Text input to three-dimensional (3D) models

Abstract

A graphics-specific search engine receives a search input from a user account of a media platform, determines a search query parsed from the input, and searches a graphics-specific database for an existing image corresponding to the search query. When the search results do not exceed the predetermined number, the image generator generates a new image corresponding to the search query. A graphical display engine sends a plurality of images to an instance of an account of a media platform.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims U.S. application serial number 18 / 054,592, filed on November 11, 2022, entitled “TEXT INPUT TO THREE-DIMENSIONAL (3D) MODELS,” the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] Embodiments described herein generally relate to providing three-dimensional (3D) models to media accounts based on text input to a media platform. Background Art

[0004] There is a growing number of implementations of text-to-image generation based on both open source and proprietary solutions. Image generators receive natural language descriptors and produce images that match the input descriptors as a result of a generator that has been trained on the descriptors and images obtained from various sources, including results obtained from Internet search engines. Summary of the invention

[0005] In one example embodiment, a media platform includes a graph-specific search engine that receives a search input, determines a search query from the received search input, and searches a graph-specific database for existing images corresponding to the search query. The media platform also includes an image generator and a graph display engine, the image generator generating a new image corresponding to the search query when the search results do not exceed a predetermined number, and the graph display engine sending at least a plurality of generated new images to an instance of an account of the media platform.

[0006] According to at least one other example embodiment, a method for generating a three-dimensional (3D) model includes: receiving a search input; searching a database for a 3D model corresponding to a keyword corresponding to the search input; and displaying a plurality of 3D models corresponding to the search for selection on an instance of an account of a multimedia platform. When a result of the search is that the number of existing 3D models is less than a threshold, generating at least a portion of the displayed 3D model based on the keyword.

[0007] According to at least one other example embodiment, a non-transitory computer-readable medium has computer-executable instructions stored thereon, and when the instructions are executed, the instructions cause one or more processors to perform operations, the operations including: receiving input; parsing searchable parameters from the input; expanding the searchable parameters; searching a database for existing images corresponding to the expanded searchable parameters; when the result of the search is a number that is at least a threshold number, displaying a predetermined number of existing images for selection on an instance of a social media account; when the result of the search is a number that is less than the threshold number, generating new images based on the expanded searchable parameters; and displaying a predetermined number of generated new images for selection on the social media account. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In the following detailed description, the embodiments are described for illustration only, since various changes and modifications will become apparent to those skilled in the art from the following detailed description.The use of the same reference numerals in different drawings indicates similar or identical items.

[0009] Figure 1 A system in which text input to a 3D model may be implemented is shown, arranged in accordance with at least some embodiments described and documented herein;

[0010] Figure 2 is a schematic diagram of a storage device / database utilized in implementing text input to a 3D model, arranged in accordance with at least some embodiments described and documented herein;

[0011] Figure 3 An example process flow for implementing text input to a 3D model according to at least some embodiments described and documented herein is shown;

[0012] Figure 4 An illustrative computing embodiment is shown in which any process and sub-process of obtaining a 3D model based on text input can be implemented as executable instructions stored on a non-transitory computer-readable medium. DETAILED DESCRIPTION

[0013] In the detailed description that follows, reference is made to the drawings that form part of the description. In the drawings, similar symbols generally identify similar components, unless the context dictates otherwise. In addition, unless otherwise stated, the description of each subsequent drawing may reference features from one or more previous drawings to provide a clearer context and substantive explanation of the current example embodiment. Nevertheless, the example embodiments described in the detailed description, drawings, and claims are not intended to be limiting. Other embodiments may be utilized, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein. It will be readily understood that the various aspects of the present disclosure, as generally described and recorded herein and as shown in the drawings, may be arranged, replaced, combined, separated, and designed in a variety of different configurations, all of which are clearly intended herein.

[0014] In addition, various parts of the present disclosure may be described in this article according to functional block components and various processing steps. It should be understood that such functional blocks can be implemented by any number of hardware components and / or software components configured to perform the specified functions.

