Method for artificial intelligence (AI) content generation and electronic device

Abstract

The present application provides a method for artificial intelligence (AI) content generation and an electronic device. In the method, the electronic device can support a user in selecting a first object from among at least one object, determine, on the basis of the first object selected by the user, one or more images used for generating AI content of the first object, and then obtain AI content generated on the basis of the one or more images and comprising an AI image of the first object. In the method, the user is not required to select, from among a plurality of images, an image required for generating AI content. Instead, the user selects an object, and the electronic device automatically determines an image required for generating the AI content. Therefore, the operation is simple and convenient, the efficiency is high, and the efficiency of AI content generation can be improved.

Description

A method and electronic device for AI content generation

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202510465133.4, filed on April 14, 2025, entitled "A Method and Electronic Device for Generating Artificial Intelligence (AI) Content", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of electronic device technology, and more particularly to a method and electronic device for AI content generation. Background Technology

[0004] Currently, the application of artificial intelligence (AI) content generation (such as AI images) is becoming increasingly widespread. Some electronic devices (such as mobile phones and tablets) can generate AI images based on images selected by users in their photo albums. This method requires users to manually select images to generate AI images, and to improve the generation effect, users may even need to repeatedly select suitable images. Therefore, the operation is relatively cumbersome and inefficient, resulting in low efficiency in AI content generation. Summary of the Invention

[0005] This application provides a method and electronic device for generating AI content, in order to improve the efficiency of AI content generation.

[0006] In a first aspect, embodiments of this application provide a method for generating AI content, applied to an electronic device. The method includes: receiving a first operation; wherein the first operation is used to select a first object from at least one object; determining one or more images containing the first object based on the selected first object; and obtaining first artificial intelligence (AI) content for the first object; wherein the first AI content is generated based on the one or more images, and the first AI content includes a first AI image of the first object. Optionally, the first AI content may be generated based on feature vectors corresponding to the one or more images, wherein the feature vectors corresponding to the one or more images include some or all of the feature vectors of each of the one or more images.

[0007] In this method, the electronic device allows a user to select one object from multiple objects and automatically determines one or more images for generating AI content for that object based on the user's selection, thereby obtaining the AI ​​content for that object generated based on those one or more images. That is, the electronic device can obtain the AI ​​content for the object simply by having the user select it. This process eliminates the need for the user to select images from numerous options; instead, the user directly selects the object, and the electronic device automatically generates the necessary images. Therefore, the operation is simple, convenient, and efficient, improving the efficiency of AI content generation. Furthermore, this method allows the electronic device to automatically determine one or more suitable images based on the user's selection to generate the AI ​​content, making it easier to obtain more suitable images compared to user-selected images, thus contributing to improved AI content generation quality.

[0008] In one possible design, the method further includes: receiving user-defined generation requirements; wherein the generation requirements are used to indicate the requirements for generating AI content for the first object; the first AI content is also generated based on the generation requirements. For example, the generation requirements may include style, background, pose, face angle or face angle range, clothing, makeup, expression, emotion, the relationship between the first object and other objects, and the degree of intimacy of the relationship between the first object and other objects. The pose may include, for example, general poses such as facing forward, turning sideways, standing, or sitting, and may also include detailed poses such as the overall angle or angle range of the object.

[0009] This method supports generating AI content that users expect based on user-defined generation requirements, thereby improving the user experience.

[0010] In one possible design, the first AI content is any of the following: a still image, a moving image, or a video. Based on the above method, electronic devices can generate various types of AI content, offering high flexibility and practicality.

[0011] In one possible design, the first object is a person or an animal.

[0012] In one possible design, the first AI content is generated by the electronic device, and obtaining the first AI content of the first object includes: generating the first AI content based on the one or more images. Alternatively, the first AI content is generated by a server, and obtaining the first AI content of the first object includes: obtaining the first AI content generated by the server based on the one or more images.

[0013] In this method, electronic devices can generate AI images on their own or through a server, offering high flexibility.

[0014] In one possible design, obtaining the first AI content generated by the server based on the one or more images includes: sending a feature vector of each of the one or more images to the server, and instructing the server to generate AI content based on the feature vector of each of the one or more images; and receiving the first AI content generated by the server based on the feature vector of each of the one or more images from the server.

[0015] In the above method, electronic devices can generate AI content through a server and send as little image-related content to the server as possible. This can reduce privacy leaks in electronic devices while ensuring the generation effect, making it highly practical.

[0016] In one possible design, receiving the user-set generation request includes at least one of the following: displaying first recommended information automatically generated by the electronic device; receiving a second operation; wherein the second operation is used to instruct that the first recommended information be included in the generation request; displaying a second control; in response to an operation acting on the second control, displaying multiple settings of a first setting item; receiving a fifth operation for selecting at least one setting from the multiple settings; wherein the fifth operation is further used to instruct that the at least one setting be included in the generation request; and receiving information input by the user through a third control displayed by the electronic device for inclusion in the generation request. Optionally, the first recommended information can be displayed through a first control, and the second operation can be an operation acting on the first control.

[0017] Based on the above method, electronic devices can visualize and enrich the settings for generating requirements through at least one type of control, offering high flexibility and practicality. Furthermore, this method allows users to select or input generating requirements with simple operations, making it convenient, fast, and efficient.

[0018] In one possible design, the first recommendation information is generated based on first reference information, which includes at least one of the following: the identity information of the first object; the facial features of the first object; the relationship features between the first object and other objects; media content displayed before receiving the first operation; user input information received before receiving the first operation; and the location information of the electronic device. For example, the first recommendation information may include style, the relationship between the first object and other objects, the closeness of the relationship between the first object and other objects, emotion, clothing features, appearance features, facial expressions, etc.

[0019] In this method, the electronic device can recommend optional information that can be included in the generation requirements to the user based on at least one type of reference information, which can provide the user with a richer user experience and help improve the efficiency of setting generation requirements.

