Server device, method for social media platform, client device, method for generating AI profile picture, non-temporary computer-readable storage medium and computer program

Abstract

The server device provides a social media platform. The server device includes one or more processors configured to cause the client device to display the graphical user interface (GUI) of the social media platform by executing instructions stored in associated memory and sending instructions to the client device, to receive at least one image of the client device's user face and at least one predetermined style selection via the GUI, to generate a plurality of artificial intelligence (AI) profile pictures via an AI model using the at least one image and the at least one predetermined style as input, and to send the plurality of AI profile pictures to the client device.

Description

Cross - reference to related applications

[0001] This application claims priority to U.S. Provisional Patent Application No. 63 / 498,268, filed on April 25, 2023, and U.S. Patent Application No. 18 / 355,345, filed on July 19, 2023, the entire contents of which are incorporated herein by reference for all purposes.

Background Art

[0002] Social media platforms typically associate avatars, user icons, profile pictures, etc. with user accounts. These images distinguish users. This is useful when a user adds another user to their friend network, browses a list of users, or identifies who is posting in the user's feed. Usually, when a user has not uploaded or selected a profile picture associated with their account, a default icon is used, and in some systems, the user may be allowed to select from pre - set stock avatars. In particular, casual users of social media platforms may be less inclined to select an image or take and upload a photo of their face for public display. Without a distinguishable profile picture, such users with default icons are less likely to form connections with other users, and as a result, are highly likely to reduce their use of the social media platform. Therefore, by encouraging users to adopt a profile picture, it is possible to improve user engagement and retention rates.

Summary of the Invention

[0003] A server device is provided that provides a social media platform. In one example, the server device includes one or more processors, which are configured to execute instructions stored in associated memory to send instructions to a client device to display the graphical user interface (GUI) of the social media platform to the client device, and to receive at least one image of the user's face and at least one predetermined style selection via the GUI. The one or more processors are configured to take the at least one image and the at least one predetermined style as input to generate a plurality of artificial intelligence (AI) profile pictures via an AI model and to send the plurality of AI profile pictures to the client device.

[0004] This summary is provided to present a simplified excerpt of the concept, which will be further described in the embodiments for carrying out the invention described below. This summary is not intended to identify the main or basic features of the claimed subject matter, nor to limit the scope of the claimed subject matter. Furthermore, the claimed subject matter is not limited to an implementation that solves any or all of the defects described in any part of this disclosure. [Brief explanation of the drawing]

[0005] [Figure 1] This is a schematic diagram of a computing system, including server equipment, that provides a social media platform.

[0006] [Figure 2] This figure shows an exemplary artificial intelligence (AI) model used by the server device shown in Figure 1 to generate a composite image.

[0007] [Figure 3] This figure shows an example of a graphical user interface (GUI) of a social media platform, displaying the user profile screen.

[0008] [Figure 4] This is a diagram showing the GUI profile editing screen.

[0009] [Figure 5] This is a diagram showing the GUI profile picture generation setup screen.

[0010] [Figure 6] This is a diagram showing the GUI style selection screen.

[0011] [Figure 7] This figure shows the GUI profile picture generation status screen.

[0012] [Figure 8] This is a diagram showing the GUI profile picture selection screen.

[0013] [Figure 9] This figure shows the profile picture selection screen in Figure 8, including additional AI profile pictures.

[0014] [Figure 10A] This figure shows an example frame displayed around the selected AI profile picture, generated by the server device shown in Figure 1.

[0015] [Figure 10B] This is a diagram illustrating an exemplary watermark displayed along with the selected AI profile picture.

[0016] [Figure 11]A diagram showing a post featuring a selected AI profile picture generated by the computing system of FIG. 1.

[0017] [Figure 12] A diagram showing an exemplary new profile picture notification featuring a selected AI profile picture.

[0018] [Figure 13] A flowchart of a method for a social media platform.

[0019] [Figure 14] A schematic diagram showing an exemplary computing environment capable of implementing the computing system of FIG. 1.

Best Mode for Carrying Out the Invention

[0020] To solve the above problem, Figure 1 shows a computing system 100 including a server device 10 that provides a social media platform 12. The server device 10 includes one or more processors 14, which execute instructions stored in associated memory 16 to realize various functions of the server device 10. The instructions may include, for example, an artificial intelligence (AI) profile picture generation module 18, a profile management module 20, and an application server program 22. One or more processors 14 may be configured to send instructions to a client device 24 to display the graphical user interface (GUI) 26 of the social media platform 12 on the client device 24. The server device 10 and the client device 24 may communicate with each other via a network 28 and one or more handlers 30 of the application server program 22. The client device 24 may be a smartphone, tablet, personal computer, etc., and includes one or more processors 32 that execute a client program 34 and display a GUI 26 on a display 36, a memory 38 for storing instructions, and one or more input devices 40 for receiving user input. The client program 34 may be a dedicated application for accessing the social media platform 12, or alternatively, a general program, such as an internet browser for accessing content from various server devices, including the social media platform 12, from the server device 10. Furthermore, the server device 10 may include multiple different servers that work together to provide the social media platform 12, or it may be a single server.