[0015] In the descriptions and notes presented, in addition to their generally accepted meanings, the following terms may be used as described below.

[0016] Reference is made herein to techniques associated with learned or trained computers or processors, by which decisions and / or actions are made autonomously, rather than by human intervention. These techniques include software (i.e., algorithms and / or programs), hardware or firmware, or any combination thereof, that supports machine learning, natural language understanding, natural language processing, speech recognition, computer vision, etc. Also included in the scope of functionality and capabilities are image generation associated with the embodiments disclosed, documented, and suggested herein. By image generation, an image or model is generated based on an input. A 3D model is among the generated images contemplated by the non-limiting embodiments disclosed, documented, and suggested herein. The example embodiments also utilize text input, although utilizing audio input or image input is also within the scope of these embodiments.

[0017] A generated image may refer to a potential representation of a user input or machine input to an enabled computer or processor. The generated image is produced by an enabled computer or processor that has been trained on a large number of images corresponding to input (whether text, audio, or image) retrieved from various sources, including defined or general searches from various Internet resources. According to at least some embodiments, the generated image is also produced by expanding, supplementing, or otherwise augmenting at least a portion of the user input or machine input with appropriately classified descriptors.

[0018] Algorithms and procedures for creating images (including 3D models) are known in the art; furthermore, the aforementioned descriptors are matched or corresponded to the input or a portion thereof based on known learning techniques.

[0019] As disclosed and documented herein, a social media application may refer to an online application that allows users holding accounts to interact with each other using a variety of media at a variety of scales, wherein such interactions include creating and / or sharing media content. As disclosed and documented herein, a user's device may have an instance of a locally stored social media application account, or the user's account may be accessed via a web-based version of a particular social media application.

[0020] As disclosed and documented herein, a platform (e.g., a social media platform) may refer to an application on which algorithms and / or programs capable of executing or implementing a series of communication-based technologies or media sharing technologies may be hosted. Non-limiting examples of these technologies may include the creation, sharing, and / or storage of multimedia products.

[0021] As referred to herein, a media or multimedia product or experience may include, but is not limited to, recorded or live transmittable content, including text, audio, images, animation, video, etc. In addition, such a product or experience may also include, but is likewise not limited to, an interactive augmented reality (AR) experience and / or an interactive virtual reality (VR) experience.

[0022] As referred to herein, augmented reality (AR) may refer to one or more interactive reality-based display environments that utilize computer-generated displays, sounds, text, and other sensory-driven effects to enhance a user's experience. AR integrates digital information into the user's real-world environment.

[0023] As referenced herein, virtual reality (VR) may refer to one or more interactive reality-based display environments that utilize computer-generated displays, sounds, text, and other sensory-driven effects to enable a user to experience and manipulate the surrounding environment as if in a real-world environment. VR provides sensory stimulation that is combined with the user's physical movements to affect the corresponding digital environment.

[0024] As disclosed, documented, and / or suggested herein, an engine or generator may refer to software, firmware, hardware, or any combination thereof that facilitates the generation of source code or markup for generating an element that initiates another process. Additionally or alternatively, an engine or generator may facilitate an automated process in which various software elements interact to produce a desired product, whether a physical product or a virtual product. The engines or generators disclosed, documented, and / or suggested herein are trained according to a unimodal or multimodal training model, according to known machine learning techniques.

[0025] As disclosed, described and / or suggested herein, a 3D (three-dimensional) image or model may refer to a single image or image model that may combine multiple viewpoints simultaneously. 3D imaging is known in the art.

[0026] Figure 1 A system in which the input to a 3D model can be implemented is shown, arranged according to at least some embodiments described and recorded herein. As shown, system 100 includes at least a media platform 105, and media platform 105 includes at least a storage device / database 110, a search engine 115, an image generator 120, and a display engine 125. System 100 also includes a device 130, and device 130 can host or access an instance of a user account 135 corresponding to media platform 105. Although shown as discrete components, various components can be divided into more components, combined into fewer components, or eliminated together while being expected to be within the scope of the disclosed subject matter. Those skilled in the art will appreciate that each function and / or operation of a component can be implemented individually and / or collectively by a variety of hardware, software, firmware, or any combination thereof.

