Snap Inc.

Bradley Kotsopoulos

Yang Gao

Rahul Bhupendra Sheth

Eli Semory

Yingying Wang

Allan Baril

Chirag Gada

Jiayu He

Michael Kozakov

Nicholas Hendriks

Derek Spencer

Wei Hu

Sitong Liu

Mark Schultz

Method starts with a processor causing an electronic program guide (EPG) to be displayed on a first client device that is associated with a first user. Processor detects a selection of a selectable item included in the EPG associated with a media content item by the first user. Processor identifies a second user that is connected to the first user on a communication platform. Processor retrieves a main user identification associated with the first user and a secondary user identification associated with the second user and generates a request for the media content item including media content identification, main user identification, and secondary user identification. Processor then receives a playlist associated with the media content item that comprises media content item segments including first avatar associated with first user and second avatar associated with second user. Other embodiments are disclosed herein.

Selecting avatars to be included in the video being generated on demand

The technical problem of reducing the amount of processing involved when searching for customizable media content items that are suitable for incorporating input text is addressed by providing a hybrid search system. In some examples, the hybrid search system executes a rough search first, to determine whether a line of text can be incorporated into a media content item, based on character count conditions associated with the media content item. A more thorough evaluation of the input text with respect to the media content item is executed subsequent to the rough search if the rough search produces a result indicating uncertainty with respect to whether the combination of specific characters included in the input text can or cannot be incorporated into the media content item.

Hybrid search system for customizable media

Method for generating media content items on demand starts with a processor receiving an animation file including a first metadata based on an animation input. The animation file is associated with a media content identification. The processor generates puppets associated with frames in the animation file using the first metadata. The processor causes a puppet matching interface to be displayed on a client device. The puppet matching interface includes one of the puppets in a first pose. The processor receives a puppet posing input associated with a second pose from the client device. The processor causes the one of the puppets to be displayed in the second pose in the puppet matching interface by the client device. The processor can also generate a second metadata based on the puppet posing input. Other embodiments are disclosed herein.

System for generating media content items on demand

A content controller system to render frames on demand comprises a rendering server system that includes a plurality of graphics processing units (GPUs). The GPUs in the rendering server system render a set of media content item segments using a media content identification and a main user identification. Rendering the set of media content item segments includes retrieving metadata from a metadata database associated with the media content identification, rendering the set of media content item segments using the metadata, generating a main user avatar based on the main user identification, and incorporating the main user avatar into the set of media content item segments. The rendering server system then uploads the set of media content item segments to a segment database; and updates segment states in a segment state database to indicate that the set of media content item segments are available. Other embodiments are disclosed herein.

Video generation system to render frames on demand using a fleet of GPUS

Systems and methods are provided for receiving a plurality of customized avatars where each customized avatar within the plurality of customized avatars include a first and second image layer. The first image layer includes input of text data overlaid on top of the second image layer, and the second image layer includes a personalized avatar. The system and method further includes receiving a modification of the input of text data from a text interface, generating a third image layer including a representation of text data associated with the modification of the input of text data, removing the first image layer from each of the customized avatars and overlaying the third image layer on top of the second image layer of each of the customized avatars.

Customizable avatar modification system

Method to generate frames on demand starts with a system receiving a request for a media content item from a client device. The request includes a media content identification and a main user identification. The system transmits to the client device a playlist including a first set of media content item segments. While the first set of media content item segments is being displayed on the client device, the system renders a second set of media content item segments using the media content identification and the main user identification. Rendering the second set of media content item segments can include rendering a main user avatar based on the main user identification and incorporating the main user avatar into the second set of media content item segments. The system then updates the playlist to include the second set of media content item segments. Other embodiments are disclosed herein.

Growing community of inventors

Pickering, Canada

Bradley Kotsopoulos