[0021] In short, the client device 24 may send a generation request 42 to the server device 10 requesting the generation of an AI profile picture. One or more processors 14 may be configured to receive the generation request 42 via the GUI 26, which includes at least one image 44 of the user's face in the client device 24 and a selection 46 (see Figure 6) of at least one predetermined style 48. One or more processors 14 may then be configured to use the at least one image 44 and at least one predetermined style 48 as input to generate a plurality of AI profile pictures 50 via an AI model, for example, a first AI model 52A. In one implementation, the AI ​​profile picture generation module 18 may include multiple models, but in other implementations, only one model may be used instead. In one implementation, the AI ​​model is a first AI model 52A, and the server device 10 may further include a second AI model 52B. In other implementations, the multiple models may additionally include another AI model 52C. Finally, one or more processors 14 may be configured to send multiple AI profile pictures 50 to a client device 24. The client device 24 may be configured, for example, to store the multiple AI profile pictures 50 in an image gallery. In this way, the user can easily and quickly receive multiple composite images that can identify the user because the user's image is used as input, and can adopt one or more of them as a profile or profile picture.

[0022] Figure 2 shows an exemplary AI model used by the server device in Figure 1 to generate a composite image. The first AI model 52A, the second AI model 52B, or any other AI model 52C may be configured according to the illustrated example. The illustrated AI model is merely an example, and any suitable generative AI model may be used. Here, the exemplary AI model is a trained machine learning model 52. An image encoder 54 is provided, which includes a pre-trained layer 54A, such as a pre-trained contrastive language-image pre-training (CLIP) vision transformer (ViT), a fine-tuning layer 54B trained to extract the user's visual features from an input image 56, such as a user image 44 of the user's face in Figure 1, and a fully connected layer 54C configured to generate a set of embeddings 58 based on the visual features of the user's face extracted by at least the fine-tuning layer 54B. In some implementations, the set of embeddings 58 may be associated with the user identifier 60 of the user of the client device 24.

[0023] A trained machine learning model 52 may include a library 62 of predetermined templates of different sets of embeddings describing different styles and / or scene information, and may be configured to accept user input 64 to select one or more styles, etc., from the library. The user input 64 and a set of embeddings 58 are provided as input to a text encoder 66, which may generate an input feature vector 68 based on at least the user input 64 and the set of embeddings 58. This input feature vector 68 may be sent to a diffusion model 70, for example, a stable diffusion model configured to generate a user's composite image 72 based on at least the input feature vector 68.

[0024] Figures 3 to 12 show various exemplary screens and images displayed by the GUI 26 in relation to the generation of an AI profile picture 50. In Figure 3, the GUI 26 displays the user profile screen 70 of user A, a user of the client device 24. User A is a new user, and not much information has been entered into the profile yet. Also, since user A has not uploaded or selected a profile picture, the default avatar 72 is displayed. One way to enter the AI ​​profile picture generation process is to select an object, such as the default avatar 72 itself, or a separate button to change the profile picture, via the user profile screen 70. Selecting the default avatar 72 or any currently used profile picture can trigger a command to edit the user's profile picture. Then, a pull-up list 74 may be displayed that includes different options for changing the default avatar 72, such as "Upload Photo," "Take Photo," and "AI Profile Picture." Selecting the AI ​​profile picture selector 76 can guide the user to the profile picture generation introduction screen 78 shown in Figure 5. Therefore, in one example, in response to a command to edit the user's profile picture, the GUI 26 may display an entry point (for example, a profile picture generation introduction screen 78) for generating the AI ​​profile picture 50. When the profile editing selector 80 is selected, a command may be sent to either the client program 34 or the profile management module 20 to open the profile editing screen 82 in the GUI 26 shown in Figure 4.

[0025] Moving to Figure 4, various editable features of the user's profile page are displayed, such as profile picture, name, and username. Similar to Figure 3, the AI ​​profile picture creation selector 84 may be displayed to guide the user to the profile picture generation introduction screen 78 in Figure 5. In this way, by placing entry points to the generation process in different locations throughout the GUI 26, interested users can choose to enter the process while browsing different screens and performing different tasks, thus allowing more users to choose to try AI profile picture generation overall.

