Meta patents avatar editing that keeps your face while changing the rest
Meta describes a method for editing digital avatars by using text prompts to change specific parts of a 2D image while keeping facial features unchanged. The system uses a segmentation mask to identify which areas can be altered and an image modification model to apply the changes. Finally, a 3D modeling tool converts the updated set of 2D images into a complete 3D avatar model.
In the filing’s own words
An embodiment includes generating, by recognizing a first facial feature in a first two-dimensional image in a set of two-dimensional images, a first segmentation mask, the first segmentation mask identifying a changeable portion and a non-changeable portion of the first two-dimensional image, the non-changeable portion comprising the first facial feature. An embodiment includes adjusting, using an image modification model, from a first numerical representation of the first two-dimensional image, the first segmentation mask, a positive prompt, and a negative prompt, the first two-dimensional image, the adjusting resulting in a second two-dimensional image, the second two-dimensional image replacing the first two-dimensional image in the set of two-dimensional images. An embodiment includes generating, using a three-dimensional modelling model, from the set of two-dimensional images comprising the second two-dimensional image, a three-dimensional model corresponding to the set of two-dimensional images.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: generating, by recognizing a first facial feature in a first two-dimensional image in a set of two-dimensional images, a first segmentation mask, the first segmentation mask identifying a changeable portion and a non-changeable portion of the first two-dimensional image, the non-changeable portion comprising the first facial feature; adjusting, using an image modification model, from a first numerical representation of the first two-dimensional image, the first segmentation mask, a positive prompt, and a negative prompt, the first two-dimensional image, the adjusting resulting in a second two-dimensional image, the second two-dimensional image replacing the first two-dimensional image in the set of two-dimensional images; and generating, using a three-dimensional modelling model, from the set of two-dimensional images comprising the second two-dimensional image, a three-dimensional model corresponding to the set of two-dimensional images.
Facts
- Company
- Meta (Meta Platforms Technologies, LLC)
- Official title
- PERSONALIZED AVATAR ADJUSTMENT USING TEXT PROMPTED IMAGE GENERATION
- Publication number
- US20260268595A1
- Application number
- 19074102
- Filed
- Mar 7, 2025
- Published
- Sep 10, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06T 17/00 Physics & computingG06T 11/60 Physics & computingG06T 19/006 Physics & computingG06V 40/168 Physics & computingMore from Meta in AI & software
- Meta patents AI summaries for notifications on glasses and watches Sep 29, 2026
- Meta patents group video effects that change when you interact with them Oct 20, 2026
- Meta patents search method that uses learning objectives to find content Oct 1, 2026
- Meta patents method to trim training data for machine learning models Sep 22, 2026
- Meta patents method to track message order in large AI clusters Sep 1, 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.