[0027] The media platform 105 may refer to one or a group of servers on which one or more algorithms and / or programs designed, programmed, or otherwise configured to perform or implement various media-related technologies are hosted. A non-limiting example embodiment of the media platform 105 is provided as a social media platform. Thus, the media platform 105 may provide a variety of services, including providing recorded or live content and interactive AR or VR experiences to accounts 135 hosted or accessed on the device 130.

[0028] Storage / database 110 may refer to algorithms, programs, components, and / or modules hosted on media platform 105 or remotely and communicatively corresponding to media platform 105. Storage / database 110 may be designed, programmed, or otherwise configured to receive and store queries and / or search terms corresponding to input 140 received from account 135 at platform 105.

[0029] Storage device / database 110 and / or search engine 115 can be trained, designed, programmed or otherwise configured to parse one or more search parameters, such as keywords and / or relevant physical features, from input 140. According to at least some embodiments, the parsed search parameters (i.e., keywords) are used as the basis for image searches. With respect to such embodiments, the parsed search parameters can be classified according to known techniques and stored in storage device / database 110.

[0030] According to non-limiting example embodiments described and documented herein, storage device / database 110 may also be trained, designed, programmed or otherwise configured to store and / or retrieve graphic images (e.g., at least 3D models generated by image generator 120) for display.

[0031] Search engine 115 may refer to an algorithm, program, component, and / or module hosted on media platform 105 or remotely and communicatively corresponding to media platform 105. Search engine 115 may be trained, designed, programmed, or otherwise configured to receive input 140 from account 135 and search the content of storage / database 110 for content, e.g., 3D models, that matches or otherwise corresponds to at least one search parameter parsed from input 140 from account 135. Input may be received directly from input 140 or, according to at least some embodiments, from storage / database 110.

[0032] According to at least some non-limiting example embodiments described, documented, and suggested herein, search engine 115 and / or storage device / database 110 are also trained, designed, programmed, or otherwise configured to augment, supplement, or otherwise extend at least one search parameter parsed from input 140 received from account 135 using appropriately categorized descriptors. Thus, search engine 115 and / or storage device / database 110 are able to expand the scope of stored content to be searched and / or retrieved for display.

[0033] Image generator 120 may refer to a trained algorithm, program, component, and / or module hosted on media platform 105 or remotely and communicatively corresponding to media platform 105. Image generator 120 may be designed, programmed, or otherwise configured to newly generate an image corresponding to at least one search parameter parsed from input 140 received from account 135. According to various embodiments disclosed, described, and suggested herein, image generator 120 may receive parsed search parameters from storage device / database 110 that have been augmented, supplemented, or otherwise expanded before generating a new image.

[0034] That is, based on known iterative training techniques, the storage device / database 110 is populated with and stores a library of categories of queries and / or search terms and descriptors corresponding to each query / term. Therefore, when keywords or other parameters are parsed from the input 140 and corresponding descriptors are attached or otherwise attached thereto, the image generator 120 newly generates an image that matches or corresponds to the query / term that has been expanded, supplemented, or otherwise extended. According to at least some embodiments, when the storage device / database 110 has less than a threshold number (e.g., 30) of search results for matching or otherwise corresponding existing images, the generation of a new image is run or performed based on the input 140 or the query / term that has been expanded, supplemented, or otherwise extended.

[0035] The display engine 125 may refer to a trained algorithm, program, component, and / or module hosted on the media platform 105 or remotely and communicatively corresponding to the media platform 105. The display engine 125 may be designed, programmed, or otherwise configured to execute instructions to display content retrieved from the storage device / database 110 when the number of existing images matching or otherwise corresponding to at least a portion of the input 140 received from the account 135 or a query / term that has been augmented, supplemented, or otherwise expanded is equal to or greater than a threshold value (e.g., 30). The scale of the threshold value may be dynamic depending on user context, user preferences, display capabilities, local storage capacity, etc. Additionally or alternatively, the display engine 125 may be designed, programmed, or otherwise configured to execute instructions to display content generated by the image generator 120.