[0026] Moving to Figure 5, the profile picture generation introduction screen 78 of GUI 26 is displayed. For example, the profile picture generation introduction screen 78 may be a partial page or popup on another screen, such as the user profile screen 70, or it may be a full-page screen. The profile picture generation introduction screen 78 may include an exit selector 86 for the user to refuse to proceed with the generation process. The screen of the profile picture generation introduction screen 78 may include several exemplary AI profile pictures 88, which may include professional examples selected for advertising, or a selection based on an algorithm of AI profile pictures of the user's friends or other related accounts. The profile picture generation introduction screen 78 may explain information about the AI ​​profile picture function, such as that a different look has been created using AI technology with the user's photo, or a guarantee that the user's photo will not be stored on the social media platform 12. In addition, the profile picture generation introduction screen 78 may provide the user with an option to start the process, i.e., enter the procedure to generate the AI ​​profile picture 50.

[0027] In the illustrated example, the AI ​​profile picture generation module 18 utilizes a first AI model 52A and a second AI model 52B for two separate and distinct paths. Here, the GUI 26 includes a first selector 90 (PLUS) that requests the generation of a first set of AI profile pictures (as multiple AI profile pictures 50) via the first AI model 52A, and a second selector 92 (LITE) that requests the generation of a second set of AI profile pictures (as multiple AI profile pictures 50) via the second AI model 52B. Generation via the first AI model 52A is slower than generation via the second AI model 52B, and the first set of AI profile pictures is greater than the second set of AI profile pictures. For example, the Plus path may use 5 to 10 user images 44 as input and complete the generation of the second set of AI profile pictures in about 20 minutes, producing 4 images as output. In contrast, the Lite path may use one user image 44 as input and complete the generation of a second set of multiple AI profile pictures in less than 30 seconds, producing 30 images as output. These are parameters that can be set considering, for example, the quality of the image output, the time deemed reasonable by the user base, the availability of model resources, and the cost. The difference in input and output between the two AI models 52A and 52B may be due to the first AI model 52A having a larger parameter size than the second AI model 52B. That is, the first AI model 52A is more complex and therefore more likely to produce the desired high-quality results, but as a trade-off, it may utilize more resources and take longer to produce results. It will be understood that other differences between the different models can be used to provide users with various options, such as using models trained on different datasets or specializing in different types of output.

[0028] Figure 6 shows the style selection screen 94 of the GUI 26. In response to receiving a selection from the first selector 90, the client device 24 may be configured to display the style selection screen 94 and proceed along the PLUS route. On the style selection screen 94, the GUI 26 may be configured to display multiple exemplary images representing a plurality of predetermined styles 48, and the user's selection of at least one of the exemplary images may constitute a selection 46 of at least one predetermined style 48. In the illustrated example, the user is allowed to select up to four styles. These styles are input as context to the first AI model 52A (see Figure 2) and affect the generated AI profile picture 50. The LITE route may present the same styles, different styles, or no styles at all. By skipping style selection by not presenting the style selection screen 94 to the user, the LITE route becomes a relatively quick option for sending results to impatient or uninterested users, and it becomes possible to prompt those users to adopt a customized profile picture if this option is not available and they might continue to use the default avatar 72. Here, the exemplary image is shown having a style name 96, but in some embodiments, it may be displayed without a text label. Upon receiving the selection of the continuation selector 98, the client device 24 may be configured to send a generation request 42 containing the user image 44 and the style selector 46 to the server device 10. Upon receipt by the server device 10, the generation request 42 is input to the associated model (here, the first AI model 52A associated with the PLUS route).

[0029] When the server device 10 starts generating profile pictures with the selected model, the profile picture generation status screen 102 of the GUI 26 may be displayed on the client device 24, as shown in Figure 7. The profile picture generation status screen 102 may include a progress meter 104 that notifies the user of the generation progress. The progress meter 104 may include either or both of the following: progress text 106 indicating the amount completed or remaining, and progress icons 108 that are filled in as generation progresses. The profile picture generation status screen 102 may also include additional information that notifies the user of what is currently happening, such as that a profile is currently being created, the time required for the process, and the number of profile pictures to be generated. In the illustrated example, the LITE path is selected instead of the PLUS path as in Figure 5. Therefore, the user can expect to receive four profile pictures in about 5 seconds. Once the progress is complete, the user can download all the generated AI profile pictures 50 by selecting the Download All selector 110. Alternatively, the user may select the Next selector 112 to proceed to the next screen of the GUI 26. If the progress is less than 100%, these selectors 110 and 112 may be displayed in gray and unavailable, as shown in the diagram.

