Microsoft patents AI design tool that swaps images while keeping layout
Microsoft describes a system that takes a user's text request and breaks it down into specific objects and themes. It then finds a matching design template and uses an image editing tool to replace the original visuals with new ones that fit the requested theme, while keeping the text and layout in the same spots.
In the filing’s own words
A data processing system implements receiving, via a user interface of a client device of a user, a first prompt requesting an image to be generated for the user by a generative model, the first prompt including textual content. The system further implements constructing a second prompt by a prompt construction unit as an input to the generative model, the prompt construction unit constructing the second prompt by extracting an artifact and a theme from the textual content and appending the artifact and the theme to an instruction string, the instruction string comprising instructions to the generative model to determine a design template matching the artifact, and to generate the image by replacing visual element(s) of the design template based on the theme while preserving a graphic layout of the design template; providing the image to the client device; and causing the user interface to present the image.
What exactly they claim (claim 1)
1. A data processing system comprising: a processor, and a machine-readable storage medium storing executable instructions which, when executed by the processor, cause the processor alone or in combination with other processors to perform following operations: receiving, via a user interface of a client device of a user, a first prompt requesting an image to be generated for the user by a generative model, the first prompt including textual content; constructing a second prompt by a prompt construction unit as an input to the generative model, the prompt construction unit constructing the second prompt by extracting at least an artifact and a theme from the textual content and appending at least the artifact and the theme to an instruction string, the instruction string comprising instructions to the generative model to determine a design template selected from a design template library that matches the artifact and having a fixed number of text fields and visual elements of a different theme, and to generate the image by identifying one or more visual elements of the design template and replacing the one or more of the visual elements using an inpainting tool based on the different theme while preserving a graphic layout of the design template, the graphic layout including positions and sizes of the text fields and the visual elements of the design template; providing the image to the client device; and causing the user interface to present the image.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Thematic variation generation for AI-assisted graphic design
- Patent number
- US12802306B2
- Application number
- 18536644
- Filed
- Dec 12, 2023
- Granted
- Nov 17, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G06T 11/60 Physics & computingG06F 40/40 Physics & computingG06T 7/12 Physics & computingG06T 11/10 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 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.