[0036] Device 130 may refer to one or more embodiments of a classical computing environment, which may be or include a classical computer, processing device, microprocessor, microcontroller, digital signal processor, or any combination thereof on which account 135 or its instances are assembled, managed, compiled, and / or executed. Device 130 may be one of or a combination of various electronic devices having one or more display screens with audio and / or video input / output and supporting the provision and consumption of content related to media platform 105. The various electronic devices may include, but are not limited to, smartphones, tablet computers, laptop computers, desktop computers, e-book readers, MP3 (moving picture experts group audio layer III, moving picture experts group audio layer III) players, MP4, and / or any other suitable electronic devices.

[0037] Any one or more servers or server clusters and devices 130 on which the media platform 105 is hosted may refer to a high-performance computing (HPC) environment that includes at least a CPU and a GPU present on, for example, a video card, embedded on a motherboard or a CPU die. As disclosed and recorded herein, the conversion of the input (e.g., text) of the 3D model may be performed entirely on the CPU, or partially on the CPU and GPU. Alternative embodiments may be performed in an evolved HPC component known in the art. In any case, the CPU, GPU, and / or HPC component may store one or more algorithms and / or programs, which, when executed thereon, may cause the operation and / or execution of the operations and / or functions disclosed and / or recorded herein. In addition, a computer-readable non-volatile medium may be provided according to the embodiments described herein. The computer-readable medium stores a computer program, which, when executed by a processor, is used to run or execute operations or functions associated with at least the embodiments described and recorded herein.

[0038] According to at least some embodiments disclosed and described herein, input 140 may refer to text, audio, or images that are manually or automatically entered into an appropriate input interface corresponding to an instance of account 135. Input 140 may be transmitted or otherwise delivered to a receiving component corresponding to media platform 105 via a wired network or a wireless network. Such a network may be viewed as a medium provided as a two-way communication link between media platform 105 and device 130. The network may include the Internet, a local area network (LAN), a wide area network (WAN), a local interconnect network (LIN), a localized cloud, and the like.

[0039] Figure 2Schematic diagram of a storage device / database 110 utilized when implementing input to a 3D model, arranged in accordance with at least some embodiments described and recorded herein. As shown, the storage device / database 110 includes at least a query library 205 and an image library 210. The query library 205 includes category sub-libraries 215A-215N and corresponding descriptor sub-libraries 220A-220N. It will be understood by those skilled in the art that the number of libraries and sub-libraries referenced herein is not limited to the number shown in the figure, as "N" is intended to imply an unlimited number. In addition, unless the context dictates otherwise, references to "category library 215" and / or "descriptor library 220" may be made in the singular or plural without excluding any other instances thereof. It will also be understood that each storage function and / or operation of the various libraries or storage components may be implemented individually and / or collectively by a variety of hardware, software, firmware, or any combination thereof.

[0040] The query library 205 may be designed, configured or otherwise programmed to receive the input 140, whether intact, parsed, or expanded, supplemented or otherwise extended. If the expansion, supplementation or extension of the parsed search parameters is performed on the storage device / database 110, the expanded parameters are assigned to or otherwise stored in one of the category libraries 215 based on known training techniques.

[0041] The query library 205 may also be designed, configured or otherwise programmed to augment, supplement or otherwise extend the categorized parsed search parameters with descriptors from an appropriately corresponding one of the libraries 220 .

[0042] Library 210 may refer to one or more sub-libraries that receive and / or store images subject to searches by search engine 115. Descriptors may be retrieved from a variety of sources, including results from one or more Internet search engines.