[0020] In one possible design, determining one or more images containing the selected first object includes: selecting from the images containing the first object one or more images that contain the first object and that conform to target features. Optionally, the target conditions include: the contained first object conforming to target features, and / or other conditions. Other conditions may include image clarity or image quality exceeding set requirements. The target features include at least one of the following: a first face angle or a first face angle range; a first pose; a first expression.

[0021] Based on the above method, electronic devices can automatically select reference images for generating AI content. This simplifies user operations and improves the user experience by eliminating the need for manual image selection and uploading. Furthermore, it makes it easier to select more suitable images for AI content generation, thereby enhancing the quality of the generated content. Based on this method, electronic devices can automatically select appropriate images to generate AI content that meets different requirements for different objects and / or different generation needs, demonstrating high universality and scalability. Furthermore, based on this method, electronic devices can also generate AI content with specific facial angles, poses, and / or expressions, further improving the generation effect.

[0022] In one possible design, some or all of the target features are determined based on requirements for instructing the generation of AI content for the first object. For example, the generation requirements may include a frontal face, and the target features may include a frontal face, or may include the face angle or face angle range corresponding to the frontal face. As another example, the generation requirements may include a side-view face angle, and the target features may include that side-view face angle. Yet another example is when the generation requirements may include a side-view pose, the target features may include a side-view pose. When the generation requirements include a smiling expression, the target features may include a smiling expression.

[0023] By combining the above methods, electronic devices can select the images that are more suitable for generating AI content based on the user's generation requirements, thereby generating AI content that better meets the user's requirements. Therefore, the generation effect of the above methods is better.

[0024] In one possible design, the method further includes: acquiring second AI content of the first object; wherein the second AI content is generated based on at least one image containing the first object when set conditions are met, and the second AI content includes a second AI image of the first object. Optionally, after acquiring the second AI content of the first object, the method further includes: displaying the second AI content. Optionally, displaying the second AI content includes: updating the already displayed first AI content to the second AI content. For example, in a scenario where the first AI content is displayed as wallpaper, after acquiring the second AI content, displaying the second AI content may specifically involve updating the displayed wallpaper from the first AI content to the second AI content. As another example, in a scenario where the first AI content is displayed as wallpaper, after acquiring the second AI content, displaying the second AI content may specifically involve updating the displayed avatar from the first AI content to the second AI content. Optionally, the second AI content may be displayed automatically or in response to user operation.

[0025] Based on the above method, electronic devices can automatically transform the generated AI content, thereby improving the display effect of AI content on electronic devices and enhancing the user experience.

[0026] In one possible design, the second AI content is also generated based on the stated conditions.

[0027] Based on this method, electronic devices can automatically transform AI content by referring to the triggering conditions of automatic transformation, making the transformation effect more in line with the actual situation, which helps to improve the immersion of AI content display and thus improve the user experience.

[0028] In one possible design, the setting conditions include at least one of the following: reaching a set time; being at a set location; or detecting a set event.

[0029] In this method, time, location, events, etc. can all trigger the automatic transformation of AI content displayed on electronic devices, which is rich and flexible, meets the needs of actual experience, and is highly practical.

[0030] In one possible design, the method further includes: displaying a first interface in response to a received third operation; wherein the first interface includes an element for selecting each of the at least one object; the first operation is an operation performed on a first element included in the second interface, the first element being an element for selecting the first object corresponding to the first object.

[0031] Based on the above method, electronic devices can easily and efficiently display at least one object to the user, thereby enabling the user to select the object from which AI content needs to be generated, thus improving efficiency.

[0032] In one possible design, the first element also serves to indicate the first object. Optionally, the first element is an image of the first object.

[0033] Based on the above method, electronic devices can clearly and intuitively display at least one object to the user, with good display effect and user viewing experience.

[0034] In one possible design, the third operation is an operation performed on a third interface. The third interface may be an interface provided by a system service or application in the electronic device. Optionally, the third interface includes a fourth control, and the third operation may specifically be an operation performed on the fourth control. The fourth control is used to trigger the generation of AI content.

[0035] In the above methods, electronic devices can present the interface used to trigger the generation of AI content to the user in different ways, offering a high degree of flexibility.

[0036] In one possible design, after acquiring the first AI content of the first object, the method further includes displaying the first AI content. This allows the AI ​​content acquired by the electronic device to be presented to the user.

[0037] In one possible design, before displaying the first AI content, the method further includes: receiving a fourth operation; wherein the fourth operation is used to instruct the application of the first AI content to at least one scenario; and displaying the first AI content includes: displaying the first AI content when in any of the at least one scenario.

[0038] Based on the above methods, electronic devices can apply the generated AI content to a specific scenario, making it highly targeted and allowing users to independently control the application methods in different scenarios. Alternatively, electronic devices can apply the generated AI content uniformly to multiple scenarios, resulting in high control efficiency.

[0039] In one possible design, applying the first AI content to at least one scenario includes at least one of the following: setting the first AI content as wallpaper; setting the first AI content as avatar; adding the first AI content to an emoji pack.

[0040] In one possible design, any of the scenarios is a wallpaper display scenario, an avatar display scenario, or an emoji display scenario; displaying the first AI content includes: when any of the scenarios is a wallpaper display scenario, displaying the first AI content as wallpaper; or, when any of the scenarios is an avatar display scenario, displaying the first AI content as an avatar; or, when any of the scenarios is an emoji display scenario, displaying the first AI content as an emoji.

[0041] Based on the above method, electronic devices can display AI content in different scenarios, which is highly practical.

[0042] Secondly, embodiments of this application provide a method for generating AI content, the method comprising: a first application in an electronic device displaying a first interface; wherein the first interface includes a first control, the first control being used to trigger the generation of AI content; the first application, in response to an operation performed on the first control, generating first AI content through a system service in the electronic device; wherein the first AI content is generated by the system service based on one or more images containing a first object, the first AI content including a first AI image of the first object, the first object being an object selected by the user from at least one object, the one or more images being determined by the system service based on the selected first object; and the first application displaying the first AI content.

