answers questions using only your company's secure files Sep 17, 2026
- OpenAI patents memory system for personalized AI chat responses Oct 8, 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.