[0043] According to a non-limiting example, if the input 140 is "armchair furniture", the search engine 115 and / or the storage device / database 110 (whether alone or in combination) can parse "armchair" from the input 140, as an example, "armchair" corresponds to the category N 215N; and "armchair" is expanded, supplemented or otherwise extended with the descriptor N in the sub-library 220N. Therefore, the search engine 115 and / or the storage device / database 110 is able to expand the scope of the content stored in the library 210, which stores, for example, 3D models of armchairs. Non-limiting examples of expanded queries / search terms can include "purple armchair", "oak armchair", "60s style armchair", "contemporary style armchair", etc. The search engine can then search the library 210 or the corresponding portion of the sub-library 210N for images that match or otherwise correspond to the expanded query / search term. This example is not limiting. For example, if the input 140 is "armchair furniture", the search engine 115 and / or the storage device / database 110 may alternatively parse "furniture" from the input "140", which may correspond to another category of categories A to N. Furthermore, with respect to any of the non-limiting example embodiments, the parsed search terms may correspond to multiple categories of categories A to N.

[0044] Figure 3 An example process flow for implementing input to a 3D model according to at least some embodiments described and documented herein is shown. As shown, process flow 300 includes subprocesses performed by various components of system 100 including media platform 105. However, process flow 300 is not limited to these components and processes, as significant modifications may be made by reordering two or more of the subprocesses described herein, deleting at least one subprocess, adding more subprocesses, replacing components, or even having various components assume subprocessing roles consistent with other components in the following description.

[0045] According to at least a non-limiting example embodiment for implementing processing of an input of a 3D model, Figure 1 and Figure 2 The various components or modules are trained, designed, programmed or otherwise configured to: receive text search input from an instance of an account of the multimedia platform; expand keywords from the received text search input; search a database for existing three-dimensional (3D) models corresponding to the expanded keywords; and display multiple existing 3D models corresponding to the expanded keywords for selection on the instance of the account of the multimedia platform.

[0046] According to at least one other non-limiting example embodiment, Figure 1 and Figure 2The various components or modules are trained, designed, programmed or otherwise configured to: receive input from a user interface of a social media account; parse at least one searchable parameter from the received input; expand at least one searchable parameter; search a database for existing images corresponding to the expanded at least one searchable parameter; when the result of the search is that the number of existing images is at least a threshold number, display a predetermined number of existing images for selection on the social media account; additionally or alternatively, when the result of the search is that the number of existing images is less than the threshold number, generate new images based on the expanded at least one searchable parameter, and display a predetermined number (e.g., 15) of the generated new images for selection on the social media account.

[0047] Processing flow 300 may include various operations, functions, or actions as shown in one or more of blocks 305, 310, 315, 320, 325, 330, 335, 340, and 345. These various operations, functions, or actions may correspond, for example, to software, program codes, or program instructions executable by a digital processor that cause the functions to be performed. Processing may begin at block 305.

[0048] At block 305 (Receive Input), storage device / database 110 and / or search engine 115 receives and / or stores input 140 from account 135. Processing may proceed to block 310.

[0049] At block 310 (Parse Searchable Parameters), the storage device / database 110 and / or search engine 115 parses one or more search parameters, such as keywords and / or relevant physical features, from the received input. The parsed search parameters (i.e., keywords) can be used as a basis for image searching, and then classified according to known techniques and stored in an appropriate one of the libraries 215. Processing can proceed to block 315.

[0050] At block 315 (Expand Searchable Parameters), the storage device / database 110 and / or search engine 115 expands, supplements, or otherwise extends the parsed search parameters with appropriately categorized descriptors stored on the storage device / database 110. Processing may proceed to block 320.

[0051] At block 320 (Search Existing Images), the search engine 115 searches for existing images that match or otherwise correspond to the expanded search parameters, such as 3D models stored on the storage device / database 110 . Processing may proceed to decision block 325 .

[0052] At decision block 325 (pre-existing images>threshold), the search engine 115 may determine whether the number of existing images (e.g., 3D models stored on the storage device / database 110) that match or otherwise correspond to the expanded search parameters exceeds a threshold. The scale of the threshold is dynamic, depending on user context, user preferences, display capabilities, local storage capacity, etc. If the determination at decision block 325 is "yes," processing may proceed to block 330; but if the determination at decision block 325 is "no," processing may proceed to block 340.