[0043] Based on this method, electronic devices can support users in selecting one object from multiple options. Based on the user-selected object, the system service automatically determines one or more images to generate AI content for that object, thus obtaining the AI ​​content generated from those images. In other words, the electronic device can obtain the AI ​​content for the object simply by having the user select it. This process eliminates the need for the user to select images from numerous options; instead, the user directly selects the object, and the electronic device automatically generates the necessary images. Therefore, the operation is simple, convenient, and efficient, improving the efficiency of AI content generation. Furthermore, this method allows the electronic device to automatically determine one or more suitable images based on the user-selected object, making it easier to obtain more suitable images compared to user-selected images, thereby improving the quality of AI content generation. In this method, applications within the electronic device can utilize system services to generate AI content, resulting in lower resource consumption and computational demands on the application, thus contributing to improved application performance.

[0044] Optionally, the first AI content is also generated based on user-defined generation requirements, which indicate the requirements for generating the AI ​​content for the first object. For example, the generation requirements may include style, background, posture, face angle or range, clothing, makeup, expression, emotion, the relationship between the first object and other objects, the degree of intimacy of the relationship between the first object and other objects, etc. Posture may include general postures such as facing forward, turning sideways, standing, sitting, etc., and may also include detailed postures such as the overall angle or range of angles of the object.

[0045] This method supports generating AI content that users expect based on user-defined generation requirements, thereby improving the user experience.

[0046] In one possible design, the first AI content is any of the following: a still image, a moving image, or a video.

[0047] In one possible design, the first object is a person or an animal.

[0048] In one possible design, the first application generates first AI content through a system service in the electronic device, including: the first application obtaining the first AI content generated and stored by the system service from a designated storage area in the electronic device; or, the first application receiving the first AI content sent by the system service.

[0049] In this method, applications in electronic devices can obtain AI content generated by system services through various means, offering high flexibility. Specifically, the method of applications retrieving AI content generated by system services from a designated storage area reduces interaction between applications and system services, lowering interaction overhead and execution complexity.

[0050] In one possible design, the method further includes: the first application acquiring second AI content generated by the system service when set conditions are met; wherein the second AI content is generated by the system service based on at least one image containing the first object when the set conditions are met, and the second AI content includes a second AI image of the first object; the first application displays the second AI content. Optionally, displaying the second AI content includes: updating the already displayed first AI content to the second AI content. Optionally, the first application may automatically display the second AI content, or may display the second AI content in response to a user operation.

[0051] In one possible design, the second AI content is also generated based on the stated conditions.

[0052] Thirdly, this application provides an electronic device, the electronic device including a memory and one or more processors; wherein the memory is used to store computer program code, the computer program code including computer instructions; when the computer instructions are executed by the one or more processors, the electronic device causes the electronic device to perform the method described in the first aspect or any possible design of the first aspect, or to perform the method described in the second aspect or any possible design of the second aspect.

[0053] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on an electronic device, causes the electronic device to perform the method described in the first aspect or any possible design of the first aspect, or to perform the method described in the second aspect or any possible design of the second aspect.

[0054] Fifthly, this application provides a computer program product comprising a computer program or instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect or any possible design of the first aspect, or to perform the method described in the second aspect or any possible design of the second aspect.

[0055] Sixthly, this application provides a chip system including a processor and a memory, wherein the memory stores instructions; when the instructions are executed by the processor, they implement the methods described in the first aspect or any possible design of the first aspect, or implement the methods described in the second aspect or any possible design of the second aspect. The chip system may be composed of chips or may include chips and other discrete devices.

[0056] The beneficial effects of the third to sixth aspects mentioned above can be found in the beneficial effects of the first or second aspects mentioned above, and will not be repeated here. Attached Figure Description

[0057] Figure 1 is a schematic diagram of the hardware architecture of an electronic device provided in an embodiment of this application;

[0058] Figure 2 is a schematic diagram of the software architecture of an electronic device provided in an embodiment of this application;

[0059] Figure 3 is a schematic diagram of an AI generation process provided in an embodiment of this application;

[0060] Figure 4 is a schematic diagram of a character avatar selection interface provided in an embodiment of this application;

[0061] Figure 5 is a schematic diagram of an AI-generated control entry point provided in an embodiment of this application;

[0062] Figure 6 is a schematic diagram of an AI-generated control entry point provided in an embodiment of this application;

[0063] Figure 7 is a schematic diagram of an AI-generated control entry point provided in an embodiment of this application;

[0064] Figure 8 is a schematic diagram of an AI-generated control entry point provided in an embodiment of this application;

[0065] Figure 9 is a schematic diagram of a visual settings interface provided in an embodiment of this application;

[0066] Figure 10 is a schematic diagram of a visual settings interface provided in an embodiment of this application;

[0067] Figure 11 is a schematic diagram of a prompt interface provided in an embodiment of this application;

[0068] Figure 12 is a schematic diagram of an AI image display interface provided in an embodiment of this application;

[0069] Figure 13 is a schematic diagram of an application scenario selection interface provided in an embodiment of this application;

[0070] Figure 14 is a schematic diagram of the interface of an application effect of AI content provided in an embodiment of this application;

[0071] Figure 15 is a schematic diagram of the interface of an AI content application effect provided in an embodiment of this application;

[0072] Figure 16 is a schematic diagram of the interface of an AI content application effect provided in an embodiment of this application;

[0073] Figure 17 is a schematic diagram of the interface for setting transformation conditions of AI content according to an embodiment of this application;

[0074] Figure 18 is a schematic diagram of an interface for generating AI content according to an embodiment of this application;

[0075] Figure 19 is a schematic diagram of an interface for generating AI content according to an embodiment of this application;

[0076] Figure 20 is a schematic diagram of an interface for generating AI content according to an embodiment of this application;

[0077] Figure 21 is a schematic diagram of an interface for generating AI content according to an embodiment of this application;

[0078] Figure 22 is a schematic diagram of an interface for generating AI content according to an embodiment of this application;

[0079] Figure 23 is a schematic diagram of an interface for generating AI content according to an embodiment of this application;

[0080] Figure 24 is a schematic diagram of a possible system architecture to which the method provided in the embodiments of this application is applicable;

[0081] Figure 25 is a schematic diagram of a method for AI content generation provided in an embodiment of this application;

[0082] Figure 26 is a schematic diagram of a method for AI content generation provided in an embodiment of this application;

[0083] Figure 27 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0084] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0085] In the description of the embodiments of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first" and "second" may explicitly or implicitly include one or more of that feature.