[0030] When the selection of the Next selector 112 is accepted, the GUI 26 may be configured to display the profile picture selection screen 114 shown in Figures 8-9. Here, the user is instructed to select a desired profile picture. Thus, one or more processors 14 may further be configured to, upon receiving a selection 116 (see Figure 1) of one of several AI profile pictures 50, an AI profile picture 118, via the GUI 26, and designate the selected AI profile picture 118 as the user's current profile picture on the social media platform 12. This provides a simple way for the user to update their profile and replace the default avatar 72 or other current profile picture with a customized relevant user profile picture. If the user is satisfied with the selected AI profile picture 118, the user may proceed by selecting another Next selector 120. However, if the user is not satisfied, the GUI 26 may provide another option to satisfy the user's needs. For example, one or more processors 14 may be configured to receive requests from the user for further generation, for example, by the user selecting a further generation selector 122. Upon receiving the request, one or more processors 14 may be configured to generate additional AI profile pictures 124 via an AI model (e.g., a first AI model 52A or a second AI model 52B) and send these additional AI profile pictures 124 to the client device 24. This allows the model to attempt again to generate an image acceptable to the user without requiring the user to start the process over from the beginning. In some implementations, the GUI 26 allows the user to request the further generation up to a predetermined number of times, for example, up to two times for a total of three generation requests. The GUI 26 may be configured to display a limitation warning 126 informing the user that there are no further generation requests remaining and when new requests will be available.If the LITE route is selected first and the user does not select any of the generated AI profile pictures 50, the GUI 26 may be configured to remind the user that the PLUS route is available as an alternative.

[0031] Figures 10A and 10B show exemplary indicators displayed with the selected AI profile picture 118. It will be understood that the indicators can take various forms other than those shown. For example, GUI 26 may be configured to display the selected AI profile picture 118 with an AI profile picture indicator 128, such as a watermark 128B (see Figure 10B) or a frame 128A (see Figure 10A), indicating that the selected AI profile picture 118 was AI-generated. These indicators can help advertise the AI ​​profile picture generation feature to other users of the social media platform 12 and, in some cases, make it clear that the selected AI profile picture 118 is not an actual photograph. As shown in Figure 10A, GUI 26 may also display a suggestion 132 that encourages other users browsing user A's profile to try the AI ​​profile picture generation feature, including a link to a GUI 26 screen from which the feature can be started. The watermark 128B and / or frame 128A may be displayed under the same or different circumstances, or may be displayed permanently or for a limited time. For example, the watermark 128B may be part of the image of the selected AI profile picture 118 itself and may always be displayed together with it, or it may only be displayed when another user selects and enlarges the selected AI profile picture 118, or when the selected AI profile picture 118 is included in a post on a social media platform 12.

[0032] In some implementations, as shown in Figure 11, the GUI 26 may be configured to generate media content such as a post 134 under the user's account featuring the selected AI profile picture 118. The post 134 may be automatically generated and posted when the selected AI profile picture 118 is confirmed as the user's profile picture, or it may be generated and presented to the user for further editing and confirmation before posting. In the latter case, the user can confirm the profile picture announcement and post the profile picture to their "story" by selecting your story selector 136. Once posted, other users on other client devices 138 can view this post and the selected AI profile picture 118 and may be inspired to try the AI ​​profile picture generation function themselves. Similar announcements may be presented in various forms in different places on the social media platform 12. For example, Figure 12 shows a new profile picture notification 140 featuring the selected AI profile picture 118. The notification 140 may be presented in a notification panel, placed between posts in the user's feed, or presented elsewhere. In some cases, notification 140 may include multiple AI profile pictures 142 of one or more different users who are contacts of the user viewing it. Notification 140 may further include a "try yours" selector 144 which includes a link that directs the user to the profile picture generation introduction screen 78 in Figure 5. For this reason, the client program 34 or profile management 20 may be configured to generate media content such as a post 134 in accordance with the selected AI profile picture 118, in response to the previous user profile picture being replaced with the selected AI profile picture 118.Alternatively, the client program 34 or profile management 20 may be configured to generate media content such as a post 134 based on at least one AI profile picture 50 after generating at least one AI profile picture 50. Other generated media content may include, for example, the indicator 128 or notification 140 shown in Figures 10A and 10B.

[0033] Figure 13 shows a flowchart of Method 1300 for a social media platform according to this disclosure. Method 1300 may be implemented by the computing device 100 shown in Figure 1. In 1302, Method 1300 may include sending a command to a client device to display the graphical user interface (GUI) of the social media platform on the client device. In 1304, Method 1300 may include receiving at least one image of the face of a user of the client device and at least one selection of a predetermined style via the GUI. In 1302, Method 1300 may include generating a plurality of artificial intelligence (AI) profile pictures via an AI model using the at least one image and the at least one predetermined style as input. Thus, the user can receive a plurality of AI-generated images that can still be associated with a profile picture, while potentially feeling less embarrassing in use than actual photographs, because they are generated using the user's own face as input. In some implementations, the GUI may be configured to display multiple exemplary images representing multiple predetermined styles, and a user's selection of at least one of these exemplary images may constitute a selection of at least one predetermined style. This can provide a simple and intuitive way for the user to select a style that is most likely to produce an acceptable output.