[0053] At block 330 (display existing images), the display engine 125 displays the content retrieved from the storage device / database 110 for viewing and / or selection by the user corresponding to the account 135. When the number of existing images that match or otherwise correspond to the expanded search parameters is equal to or greater than a threshold, the retrieved content is displayed. According to at least some example embodiments, the existing images are displayed based on a popularity or likeness ranking determined by previous use or selection by a community of user accounts 135 that are also able to access content on the storage device / database 110. The popularity or likeness within the aforementioned community can relate to the most frequently utilized images in videos posted on the platform. Processing can proceed to block 335.

[0054] At block 335 (Store Images), upon display and / or selection or use by account 135, the displayed images are also stored in storage device / database 110, arranged to be retrievable by ranking or popularity. The order or sequence of the storage of the images corresponds to the popularity or popularity ranking of the images, which may be based on the selection made during execution at block 330.

[0055] At block 340 (Generate New Image), the image generator 120 generates a new image corresponding to the expanded search parameters received from the storage device / database 110 .

[0056] According to some non-limiting example embodiments, when the determination at decision block 325 is “no,” block 340 is executed. However, according to some alternative embodiments, block 340 may be executed serially or sequentially with the block 330 being executed. Regardless, processing may proceed to block 345.

[0057] At block 345 (Display New Image), display engine 125 displays the newly generated content by image generator 120. Processing may proceed to block 335.

[0058] At block 335 (Store Image), upon display and / or selection or use of the newly generated image by account 135, the new image is stored in storage device / database 110. The order or sequence of storage of the images corresponds to the popularity or likeness ranking of the images based on the selection made during execution at block 340. Likewise, the popularity or likeness of others within the aforementioned community may relate to the images most frequently utilized in videos posted on the platform.

[0059] Once the existing images and / or newly generated images are stored, the existing images may then be displayed based on popularity or likeness ranking based on previous use or selection by a community of user accounts 135 that are also able to access content on the storage device / database 110, according to block 335.

[0060] Figure 4 An illustrative computing embodiment is shown, in which any process and sub-process of obtaining a 3D model based on text input can be implemented as executable instructions stored on a non-transitory computer-readable medium. The computer-readable instructions can be executed, for example, by a processor of a device as referenced herein, the device having a network element corresponding thereto and / or any other device, particularly suitable for the above-mentioned application and / or program corresponding to the system 100 for obtaining a 3D model based on text input.

[0061] In a very basic configuration, computing device 400 may typically include at least one or more processors 402 , memory 404 , one or more input components 406 , one or more output components 408 , a display component 410 , computer-readable media 412 , and a transceiver 414 .

[0062] Processor 402 may refer to, for example, a microprocessor, a microcontroller, a digital signal processor, or any combination thereof.

[0063] The memory 404 may refer to, for example, a volatile memory, a non-volatile memory, or any combination thereof. The memory 404 may store therein an operating system, one or more applications corresponding to the media platform 105, and / or program data thereof. That is, the memory 404 may store executable instructions to implement any of the above functions or operations, and therefore, the memory 404 may be regarded as a computer-readable medium.

[0064] Input component 406 may refer to a built-in or communicatively coupled keyboard, touch screen, or telecommunication device. Alternatively, input component 406 may include a microphone configured to receive voice commands from a user of computing device 400 in cooperation with a voice recognition program that may be stored in memory 404. Furthermore, if not built into computing device 400, input component 406 may communicate with the user via a short-range communication protocol (including, but not limited to, radio frequency or ) and is communicatively coupled to computing device 400.

[0065] Output component 408 may refer to a component or module built into or removable from computing device 400 that is configured to output commands and data to an external device.

[0066] Display component 410 may refer to, for example, a solid-state display that may have touch input capabilities. That is, display component 410 may include capabilities that may be shared with input component 406, or may replace the capabilities of input component 406.

[0067] Computer readable medium 412 may refer to a detachable machine-readable medium configured to store one or more programs embodying any of the functions or operations described above. That is, the computer readable medium 412 that can be received into a drive component of the computing device 400 or otherwise connected to a drive component of the computing device 400 can store executable instructions to implement any of the functions or operations described above. These instructions may be complementary or otherwise independent of the instructions stored by the memory 404.