[0086] It should be understood that in the embodiments of this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, a and b, a and c, b and c, or a, b, and c, where a, b, and c can be single or multiple.

[0087] To improve the efficiency of AI image generation, this application provides a method and electronic device for AI content generation. In this method, the electronic device can support a user in selecting one object from multiple objects and obtaining an AI image of the selected object. It can also support a user setting requirements for generating the AI ​​image and generating the AI ​​image of the selected object according to those requirements. In this AI image generation process, the user does not need to select the desired image from numerous images; instead, the user directly selects the object, and the subsequent image determination can be automatically completed by the electronic device. Therefore, the operation is simple, convenient, and efficient, improving the efficiency of AI content generation. After the user selects an object, the electronic device can automatically generate an AI image of that object based on one or more suitable images, which helps improve the accuracy, universality, and scalability of the generated AI image. Therefore, the generated AI image has a better effect and stronger practicality.

[0088] In some embodiments of this application, the electronic device can be a portable device, such as a mobile phone, tablet computer, wearable device with wireless communication capabilities (e.g., smartwatch, smart glasses, etc.), in-vehicle terminal device, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), smart home device (e.g., smart TV, smart speaker, etc.), smart robot, workshop equipment, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, or wireless terminal in smart home, flying equipment (e.g., smart robot, drone, airplane), etc. Wearable devices are portable devices that users can wear directly on their body or integrate into their clothing or accessories.

[0089] In some embodiments of this application, the electronic device may also be a portable terminal device that includes other functions. Exemplary embodiments of the portable terminal device include, but are not limited to, carrying... Alternatively, it could be a portable terminal device with another operating system. The aforementioned portable terminal device could also be other portable terminal devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of this application, the aforementioned electronic device may not be a portable terminal device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0090] For a description of the performance of electronic devices, please refer to the relevant descriptions below.

[0091] Referring to Figure 1 below, the structure of the electronic device to which the method provided in the embodiments of this application is applicable will be described.

[0092] As shown in Figure 1, the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a USB interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a SIM card interface 195, etc.

[0093] The sensor module 180 may include a gyroscope sensor, an accelerometer, a proximity sensor, a fingerprint sensor, a touch sensor, a temperature sensor, a pressure sensor, a distance sensor, a magnetic sensor, an ambient light sensor, a barometric pressure sensor, a bone conduction sensor, etc.

[0094] It is understood that the electronic device 100 shown in Figure 1 is merely an example and does not constitute a limitation on the electronic device. Furthermore, the electronic device may have more or fewer components than those shown in the figure, may combine two or more components, or may have different component configurations. The various components shown in Figure 1 can be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and / or application-specific integrated circuits (ASICs).

[0095] Processor 110 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, memory, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). Different processing units may be independent devices or integrated into one or more processors. The controller may serve as the central nervous system and command center of the electronic device 100. The controller can generate operation control signals based on instruction opcodes and timing signals to control instruction fetching and execution.

[0096] The processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. This memory can store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instruction or data again, it can retrieve it directly from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0097] The execution of the AI ​​content generation method provided in this application embodiment can be controlled by the processor 110 or by calling other components. For example, it can call the processing program of this application embodiment stored in the internal memory 121, or call the processing program of this application embodiment stored in a third-party device through the external memory interface 120 to control the wireless communication module 160 to perform data communication with other devices, thereby improving the intelligence and convenience of the electronic device 100 and enhancing the user experience. The processor 110 may include different devices. For example, when integrating a CPU and a GPU, the CPU and GPU can cooperate to execute the AI ​​content generation method provided in this application embodiment. For example, in the AI ​​content generation method, some algorithms are executed by the CPU, and other algorithms are executed by the GPU to achieve faster processing efficiency.

[0098] Display screen 194 is used to display images, videos, etc. Display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a Miniled LED, a MicroLED, a Micro-OLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, electronic device 100 may include one or N displays screens 194, where N is a positive integer greater than 1. Display screen 194 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces (GUIs). For example, display screen 194 can display various interfaces such as the recommendation interface described in the embodiments of this application.

[0099] In this embodiment of the application, the display screen 194 can be a single flexible display screen, or it can be a splicing display screen composed of two rigid screens and a flexible screen located between the two rigid screens.

[0100] Camera 193 (a front-facing camera or a rear-facing camera, or a single camera that can function as both) is used to capture still images or videos. Typically, camera 193 may include a photosensitive element such as a lens assembly and an image sensor. The lens assembly includes multiple lenses (convex or concave lenses) for collecting light signals reflected from the object being photographed and transmitting these signals to the image sensor. The image sensor generates a raw image of the object being photographed based on the light signals.

[0101] The internal memory 121 can be used to store computer executable program code, which includes instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. The program storage area can store the operating system, application program code (such as the functions corresponding to the scheme in this application), etc. The data storage area can store data created during the use of the electronic device 100.

[0102] The internal memory 121 may also store one or more computer programs corresponding to the algorithm of this application. The one or more computer programs are stored in the internal memory 121 and configured to be executed by one or more processors 110. The one or more computer programs include instructions that can be used to perform the various steps in the following embodiments.