[0034] In 1308, the AI ​​model may be a first AI model, and the GUI may include a first selector that requests the generation of a first set of AI profile pictures via the first AI model, and a second selector that requests the generation of a second set of AI profile pictures via the second AI model. Alternatively, in 1310, the AI ​​model may be a second AI model. Generation via the first AI model may be slower than generation via the second AI model, and the first set of AI profile pictures may be greater than the second set of AI profile pictures. This may be because the first AI model has a larger parameter size than the second AI model. Therefore, in 1312, using the first AI model yields more profile pictures, while in 1314, using the second AI model yields fewer profile pictures. However, other differences between the models may be utilized. By providing at least these two different paths, users can choose, based on their preferences and levels of interest, to spend more time to get better results or to sacrifice quality for a quicker turnaround. In some implementations, the method may further include generating an additional number of AI profile pictures via the AI ​​model in response to receiving a request for further generation from the user, and transmitting the additional number of AI profile pictures to the client device. And in 1316, method 1300 may also include transmitting the number of AI profile pictures to the client device.

[0035] In 1318, the method may include, upon receiving a selection of one AI profile picture from the plurality of AI profile pictures via the GUI, designating the selected AI profile picture as the user's current profile picture on the social media platform. This makes it possible to increase the proportion of users who have a recognizable and useful user profile picture associated with their profile and account on the social media platform. Accordingly, in 1322, the method may include configuring the GUI to display the selected AI profile picture, and in 1324, the selected AI profile picture may be displayed to other users with a watermark or frame indicating that the selected AI profile picture was AI-generated. This can serve to advertise the AI ​​profile picture generation feature to other users who may be interested. Another way to attract more interested users is for the GUI to be configured to generate posts under the user's account featuring the selected AI profile picture.

[0036] In some embodiments, the methods and processes described herein may be linked to a computing system of one or more computing devices. Specifically, such methods and processes may be implemented as computer application programs or services, application programming interfaces (APIs), libraries, and / or other computer program products.

[0037] Figure 14 schematically illustrates a non-limiting embodiment of a computing system 1400 capable of implementing one or more of the methods and processes described above. The computing system 1400 is shown in a simplified form. The computing system 1400 may embody the computer device 10 shown in Figure 2 as described above. The computing system 1400 may take the form of one or more personal computers, server computers, tablet computers, home entertainment computers, network computing, game devices, mobile computing devices, mobile communication devices (e.g., smartphones) and / or other computing devices, and wearable computing devices, such as smart watches and head-mounted augmented reality devices.

[0038] The computing system 1400 includes a logical processor 1402, a volatile memory 1404, and a non-volatile storage device 1406. The computing system 1400 may optionally include a display subsystem 1408, an input subsystem 1410, a communication subsystem 1412, and / or other components not shown in Figure 14.

[0039] The logical processor 1402 includes one or more physical devices configured to execute instructions. For example, the logical processor may be configured to execute instructions that are part of one or more applications, programs, routines, libraries, objects, components, data structures, or other logical structures. Such instructions may be implemented to perform tasks, realize data types, transform the state of one or more components, achieve technical effects, or otherwise achieve desired results.

[0040] A logical processor may include one or more physical processors (hardware) configured to execute software instructions. Additionally or alternatively, a logical processor may include one or more hardware logic circuits or firmware devices configured to execute hardware-implemented logic or firmware instructions. The processor of the logical processor 1402 may be single-core or multi-core, and the instructions executed thereon may be configured for sequential, parallel, and / or distributed processing. Individual components of the logical processor may optionally be distributed across two or more separate devices located remotely and / or configured for coordinated processing. Embodiments of the logical processor may be virtualized and executed by computing devices connected to a remotely accessible network configured in a cloud computing setup. In such cases, it should be understood that these virtualized embodiments run on different physical logical processors on various different machines.

[0041] The non-volatile storage device 1406 includes one or more physical devices configured to hold instructions executable by a logical processor in order to implement the methods and processes described herein. When such methods and processes are implemented, the state of the non-volatile storage device 1406 may be transformed, for example, to hold different data.

[0042] The non-volatile storage device 1406 may include removable and / or built-in physical devices. The non-volatile storage device 1406 may include optical memory (e.g., CD, DVD, HD-DVD, Blu-ray disc, etc.), semiconductor memory (e.g., ROM, EPROM, EEPROM, flash memory, etc.), and / or magnetic memory (e.g., hard disk drive, floppy disk drive, tape drive, MRAM, etc.), or other mass storage technology. The non-volatile storage device 1406 may include non-volatile, dynamic, static, read / write, read-only, sequential access, position-addressable, file-addressable, and / or content-addressable devices. It will be understood that the non-volatile storage device 1406 is configured to retain instructions even when power to the non-volatile storage device 1406 is cut off.

[0043] The volatile memory 1404 may include a physical device containing random access memory. The volatile memory 1404 is typically used by the logical processor 1402 to temporarily store information during the processing of software instructions. If power to the volatile memory 1404 is cut off, it is understood that the volatile memory 1404 will not typically continue to store instructions.

