Google patents AI that edits search images using your context
This patent describes a system that takes a standard image from a search result and uses AI to modify it based on your specific query and context. A language model creates instructions for an image-editing tool to adjust the picture, ensuring the final image matches the user's intent more closely than the original file.
In the filing’s own words
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enabling artificial intelligence to generate new images based on contextual data and to generate digital components based on the images. In one aspect, a method includes receiving one or more queries from a client device of a user. A digital component is selected based on the one or more queries. A customized digital component is generated by obtaining an image of an object corresponding to the selected digital component and generating, using a language model, an image editing prompt for editing the image based on digital component data related to the digital component and query data including the one or more queries and contextual data. The image and the image editing prompt are provided to an image editing model. An edited image is received and used to generate the customized digital component.
What exactly they claim (claim 1)
1. A method, comprising: receiving one or more queries from a client device of a user; selecting a digital component based on the one or more queries; generating a customized digital component for the user, the generating comprising: obtaining an image of an object corresponding to the selected digital component; generating, using a language model, an image editing prompt for editing the image based on (i) digital component data related to the digital component and (ii) query data comprising the one or more queries and contextual data that characterizes a context in which the one or more queries are received from the client device; identifying mismatching concepts among one or more first concepts identified based on the digital component data and one or more second concepts identified from the query data; filtering the mismatching concepts, wherein filtering the mismatching concepts comprises filtering only a portion of the mismatching concepts based on a level of importance of each mismatching concept; providing the image and the image editing prompt to an image editing model that is trained to edit images based on input prompts and input images; receiving, from the image editing model, an edited image; and generating the customized digital component using the edited image; and sending the customized digital component to the client device of the user.
Facts
- Company
- Google (Google LLC)
- Official title
- Using generative artificial intelligence to edit images based on contextual data
- Patent number
- US12743581B2
- Application number
- 18815790
- Filed
- Aug 26, 2024
- Granted
- Sep 22, 2026
- Inventors
- 2
- Claims
- 17
Classified under
G06T 11/60 Physics & computingG06F 40/279 Physics & computingG06F 40/40 Physics & computingG06T 7/194 Physics & computingG06T 2207/20084 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.