[0103] In addition, the internal memory 121 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0104] Of course, the algorithm code of the embodiment of this application can also be stored in external memory. In this case, the processor 110 can run the algorithm code of the embodiment of this application stored in external memory through the external memory interface 120.

[0105] A touch sensor, also known as a "touch panel," can be located on the display screen 194. The touch sensor and display screen 194 together form a touch display screen, also called a "touch screen." The touch sensor detects touch operations applied to or near it. The touch sensor can transmit the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through the display screen 194. In other embodiments, the touch sensor may also be located on the surface of the electronic device 100, in a different position than the display screen 194.

[0106] For example, the display screen 194 of the electronic device 100 can display a main interface, which includes icons for multiple applications (such as a camera application, a fitness and health application, etc.). For instance, a user can tap the camera application icon on the main interface using a touch sensor, triggering the processor 110 to launch the camera application and open the camera 193. The display screen 194 then displays the camera application's interface, such as the viewfinder.

[0107] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0108] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with tuning switches.

[0109] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves via antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves before transmitting them to a modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1. In some embodiments, at least some functional modules of the mobile communication module 150 may be housed in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 may be housed in the same device. In this embodiment, the mobile communication module 150 can also be used for information interaction with other devices.

[0110] The modem processor may include a modulator and a demodulator. The modulator modulates the low-frequency baseband signal to be transmitted into a mid-to-high frequency signal. The demodulator demodulates the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After processing by the baseband processor, the low-frequency baseband signal is transmitted to the application processor. The application processor outputs sound signals through an audio device (not limited to speaker 170A, receiver 170B, etc.) or displays images or videos through the display screen 194. In some embodiments, the modem processor may be a separate device. In other embodiments, the modem processor may be independent of the processor 110 and may be housed in the same device as the mobile communication module 150 or other functional modules.

[0111] The wireless communication module 160 can provide solutions for wireless communication applications on the electronic device 100, including wireless local area networks (WLANs) (such as wireless fidelity (WiFi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signals, and sends the processed signal to processor 110. The wireless communication module 160 can also receive signals to be transmitted from processor 110, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2. In this embodiment, the wireless communication module 160 can be used to establish connections with other electronic devices for data interaction. Alternatively, the wireless communication module 160 can be used to access access point devices, send control commands to other electronic devices, or receive data from other electronic devices.

[0112] In addition, the electronic device 100 can implement audio functions through an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, and an application processor, such as music playback and recording. The electronic device 100 can receive input from buttons 190, generating key signal inputs related to user settings and function control. The electronic device 100 can use a motor 191 to generate vibration alerts (such as vibration alerts for incoming calls). The indicator 192 in the electronic device 100 can be an indicator light, used to indicate charging status, battery level changes, messages, missed calls, notifications, etc. The SIM card interface 195 in the electronic device 100 is used to connect a SIM card. The SIM card can be inserted into or removed from the SIM card interface 195 to achieve contact and separation with the electronic device 100.

[0113] It should be understood that in practical applications, the electronic device 100 may include more or fewer components than those shown in FIG. 1, and the embodiments of this application are not limited thereto. The illustrated electronic device 100 is merely an example, and the electronic device 100 may have more or fewer components than shown in the figure, may combine two or more components, or may have different component configurations. The various components shown in the figure may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and / or application-specific integrated circuits.

[0114] The software system of electronic device 100 can adopt a layered architecture, event-driven architecture, microkernel architecture, microservice architecture, or cloud architecture. A layered architecture divides the software into several layers, each with a clear role and function. Layers communicate with each other through software interfaces. For example, as shown in Figure 2, this software architecture can be divided into four layers, from top to bottom: the application layer, the application framework layer (framework, FWK), the runtime and system libraries, and the (Linux) kernel layer.

[0115] The application layer is the top layer of the operating system and includes native operating system applications such as camera, gallery, calendar, Bluetooth, music, video, and messaging applications, as well as third-party applications. The applications discussed in this application embodiment are referred to as applications (APPs), which are software programs capable of performing one or more specific functions. Typically, multiple applications can be installed on an electronic device, such as camera applications and email applications. The applications mentioned below can be system applications pre-installed on the electronic device at the factory, or third-party applications downloaded by the user from the network or obtained from other electronic devices during the use of the electronic device.

[0116] Of course, for developers, they can write applications and install them into this layer. In one possible implementation, the application can be developed using the Java language, by calling the application programming interface (API) provided by the application framework layer. Developers can then interact with the underlying operating system (such as the kernel layer) through the application framework to develop their own applications.

[0117] The application framework layer provides the API and programming framework for the application layer. It can include predefined functions. The application framework layer may include a window manager, content provider, view system, phone manager, resource manager, notification manager, etc.

[0118] The window manager is used to manage window programs. The window manager can obtain the screen size, determine if a status bar is present, lock the screen (or display), and capture the screen, among other things.

[0119] Content providers are used to store and retrieve data, making that data accessible to applications. This data may include files (e.g., documents, videos, images, audio), text, and other information.

[0120] A view system includes visual controls, such as controls that display text, images, documents, and other content. View systems can be used to build applications. An interface in a display window can consist of one or more views. For example, a display interface including a text message notification icon could include a view that displays text and a view that displays images.

[0121] The phone manager provides communication functionality for electronic devices. The notification manager allows applications to display notification information in the status bar; it can be used to convey informative messages and can disappear automatically after a short pause without user interaction.

[0122] The runtime includes the core libraries and the virtual machine. The runtime is responsible for system scheduling and management.

[0123] The system's core library consists of two parts: one part contains the functionalities that the Java language needs to call, and the other part is the system's core library. The application layer and application framework layer run in a virtual machine. Taking Java as an example, the virtual machine executes the Java files in the application layer and application framework layer as binary files. The virtual machine is used to perform functions such as object lifecycle management, stack management, thread management, security and exception management, and garbage collection.