[0044] Embodiments of the logic processor 1402, volatile memory 1404, and non-volatile storage device 1406 may be integrated together in one or more hardware logic components. Such hardware logic components may include, for example, field-programmable gate arrays (FPGAs), integrated circuits for specific programs and applications (PASICs / ASICs), standard products for specific programs and applications (PSSPs / ASSPs), systems on a chip (SOCs), and complex programmable logic devices (CPLDs).

[0045] The terms “module,” “program,” and “engine” may be used to describe a form of computing system 1400 that is typically implemented in software to perform a function, which involves a conversion process that specially configures the processor to perform a specific function using a portion of volatile memory. Thus, a module, program, or engine may be instantiated using a portion of volatile memory 1404 via a logic processor 1402 that executes instructions held by a non-volatile memory 1406. It will be understood that different modules, programs, and / or engines may be instantiated from the same application, service, code block, object, library, routine, API, function, etc. Similarly, the same module, program, and / or engine may be instantiated from different applications, services, code block, object, routine, API, function, etc. The terms “module,” “program,” and “engine” may include individuals or groups such as executable files, data files, libraries, drivers, scripts, database records, etc.

[0046] The display subsystem 1408, if included, may be used to present a visual representation of the data held by the non-volatile memory 1406. This visual representation may take the form of a graphical user interface (GUI). Since the methods and processes described herein modify the data held by the non-volatile memory and transform the state of the non-volatile memory, the state of the display subsystem 1408 may also be transformed to visually represent the changes in the underlying data. The display subsystem 1408 may include one or more display devices utilizing substantially any type of technology. Such display devices may be combined with the logical processor 1402, volatile memory 1404 and / or non-volatile memory 1406 within a shared enclosure, or such display devices may be peripheral display devices.

[0047] The input subsystem 1410 may include, if included, one or more user input devices, such as a keyboard, mouse, touchscreen, or game controller, and may interact with them. In some embodiments, the input subsystem may include, and may interact with, selected natural user input (NUI) components. These components may be integrated or peripheral, and the transmission and / or processing of input actions may be handled onboard or offboard. Exemplary NUI components may include a microphone for speech and / or voice recognition, an infrared camera, color camera, stereo camera, and / or depth camera for machine vision and / or gesture recognition, a head tracker, eye tracker, accelerometer, and / or gyroscope for motion detection and / or intent recognition, an electric field sensing component for evaluating brain activity, and / or any other suitable sensors.

[0048] The communication subsystem 1412, if included, may be configured to enable communication between the various computing devices described herein and other devices. The communication subsystem 1412 may include wired and / or wireless communication devices compatible with one or more different communication protocols. In a non-limiting example, the communication subsystem may be configured to communicate via a wireless telephone network, or via a wired or wireless local or wide area network, such as HDMI® over a Wi-Fi connection. In some embodiments, the communication subsystem may enable the computing system 1400 to send and receive messages with other devices over a network such as the Internet.

[0049] The following paragraphs provide further explanation of the subject matter of this disclosure. One embodiment provides a server device that provides a social media platform, the server device including one or more processors configured to execute instructions stored in associated memory. The one or more processors of the server device are configured to send instructions to a client device causing the client device to display a graphical user interface (GUI) of the social media platform, and to receive via the GUI at least one image of a user's face and at least one selection of a predetermined style. The one or more processors are further configured to take the at least one image and the at least one predetermined style as input to generate a plurality of artificial intelligence (AI) profile pictures via an AI model, and to send the plurality of AI profile pictures to the client device. In this embodiment, additionally or alternatively, the AI ​​model may be a first AI model, the server device may further include a second AI model, and the GUI may include a first selector that requests the generation of a first plurality of AI profile pictures via the first AI model, and a second selector that requests the generation of a second plurality of AI profile pictures via the second AI model. In this embodiment, additionally or alternatively, generation via the first AI model may be faster than generation via the second AI model, and the first plurality of AI profile pictures may be fewer than the second plurality of AI profile pictures. In this embodiment, additionally or alternatively, the first AI model may have a larger parameter size than the second AI model.In this embodiment, additionally or alternatively, the one or more processors may further be configured to, upon receiving a selection of one of the multiple AI profile pictures via the GUI, designate the selected AI profile picture as the user's current profile picture on the social media platform. In this embodiment, additionally or alternatively, the GUI may be configured to display the selected AI profile picture with a watermark or frame indicating that the selected AI profile picture was AI-generated. In this embodiment, additionally or alternatively, the GUI may be configured to generate posts under the user's account featuring the selected AI profile picture. In this embodiment, additionally or alternatively, the GUI may be configured to display a plurality of exemplary images representing a plurality of predetermined styles, wherein the user's selection of at least one of the exemplary images constitutes the selection of at least one predetermined style. In this embodiment, additionally or alternatively, the one or more processors may be configured to generate additional plurality of AI profile pictures via the AI ​​model in response to receiving a request for further generation from the user, and to send the additional plurality of AI profile pictures to the client device. In this embodiment, as an addition or alternative, the GUI may be configured to allow the user to request the further generation up to a predetermined number of times.