[0068] The transceiver 414 may refer to a network communication link of the computing device 400 configured as a wired network or a direct wired connection. Alternatively, the transceiver 414 may be configured as a wireless connection, for example, a radio frequency (RF), Bluetooth and other wireless protocols.

[0069] It will be understood from the foregoing that various embodiments of the present disclosure have been described herein for illustrative purposes, and that various modifications may be made without departing from the scope and spirit of the present disclosure. Accordingly, the various embodiments disclosed herein are not intended to be limiting, with the true scope and spirit being indicated by the appended claims.

[0070] aspect

[0071] Aspect 1: A media platform, comprising:

[0072] Graph-specific search engine for:

[0073] Receive search input,

[0074] determining a search query from the received search input, and

[0075] searching the graphics-specific database for existing images corresponding to the expanded search query;

[0076] an image generator for generating a new image corresponding to the search query when the search results do not exceed a predetermined number; and

[0077] A graphics display engine is configured to send at least a plurality of generated new images to an instance of an account of a media platform.

[0078] Aspect 2: The media platform according to Aspect 1, wherein the graphic display engine is further configured to send at least some of the existing images to an instance of an account of the media platform.

[0079] Aspect 3: The media platform according to aspect 1 or aspect 2, wherein the image generator is a three-dimensional (3D) image generator.

[0080] Aspect 4: The media platform according to any of aspects 1-3, wherein existing images and new images are stored in a storage system for use and sorted by popularity.

[0081] Aspect 5: The media platform of any one of aspects 1-4, wherein the search query is expanded.

[0082] Aspect 6: A method for generating a three-dimensional (3D) model, comprising:

[0083] Receive text search input;

[0084] searching the database for a 3D model corresponding to the keyword corresponding to the expanded search input; and

[0085] displaying a plurality of existing 3D models corresponding to the expanded keyword for selection on an instance of an account of a multimedia platform;

[0086] Wherein, when the result of the search is that the number of existing 3D models is less than a threshold, at least some of the displayed 3D models are generated based on the keyword.

[0087] Aspect 7: The method according to aspect 6, wherein the search input is in text form, and the keyword is expanded from the received text search input.

[0088] Aspect 8: The method according to Aspect 6 or Aspect 7, wherein the multimedia platform is a social media platform.

[0089] Aspect 9: The method according to any one of Aspects 6-8, wherein the multimedia platform is a virtual reality (VR) platform.

[0090] Aspect 10: The method according to any one of aspects 6-9, wherein the 3D model is generated by an image generator.

[0091] Aspect 11: The method according to any one of Aspects 6 to 10, wherein when the result of the search is that the number of existing 3D models is less than a threshold, the method further comprises:

[0092] transmitting the expanded keywords to an image generator; and

[0093] Displays a 3D model including existing images and generated new images.

[0094] Aspect 12: The method according to any one of aspects 6-11, wherein the display of the 3D models is sorted by matching attributes and popularity.

[0095] Aspect 13: The method according to any one of aspects 6-12, wherein the displaying of the existing 3D model and the displaying of the new 3D model are performed on a social media platform.

[0096] Aspect 14: The method according to any one of Aspects 6-12, wherein the displaying of the existing 3D model and the displaying of the new 3D model are performed on a VR media platform.

[0097] Aspect 15: A non-transitory computer-readable medium having computer-executable instructions stored thereon, which instructions, when executed, cause one or more processors to perform operations, the operations comprising:

[0098] Receive input;

[0099] parsing at least one searchable parameter from the received input;

[0100] Expand at least one searchable parameter;

[0101] searching the database for existing images corresponding to the expanded at least one searchable parameter;

[0102] If the result of the search is that the number of existing images is at least a threshold number, displaying a predetermined number of existing images for selection on the instance of the social media account;

[0103] When the result of the search is that the number of existing images is less than a threshold number, generating a new image based on the expanded at least one searchable parameter; and

[0104] A predetermined number of generated new images are displayed for selection on the social media account.