[0124] The system library can include multiple functional modules. Examples include: a surface manager, a media library, a 3D graphics processing library (e.g., OpenGL ES), a 2D graphics engine (e.g., SGL), and an image processing library. The surface manager manages the display subsystem and provides fusion of 2D and 3D layers for multiple applications. The media library supports playback and recording of various common audio and video formats, as well as still image files. It supports multiple audio and video encoding formats, such as MPEG4, H.564, MP3, AAC, AMR, JPG, and PNG. The 3D graphics processing library implements 3D graphics drawing, image rendering, compositing, and layer processing. The 2D graphics engine is the drawing engine for 2D graphics.

[0125] The kernel layer provides core system services for the operating system, such as security, memory management, process management, network protocol stack, and driver models, all of which are implemented based on the kernel layer. The kernel layer also serves as an abstraction layer between the hardware and software stacks. This layer contains many drivers related to electronic devices, including: display drivers; keyboard drivers as input devices; Flash drivers for memory-based devices; camera drivers; audio drivers; Bluetooth drivers; and WiFi drivers.

[0126] It is important to understand that the functional services described above are just an example. In practical applications, electronic devices may be divided into more or fewer functional services based on other factors, or the functions of each service may be divided in other ways, or they may not be divided into functional services but work as a whole.

[0127] The solution provided in this application will be described in detail below with reference to the accompanying drawings.

[0128] AI avatars are digital virtual representations created by users in the virtual world or digital environment, representing specific objects. AI avatars can serve as personalized virtual representations of these objects. These avatars can be digital mappings of the object itself or idealized versions of the object designed by the user. AI avatars can be used in various settings, including social, entertainment, and work.

[0129] Referring to Figure 3, the solution provided in this application embodiment may include multiple stages such as avatar display, avatar selection, generation requirement setting, AI image generation, and AI image application. In the avatar display stage, the electronic device can display the avatar of at least one object after being triggered by the user. Each object's avatar is associated with a set of media content such as images and videos of that object in the electronic device, as well as the object's feature information. Optionally, the set corresponding to each object may include all media content such as images of that object. For example, the objects described in this application embodiment may include people, animals, or other objects (e.g., cosmetics or beverage packaging). In the avatar selection stage, the user can indicate the object for which the electronic device should generate an AI image by selecting the avatar of at least one object displayed on the electronic device. In the generation requirement setting stage, the electronic device can display options related to the generation requirements for the user, from which the user can select the requirements for generating the AI ​​image. The user can also directly input the requirements for generating the AI ​​image. In the AI ​​image generation stage, the electronic device can generate an AI image that meets the user's requirements based on the AI ​​image generation requirements set by the user and the set associated with the user-selected avatar. In the AI ​​avatar application stage, users can apply the AI ​​avatar generated by electronic devices to various scenarios, such as generating AI images based on AI avatars and setting them as avatars, wallpapers, etc.

[0130] The following provides a detailed explanation of the solutions for each stage. For ease of understanding and description, the following examples use a person as the object, a person's portrait as the avatar, and an image set (i.e., a set of all images of the object corresponding to the portrait) as an example.

[0131] Phase 1: Avatar Display Phase

[0132] In some embodiments of this application, the electronic device may display an avatar selection interface on a display screen in response to a received first user operation. The avatar selection interface may include at least one person's avatar, wherein each avatar can be used to identify a person, and each avatar is associated with a set of images of the corresponding person (i.e., the person identified by the avatar) and facial features of that person extracted based on the images in that set. Optionally, the image set for each person may include all images of that person in the electronic device. The facial features of each person include at least the person's facial features, and may also include other features such as pose features. Optionally, the electronic device may include a gallery application for storing and managing images, and the image set for each person may include all images of that person in the gallery application.

[0133] In one example, taking a mobile phone as an electronic device, the avatar selection interface displayed on the electronic device can refer to the interface shown in Figure 4. For instance, as shown in Figure 4, this avatar selection interface can include avatars 1 to 5, each corresponding to a person 1 to 5. Avatar 1 can be associated with an image set 1 containing all images of person 1, and the facial features of person 1 identified based on images in image set 1. The other avatars are similar and will not be described individually.

[0134] In some embodiments of this application, the electronic device can maintain a facial feature library, which may include facial features of different individuals. Since the facial features of each individual are extracted from all images of that individual, the comprehensiveness (e.g., facial features can cover different postures, facial angles, and expressions of the user) and stability of each individual's facial features are high. For example, it can support generating the same image with different postures, facial angles, and expressions. Therefore, when subsequently applying AI avatars, the posture, facial angle, clothing, and expressions of the AI ​​avatar can be changed based on the facial features in the facial feature library, and even the AI ​​avatar can be dynamically changed.

[0135] In some embodiments of this application, each person's avatar can be generated based on an image of the corresponding person. For example, a person's head image can be cropped from an image as an avatar, or a specific style AI avatar can be generated based on a person's image or facial features. Of course, avatars can also be generated in other ways, as long as the generated avatar can be used to represent the person. This application does not limit the method of generating avatars. Optionally, the avatar can also be replaced with other representations that can be used to identify a person.

[0136] In this application embodiment, there are no restrictions on the method by which the electronic device acquires the image set and facial features of each person. For example, the electronic device can extract all images of the same person from images in the electronic device (e.g., images in a gallery) through methods such as clustering, or it can be achieved through other methods.

[0137] Optionally, the aforementioned at least one person's avatar may include all or part of the avatars of people acquired by the electronic device. For example, when the electronic device extracts a set of images of multiple people based on images stored in the electronic device, the electronic device may display all of the avatars of the multiple people in the avatar selection interface, or it may display only some of the avatars of the multiple people in the avatar selection interface, and may switch the avatars displayed in the avatar selection interface in response to received user operations. The selection of some people may be based on actual circumstances, as detailed in the relevant descriptions in the following embodiments, which will not be elaborated here.