[0050] Another embodiment provides a method for a social media platform, the method comprising: sending a command to a client device to display a graphical user interface (GUI) of the social media platform on the client device; and receiving, via the GUI, at least one image of a user's face and at least one selection of a predetermined style. The method further comprises: generating a plurality of artificial intelligence (AI) profile pictures via an AI model, taking the at least one image and the at least one predetermined style as input; and transmitting the plurality of AI profile pictures to the client device. In this embodiment, the AI ​​model may be a first AI model, and the GUI may include a first selector requesting the generation of a first plurality of AI profile pictures via the first AI model; and a second selector requesting the generation of a second plurality of AI profile pictures via a second AI model. In this embodiment, additionally or alternatively, generation via the first AI model may be faster than generation via the second AI model, and the first plurality of AI profile pictures may be fewer than the second plurality of AI profile pictures. In this embodiment, additionally or alternatively, the first AI model may have a larger parameter size than the second AI model. In this embodiment, additionally or alternatively, the method may further include, upon receiving a selection of one of the plurality of AI profile pictures via the GUI, designating the selected AI profile picture as the user's current profile picture on the social media platform. In this embodiment, additionally or alternatively, the GUI may be configured to display the selected AI profile picture with a watermark or frame indicating that the selected AI profile picture was AI-generated.In this embodiment, additionally or alternatively, the GUI may be configured to generate posts under the user's account featuring the selected AI profile picture. In this embodiment, additionally or alternatively, the GUI may be configured to display a plurality of exemplary images representing a plurality of predetermined styles, wherein the user's selection of at least one of the exemplary images constitutes the selection of at least one predetermined style. In this embodiment, additionally or alternatively, the method may further include generating an additional plurality of AI profile pictures via the AI ​​model in response to receiving a request for further generation from the user, and transmitting the additional plurality of AI profile pictures to the client device.

[0051] Another embodiment provides a client device for accessing a social media platform. The client device includes one or more processors configured to display the graphical user interface (GUI) of the social media platform by executing instructions stored in associated memory, to transmit at least one image of the client device's user face and at least one predetermined style selection via the GUI to a server device including an artificial intelligence (AI) model, and to receive from the server device a plurality of AI profile pictures generated via the AI ​​model with the at least one image and the at least one predetermined style as input.

[0052] Another embodiment provides a method for generating an AI profile picture of a social media platform user. The method includes displaying the graphical user interface (GUI) of the social media platform, displaying an entry point for generating the AI ​​profile picture in response to a command to edit the user's profile picture, and entering a procedure for generating the AI ​​profile picture. The procedure includes receiving a first input of at least one image of the user's face and a second input of at least one style, and generating at least one AI profile picture via an artificial intelligence (AI) model based on the at least one image and the at least one predetermined style. The method further includes receiving a selection of an AI profile picture from the at least one AI profile picture and replacing the user's profile picture to become the selected AI profile picture. In this embodiment, additionally or alternatively, the method may further include generating media content in response to the selected AI profile picture in response to the replacement. In this embodiment, additionally or alternatively, the method may further include generating media content based on the at least one AI profile picture after generating the at least one AI profile picture. In this embodiment, additionally or alternatively, the media content may include a link to generate an AI profile picture for another user.

[0053] It will be understood that the configurations and / or approaches described herein are illustrative in nature and are subject to numerous modifications; therefore, these specific embodiments or examples should not be considered restrictively. The specific routines or methods described herein may represent one or more of any number of processing strategies. For this reason, the illustrated and / or described operations may be performed in parallel, in any other order, or omitted, in the order illustrated and / or described. Similarly, the order of the processes described above may be changed.

[0054] The subject matter of this disclosure includes novel and non-obvious combinations and subcombinations of the various processes, systems, configurations, and other features, functions, operations, and / or characteristics disclosed herein, as well as all equivalents thereof.

[0055] Further documentation illustrating embodiments of this disclosure is attached.

Claims

1. A server device that provides a social media platform, and said server device, By executing the instruction stored in the associated memory, A command is sent to the client device to display the graphical user interface (GUI) of the social media platform on the client device. The GUI receives at least one image of the user's face and at least one selection of a predetermined style from the client device. Using the aforementioned at least one image and the aforementioned at least one predetermined style as input, a plurality of artificial intelligence (AI) profile pictures are generated via an AI model. The client device transmits the plurality of AI profile pictures. Includes one or more processors configured as follows: Server device.

