Google patents method to train image AI using AI-written descriptions
This patent describes a process for improving text-to-image AI models by first using one AI to write detailed captions for existing images. These captions are then used to train a second AI model, which can generate new images from text prompts more effectively.
In the filing’s own words
A method of generating high-performance images includes generating, by one or more processors, a first plurality of captions each corresponding to a different one of a first plurality of images. Generating the first plurality of captions includes inputting the first plurality of images into a first generative artificial intelligence (AI) model. The method also includes training or finetuning, by the one or more processors, a second generative AI model using the first plurality of images and the first plurality of captions, and generating, by the one or more processors, a second plurality of images. Generating the second plurality of images includes inputting a plurality of text prompts into the trained or finetuned second generative AI model.
What exactly they claim (claim 1)
1. A method of generating high-performance images, the method comprising: generating, by one or more processors, a first plurality of captions each corresponding to a different one of a first plurality of images, wherein generating the first plurality of captions includes inputting the first plurality of images into a first generative artificial intelligence (AI) model; training or finetuning, by the one or more processors, a second generative AI model by: generating a plurality of training or finetuning text prompts each including (i) a different one of the first plurality of captions, and (ii) a text indication of an image type of the image, of the first plurality of images, that corresponds to the different one of the first plurality of captions; and using the first plurality of images and the generated plurality of training or finetuning text prompts; and generating, by the one or more processors, a second plurality of images, wherein generating the second plurality of images includes inputting a plurality of text prompts into the trained or finetuned second generative AI model.
Facts
- Company
- Google (GOOGLE LLC)
- Official title
- Performance-aware image generation based on text
- Patent number
- US12743587B2
- Application number
- 18742553
- Filed
- Jun 13, 2024
- Granted
- Sep 22, 2026
- Inventors
- 5
- Claims
- 24
Classified under
G06T 11/60 Physics & computingG06F 40/40 Physics & computingG06N 3/096 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.