[0138] In some embodiments of this application, different avatars generated by the electronic device can be distributed across a spherical area. The avatar selection interface displayed by the electronic device can include a portion of the avatars distributed across the spherical area. That is, the avatar selection interface displayed by the electronic device can correspond to a portion of the spherical area, and the avatars distributed in that portion are included in the avatar selection interface. For example, avatars 1 to 5 shown in Figure 4 can be a portion of the avatars generated by the electronic device. Optionally, the relative positions between different avatars in the spherical area can be fixed. Users can switch the avatar selection interface corresponding to a specific spherical area displayed by the electronic device by performing a swipe operation on the display screen. That is, the swipe operation performed by the user on the display screen can be used to rotate the spherical area, and the electronic device can display the avatars in the portion of the spherical area rotated by the user through the avatar selection interface.

[0139] In some embodiments of this application, the size and / or clarity of different human portraits may be different.

[0140] As an alternative implementation, in the avatar selection interface displayed on the electronic device, the size of the avatar can be negatively correlated with the distance between the avatar and the center of the interface, and the sharpness of the avatar can also be negatively correlated with the distance between the avatar and the center of the interface. For example, the avatar located in the center can be the largest, and the avatar further away from the center can be smaller.

[0141] As an alternative implementation, in the avatar selection interface displayed on the electronic device, the avatar in the center position can be the largest, and the sizes of other avatars can be positively correlated with a reference correlation. Here, the reference correlation can be the degree of association between the person corresponding to the other avatars and the person corresponding to the avatar in the center position. In the above method, when the user switches the avatars displayed on the electronic device by swiping, the size and / or clarity of different avatars can change with the position of the avatars. For example, as a avatar gradually moves away from the center of the interface, the size and / or clarity of that avatar can gradually decrease.

[0142] In some embodiments of this application, the first user operation may be an operation performed on a first control displayed on an electronic device to initiate the generation of an AI avatar. The electronic device may include a gallery application for storing and managing images within the electronic device and a first application. The first application may be any application other than a gallery application. The AI ​​avatar generated by the electronic device may be applied in the first application.

[0143] In the first possible approach, the first control could be a control displayed in the gallery app. Based on this method, users could enable AI-generated images within the gallery app.

[0144] As an example, as an optional implementation, as shown in Figure 5, the first control can be a control displayed on the homepage of a gallery application. Optionally, as shown in Figure 5, the first control may also include a prompt message for generating an AI avatar for the user associated with the electronic device. In this scenario, the first control can be used to recommend that the user use the AI ​​avatar generation function. The electronic device can respond to the user's click on the first control shown in Figure 5, switching to displaying the avatar selection interface shown in Figure 4.

[0145] For example, as another optional implementation, the person's avatar generated by the electronic device and the AI ​​image previously generated by the electronic device can form an AI album. The first control can be a control for opening the AI ​​album. For example, the electronic device can display the album interface shown in Figure 6 in response to the user clicking the first control displayed in the application interface of the gallery application for opening the AI ​​album. As shown in Figure 6, the album interface can include the AI ​​image 1 already generated by the electronic device and the person's avatars 1 to 5 shown in Figure 4. In this scenario, the interface area including the person's avatar in the album interface shown in Figure 6 (e.g., the display interface in the dashed box in Figure 6) can also be understood as the person's avatar selection interface.

[0146] In the second possible approach, the first control can be a control displayed in the first application. Based on this approach, the user can enable the AI ​​avatar generation function in the first application. Optionally, the first application can display the first control in response to the user's operation, or the first application can automatically display the first control in a specific application interface. For example, the first application can automatically display the first control in a pre-defined interface where AI avatars or AI images can be applied; this is not limited in the embodiments of this application.

[0147] For example, taking the first application as the Contacts application, in a scenario where it is necessary to set a contact avatar, the first application can respond to the user's operation on the image selection control shown in the schematic diagram in Figure 7(a) (which can be used to trigger the selection of an image for generating a contact avatar), automatically display the first control shown in the schematic diagram in Figure 7(b), and respond to the user's operation of clicking the first control to display the avatar selection interface shown in Figure 4.

[0148] In a third possible solution, the first control could be a control displayed in a pop-up window pushed by the electronic device. Based on this approach, the electronic device could proactively recommend the use of the AI ​​avatar generation function. Specifically, the electronic device could display a pop-up window containing the first control under certain conditions, and this pop-up window could also include prompts to encourage the user to use the AI ​​avatar generation function.

[0149] For example, if the first contact has not set a profile picture, when receiving a call from the first contact, the electronic device can display the call interface shown in the schematic diagram of Figure 8(a). After the call with the first contact ends, the electronic device can display a pop-up window including a first control, as shown in the schematic diagram of Figure 8(b). This pop-up window may also include a prompt message to set an AI profile picture for the first contact. In response to the user clicking the first control in the pop-up window shown in the schematic diagram of Figure 8(b), the electronic device can switch to displaying the profile picture selection interface shown in Figure 4.

[0150] Phase 2: Avatar Selection Phase

[0151] In some embodiments of this application, after displaying the avatar selection interface, the electronic device can receive a second user operation performed by the user to select a first person's avatar, i.e., the avatar of a first person. The user can select one avatar from at least one avatar displayed in the avatar selection interface. Alternatively, the user can first switch the avatars in the avatar selection interface by swiping, and then select one avatar from the switched avatars. For example, the user can select one avatar from avatars 1-5 shown in Figure 4, or they can first switch avatars 1-5 to avatars 3-7 shown in Figure 4 by swiping, and then select one avatar from avatars 3-7.

[0152] In one possible approach, after the electronic device displays an avatar selection interface, the user can select a first avatar by clicking on the avatars displayed on the interface; that is, the second user action can be the user clicking on the first avatar. For example, the user can select avatar 1 by clicking on avatar 1 shown in Figure 4.

