Google patents image generator that learns by matching text and pictures
Google describes a method for creating images from text descriptions using a neural network. The system is trained to pull matching text and image pairs closer together in a digital space while pushing non-matching pairs apart, helping the model understand the connection between words and visuals.
In the filing’s own words
A computer-implemented method includes receiving, by a computing device, a particular textual description of a scene. The method also includes applying a neural network for text-to-image generation to generate an output image rendition of the scene, the neural network having been trained to cause two image renditions associated with a same textual description to attract each other and two image renditions associated with different textual descriptions to repel each other based on mutual information between a plurality of corresponding pairs, wherein the plurality of corresponding pairs comprise an image-to-image pair and a text-to-image pair. The method further includes predicting the output image rendition of the scene.
What exactly they claim (claim 1)
1. A computer-implemented method, comprising: receiving, by a computing device, a textual description of a scene; generating a random noise input; and processing the random noise input and the textual description using a generative neural network to generate an output image rendition of the scene, wherein the generative neural network comprises a plurality of attention mechanisms configured to condition the generation of the output image rendition on the textual description, and wherein the generative neural network has been trained using a contrastive loss objective that maximizes mutual information between image features and text features by causing paired image-text representations to attract in a feature space and unpaired image-text representations to repel in the feature space.
Facts
- Company
- Google (Google LLC)
- Official title
- Cross-Modal Contrastive Learning for Text-to-Image Generation based on Machine Learning Models
- Publication number
- US20260330705A1
- Application number
- 19461275
- Filed
- Jan 27, 2026
- Published
- Oct 22, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06T 11/00 Physics & computingG06F 18/2148 Physics & computingG06F 18/22 Physics & computingG06N 3/08 Physics & computingG10L 15/26 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.