System

A system comprising:

• a communication interface including a network interface controller coupled to a packet-switched network and configured to transmit and receive data packets;
• a memory storing instructions, a convolutional neural network model for feature extraction, a natural language processing model, and a generative neural network model;
• and
• circuitry comprising one or more processors coupled to the memory and configured to execute the instructions to:
• receive, via the communication interface, image data of a user from a terminal device and natural language input data representing a desired appearance attribute;
• extract feature data from the image data using the convolutional neural network model, the feature data including contour information and feature point coordinates;
• extract style attribute data from the natural language input data using the natural language processing model, and transmit a prompt data structure encoding the style attribute data to the generative neural network model to receive structured attribute information;
• generate a three-dimensional model based on the feature data and the structured attribute information by constructing polygon mesh geometry and applying shading and texturing;
• superimpose the three-dimensional model on the image data and transmit a composite display data structure to the terminal device via the communication interface;
• generate a plurality of candidate three-dimensional models by varying at least one parameter of the structured attribute information and transmit the candidates to the terminal device;
• and
• transmit data representing a selected candidate three-dimensional model and the corresponding structured attribute information to a second terminal device via the communication interface.

A method performed by circuitry of a server coupled to a packet-switched network via a communication interface, the method comprising:

• receiving, via the communication interface, image data of a user from a terminal device and natural language input data representing a desired appearance attribute;
• analyzing the image data to extract feature data of the user;
• analyzing the natural language input data to extract style attribute data;
• generating a three-dimensional model based on the feature data and the style attribute data;
• superimposing the three-dimensional model on the image data and transmitting a composite display data structure to the terminal device via the communication interface;
• presenting a plurality of candidate three-dimensional models to the user via the terminal device;
• and
• transmitting data representing a selected candidate three-dimensional model to a second terminal device via the communication interface.