[0105] Aspect 16: The computer-readable medium of aspect 15, wherein the received input is textual input.

[0106] Aspect 17: The computer-readable medium of aspect 15, wherein the received input is in an audio format.

[0107] Aspect 18: The computer-readable medium of any of Aspects 15-17, wherein the database stores existing images and new images for use and ranking by other accounts on the same platform as the social media account.

[0108] Aspect 19: The computer-readable medium according to any one of aspects 15-18, wherein the existing image and the generated new image are 3D models generated by an image generator.

[0109] Clause 20: The computer-readable medium of any one of clauses 15-19, wherein the predetermined number of existing images are displayed according to a ranking protocol.

[0110] Aspect 21: The computer-readable medium of aspect 20, wherein the ranking protocol is based on a number of uses of corresponding ones of the existing images by at least some other accounts on the same platform as the social media account.

Claims

1. A media platform, include: Graph-specific search engine for: Receive search input, determining a search query from the received search input, searching the graphics-specific database for existing images corresponding to the search query; an image generator for generating a new image corresponding to the search query when the results of the search do not exceed a predetermined number; as well as A graphics display engine is configured to send at least a plurality of the generated new images to an instance of an account of the media platform.

2. The media platform of claim 1, wherein the graphics display engine is further configured to send at least some of the existing images to the instance of the account of the media platform.

3. The media platform of claim 1, wherein the image generator is a three-dimensional (3D) image generator.

4. The media platform of claim 1, wherein the existing images and the new images are stored in a storage system for use and sorted by popularity.

5. The media platform of claim 1, wherein the search query is expanded.

6. A method for generating a three-dimensional 3D model, include: Receive search input; searching a database for a 3D model corresponding to a keyword corresponding to the search input; as well as displaying a plurality of 3D models corresponding to the search for selection on an instance of an account of the multimedia platform; Wherein, if the result of the search is that the number of existing 3D models is less than a threshold, at least some of the displayed 3D models are generated based on the keyword.

7. The method of claim 6, wherein the search input is in text form and the keywords are expanded from the received text search input.

8. The method of claim 6, wherein the multimedia platform is a social media platform.

9. The method according to claim 6, wherein the multimedia platform is a virtual reality (VR) media platform.

10. The method of claim 6, wherein the 3D model is generated by an image generator.

11. The method according to claim 10, wherein if the result of the search is that the number of existing 3D models is less than a threshold, the method further include: transmitting the keyword to the image generator; as well as The 3D model including the existing image and the generated new image is displayed.

12. The method of claim 11, wherein the display of the 3D models is sorted by matching attributes and popularity.

13. The method of claim 11, wherein the displaying of the existing 3D model and the displaying of the new 3D model are performed on a social media platform.

14. The method according to claim 11, wherein the displaying of the existing 3D model and the displaying of the new 3D model are performed on a VR media platform.

15. A non-transitory computer-readable medium having computer-executable instructions stored thereon, the instructions, when executed, causing one or more processors to perform operations, the operations include: Receive input; parsing at least one searchable parameter from the received input; expanding the at least one searchable parameter; searching the database for an existing image corresponding to the expanded at least one searchable parameter; If a result of the search is that the number of existing images is at least a threshold number, displaying a predetermined number of existing images for selection on an instance of a social media account; If the result of the search is that the number of the existing images is less than the threshold number, generating a new image based on the expanded at least one searchable parameter; as well as A predetermined number of the generated new images are displayed for selection on the social media account.

16. The computer-readable medium of claim 15, wherein the input received is textual input.

17. The computer-readable medium of claim 15, wherein the database stores the existing images and the new images for use and ranking by other accounts on the same platform as the social media account.

18. The computer-readable medium of claim 17, wherein the existing image and the generated new image are 3D models generated by an image generator.

19. The computer-readable medium of claim 17, wherein the predetermined number of existing images are displayed according to a sorting protocol.

20. The computer-readable medium of claim 19, wherein the ranking protocol is based on a number of uses of corresponding ones of the existing images by at least some other accounts on the same platform as the social media account.

Images