2. The AI ​​model is a first AI model, and the server device further includes a second AI model. The GUI includes a first selector that requests the generation of a first plurality of AI profile pictures via the first AI model, and a second selector that requests the generation of a second plurality of AI profile pictures via the second AI model. The server device according to claim 1.

3. Generation via the first AI model is slower than generation via the second AI model, and the number of AI profile pictures in the first model is greater than the number of AI profile pictures in the second model. The server device according to claim 2.

4. The first AI model has a larger parameter size than the second AI model. The server device according to claim 2.

5. The one or more processors are further configured to, upon receiving a selection of one of the multiple AI profile pictures via the GUI, designate the selected AI profile picture as the user's current profile picture on the social media platform. The server device according to claim 1.

6. The GUI is configured to display the selected AI profile picture along with a watermark or frame indicating that the selected AI profile picture was generated by AI. The server device according to claim 1.

7. The GUI is configured to generate posts under the user account characterized by the selected AI profile picture. The server device according to claim 1.

8. The GUI is configured to display a plurality of exemplary images representing a plurality of predetermined styles, and the user's selection of at least one of the exemplary images constitutes the selection of at least one predetermined style. The server device according to claim 1.

9. The one or more processors, upon receiving a request from the user for further generation, Multiple additional AI profile pictures are generated through the aforementioned AI model. The client device is configured to send the aforementioned additional AI profile pictures. The server device according to claim 1.

10. The GUI allows the user to request further generation up to a predetermined number of times. The server device according to claim 1.

11. A method for a social media platform, the method is The steps include sending a command to the client device to display the graphical user interface (GUI) of the social media platform on the client device, The steps include receiving at least one image of the user's face of the client device and the selection of at least one predetermined style via the GUI, The steps include generating multiple artificial intelligence (AI) profile pictures via an AI model using the at least one image and the at least one predetermined style as input, The steps include transmitting the plurality of AI profile pictures to the client device, including, method.

12. The aforementioned AI model is the first AI model, The GUI includes a first selector that requests the generation of a first set of AI profile pictures via the first AI model, and a second selector that requests the generation of a second set of AI profile pictures via the second AI model. The method according to claim 11.

13. Generation via the first AI model is slower than generation via the second AI model, and the number of AI profile pictures in the first model is greater than the number of AI profile pictures in the second model. The method according to claim 12.

14. The first AI model has a larger parameter size than the second AI model. The method according to claim 12.

15. The GUI further includes the step of receiving a selection of one AI profile picture from among the plurality of AI profile pictures, and designating the selected AI profile picture as the user's current user profile on the social media platform. The method according to claim 11.

16. The GUI is configured to display the selected AI profile picture along with a watermark or frame indicating that the selected AI profile picture was generated by AI. The method according to claim 11.

17. The GUI is configured to generate posts under the user account characterized by the selected AI profile picture. The method according to claim 11.

18. The GUI is configured to display a plurality of exemplary images representing a plurality of predetermined styles, and the user's selection of at least one of the exemplary images constitutes the selection of at least one predetermined style. The method according to claim 11.

19. Upon receiving a request for further generation from the aforementioned user, The steps include generating additional AI profile pictures through the aforementioned AI model, The steps include transmitting the additional AI profile pictures to the client device, Further including, The method according to claim 11.

20. A client device for accessing a social media platform, wherein the client device is By executing the instruction stored in the associated memory, The graphical user interface (GUI) of the aforementioned social media platform is displayed. The GUI transmits to a server device including an artificial intelligence (AI) model at least one image of the user's face and at least one selection of a predetermined style from the client device. The server device receives a plurality of AI profile pictures generated via the AI ​​model, with the at least one image and the at least one predetermined style as input. Includes one or more processors configured as follows: Client device.

21. A method for generating an AI profile picture of a user on a social media platform, the method being The steps include: displaying the graphical user interface (GUI) of the social media platform; The steps include: displaying an entry point for generating the AI ​​profile picture in response to a command to edit the user's profile picture; The step of entering a procedure to generate the aforementioned AI profile picture, The steps include receiving a first input of at least one image of the user's face and a second input of at least one style, and Steps to enter into a procedure for generating an AI profile picture, which includes the step of generating at least one AI profile picture via an artificial intelligence (AI) model based on at least one image and at least one style, The steps include receiving a selection of an AI profile picture from the at least one AI profile picture, The steps include replacing the user's profile picture with the selected AI profile picture, including, method.

22. The step of generating media content according to the selected AI profile picture in response to the replacement further includes: The method according to claim 21.

23. The process further includes generating media content based on the at least one AI profile picture after generating the at least one AI profile picture. The method according to claim 21.

24. The media content includes a link for generating an AI profile picture for another user. The method according to claim 22.

25. A computer program that implements the method described in claim 11 when executed by a processor is stored. A non-temporary computer-readable storage medium.

26. It stores a computer program that implements the method described in claim 21 when executed by a processor. A non-temporary computer-readable storage medium.

Images