Progressive real-time diffusion of layered content files with animated features

Patent metadata

Field	Value
Publication number	US-12573124-B2
Application number	US-202418617535-A
Country	US
Kind code	B2
Filing date	Mar 26, 2024
Priority date	Mar 26, 2024
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

Systems or methods for providing a content editing service that integrates a layered structure of digital image editing integrated with AI-based image-guided content generation modifier that is guided based on different features stored in association with the separate layers of the layered structure. The image-guided content generation utilizes a non-destructive nature of the layer-based image editing process to extract metadata associated with input layers of a provided image to output computer-generated content.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
storing one or more layers in memory, wherein the one or more layers are stored in relation to a content file; receiving, from a client application of a content editing service, animation metadata pertaining to an animating element in a first layer of the one or more stored layers of the content file, wherein the animation metadata describes how the animating element is animated, wherein the first layer is a child layer of a second layer, and wherein the second layer includes an image-guided content generation modifier; generating two or more animation frames of the content file based on the animation metadata; applying the image-guided content generation modifier to the two or more animation frames in parallel to generate modified animation frames; and sending the modified animation frames to be displayed in a preview interface displayed alongside a canvas interface of the client application that contains the animating element, wherein the modified animation frames are presented as an animation.

2 . The computer-implemented method of claim 1 , wherein the modified animation frames are displayed as a continuous loop through the modified animation frames over a period of time.

3 . The computer-implemented method of claim 1 , wherein the two or more animation frames are at intermittent intervals and separated by interposed animation frames.

4 . The computer-implemented method of claim 3 , further comprising:
while the modified animation frames are displayed at the client application, modifying the interposed animation frames by applying the image-guided content generation modifier to the respective interposed animation frames in parallel; and after the modified interposed animation frames are generated, sending the modified interposed animation frames to replace temporary interposed animation frames interposed between the modified animation frames to display an updated animation at the client application.

5 . The computer-implemented method of claim 4 , further comprising:
using the animation metadata or the two or more animation frames to generate optical flow vectors; and using the optical flow vectors to generate the temporary interposed animation frames.

6 . The computer-implemented method of claim 5 , further comprising:
determining, based on the optical flow vectors, one or more regions in the two or more animation frames that do not have animation; and sending instructions to hold the regions in memory of a first modified animation frame throughout the animation.

7 . The computer-implemented method of claim 5 , further comprising:
determining, based on the optical flow vectors, one or more regions in the two or more animation frames that do not have animation; and generating a masked region of the respective animation frames that excludes the one or more regions, wherein the applying of the image-guided content generation modifier is to the masked region of the respective animation frames.

8 . The computer-implemented method of claim 7 , wherein the masked region is generated by using at least one of a transparency matte of the respective animation frames or an automatic image segmentation technique of the respective animation frames to automatically generate the masked region.

9 . The computer-implemented method of claim 1 , wherein the two or more animation frames are at intermittent intervals and separated by interposed animation frames, and wherein the generation of at least some of the two or more animation frames further comprises:
encoding animation data in pixels of the at least some of the two or more animation frames, wherein the animation data includes optical flow vectors generated based on the animation metadata; and sending the encoded animation data to the client application that uses the encoded animation data to create temporary interposed animation frames interposed between the modified animation frames for display in the animation while modified interposed animation frames are being generated.

10 . The computer-implemented method of claim 1 , wherein the content editing service is a collaborative content editing service.

11 . The computer-implemented method of claim 1 , further comprising:
applying the animation metadata to a shadow copy of the content file, wherein the two or more animation frames are generated from the shadow copy with the applied animation metadata.

12 . The computer-implemented method of claim 11 , wherein the shadow copy is stored with a collaboration service for real-time state synchronization.

13 . The computer-implemented method of claim 1 , wherein metadata of the one or more layers guides the image-guided content generation modifier to boost a control strength of one or more contours contiguous with a respective transparent background of the two or more animation frames.

14 . The computer-implemented method of claim 1 , wherein the modified animation frames includes a set of output layers corresponding to the one or more layers.

15 . The computer-implemented method of claim 1 , further comprising:
receiving a text prompt or contextual data to further guide the image-guided content generation modifier in generating the modified animation frames.

16 . The computer-implemented method of claim 15 , wherein the contextual data includes optical flow vector data that provides context to movement of one or more features of the two or more animation frames.

17 . A computing device comprising:
one or more processors; and memory storing instructions that, when executed by the one or more processors, configure the computing device to: store one or more layers in memory, wherein the one or more layers are stored in relation to a content file;
receive, from a client application of a content editing service, animation metadata pertaining to an animating element in a first layer of the one or more stored layers of the content file, wherein the animation metadata describes how the animating element is animated, wherein the first layer is a child layer of a second layer, and wherein the second layer includes an image-guided content generation modifier;
generate two or more animation frames of the content file based on the animation metadata;
apply the image-guided content generation modifier to the two or more animation frames in parallel to generate modified animation frames; and
send the modified animation frames to be displayed in a preview interface displayed alongside a canvas interface of the client application that contains the animating element, wherein the modified animation frames are presented as an animation.

18 . The computing device of claim 17 , wherein the two or more animation frames are at intermittent intervals and separated by interposed animation frames.

19 . A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to:
store one or more layers in memory, wherein the one or more layers are stored in relation to a content file; receive, from a client application of a content editing service, animation metadata pertaining to an animating element in a first layer of the one or more stored layers of the content file, wherein the animation metadata describes how the animating element is animated, wherein the first layer is a child layer of a second layer, and wherein the second layer includes an image-guided content generation modifier; generate two

Assignees

• Figma Inc

Inventors

• Cowburn Piers
• Belli Djan
• Kristiansen Martin

Classifications

• G06T11/60 Primary

  Creating or editing images; Combining images with text · CPC title

• G06T7/20

  Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) · CPC title

• G06T2200/24

  involving graphical user interfaces [GUIs] · CPC title

• G06T13/80 Primary

  Two-dimensional [2D] animation, e.g. using sprites · CPC title

• G06T13/00

  Animation · CPC title