[0153] In another possible approach, the avatar selection interface can also include selection controls for each character avatar. Users can select a first character avatar by clicking the selection control corresponding to that first avatar; that is, the second user action can be the user clicking the selection control corresponding to the first character avatar. For example, a user can select character avatar 1 by clicking the first control corresponding to character avatar 1 shown in Figure 6. In this method, the first control can be used to trigger the generation of the AI ​​avatar.

[0154] Phase 3: Setting Generation Requirements

[0155] In some embodiments of this application, after displaying the avatar selection interface, the electronic device can switch to displaying the image settings interface in response to the received second user operation. The image settings interface may include the aforementioned first avatar, a prompt control, and a generation control. The prompt control is a control that receives prompts, which are information provided to the AI ​​model to guide it in generating expected content. Prompts can be used to clarify task requirements, constrain the content generation direction of the AI ​​model, and control the quality and style of the AI ​​model's output. Prompts can be questions, instructions, keywords, reference content, or others. Prompts can include multimodal content such as text, images, videos, and audio. In some embodiments of this application, the prompt control may include at least one of a keyword control, a selection control, and an input control. Optionally, the first avatar may be located in the center of the image settings interface, and other controls may be distributed around the first avatar.

[0156] Example 1: In one example, the image settings interface displayed by the electronic device can be referred to Figure 9. Specifically, based on the scenario of setting a contact avatar as shown in Figure 7, the electronic device can switch to displaying the avatar selection interface shown in Figure 4 in response to the user clicking the first control shown in the schematic diagram (b) of Figure 7, and can switch to displaying the image settings interface shown in Figure 9 in response to the user clicking the person avatar 1 shown in Figure 4. As shown in Figure 7, the image settings interface may include person avatar 1 (corresponding to the first contact), keyword control 1, selection control 1, input control 1, and generation control 1.

[0157] The functions of each type of control are explained in detail below.

[0158] 1) Keyword control

[0159] The profile settings interface may include at least one keyword control, and each keyword control can be used to indicate a keyword.

[0160] In some embodiments of this application, keywords may be pre-set or default, or they may be recommended by the electronic device based on contextual information. Contextual information may include at least one of the following: content displayed by the electronic device before displaying the avatar selection interface; related content of the interface or content displayed by the electronic device before displaying the avatar selection interface; related content of the task performed by the electronic device before displaying the avatar selection interface; user input or selection received by the electronic device before displaying the avatar interface; and information about the first person corresponding to the first person's avatar (e.g., the person's identity, facial features, etc.). Of course, the electronic device may also recommend keywords based on other available contextual information; all possible contextual information will not be listed in this embodiment.

[0161] Optionally, when recommending keywords based on contextual information, the electronic device can directly select some or all of the information from the context as keywords, or it can generate keywords based on the contextual information (e.g., generating summary, outline, or feature-indicating keywords after summarizing or analyzing the contextual information). For example, in the scenario of Example 1, the contextual information may include information about the first contact person, the relationship between the first contact person and the user associated with the electronic device (e.g., the device owner), etc. The electronic device can generate keywords based on the contextual information to indicate the closeness of the relationship between the first contact person and the user associated with the electronic device. For example, when the first contact person is a family member of the user associated with the electronic device, the keyword generated by the electronic device could be "closeness" as shown in Figure 9.

[0162] In some embodiments of this application, users can select a keyword indicated by a keyword control in the avatar settings interface. Optionally, after the user clicks the keyword control, the electronic device can mark the keyword control as selected. The keyword selected by the user can be used as a prompt when generating the AI ​​avatar later.

[0163] 2) Selection Control

[0164] The character settings interface can include at least one selection control, each corresponding to a setting item (or control item). Each selection control can be used to choose a target option from multiple different options within a given setting item. Each option represents a specific setting method, and each setting item and its multiple different options can be pre-configured. For example, a style setting item can have multiple style options such as realistic, three-dimensional (3D), and cartoon styles. Similarly, a background setting item can have multiple different background options, and a clothing setting item can have multiple different clothing options, and so on.

[0165] Initially, the selection control may include a prompt message to guide the user to select a specific option for the corresponding setting. For example, selection control 1, as shown in Figure 8, may include a prompt message to guide the user to select a style.

[0166] The electronic device can display multiple different options for the corresponding settings after the user clicks the selection control. After the user selects an option, the electronic device can mark that option as selected and update the prompt information in the selection control to indicate that option. The option selected by the user can be used as a prompt word when generating the AI ​​image later. For example, after the user clicks the selection control 1 shown in Figure 8, the electronic device can display the selection panel shown in the schematic diagram in Figure 10(a), which includes three options: realistic, cartoon, and 3D. After the user selects the cartoon option, as shown in the schematic diagram in Figure 10(b), the electronic device can mark the cartoon option as selected and update the prompt information in the selection control 1 to "cartoon style".

[0167] 3) Input controls

[0168] Input controls can be used by users to input requirements or reference information for generating an AI avatar. Electronic devices can set the information input by users through input controls as prompts for generating an AI avatar.

[0169] For example, the electronic device can display an input panel in response to a user clicking an input control and receive information entered by the user in the input panel. Optionally, after the user finishes inputting, the electronic device can display the user-entered information in a profile settings interface.

[0170] 4) Generate controls

[0171] The generate control can be used to trigger the generation of an AI avatar. Electronic devices can respond to a user clicking the generate control and begin generating an AI avatar.

[0172] Phase 4: AI Image Generation Phase

[0173] After the prompt words are set in stage 3 above, the electronic device can respond to a received third user operation (e.g., a user clicking the generate control) and, using at least one model (e.g., an AI model), generate at least one AI image of the first person from any angle (e.g., any facial angle or any body angle) based on a first image set associated with the first person's avatar (i.e., all images of the first person) and the prompt words. The prompt words can include user-set prompt words and / or prompt words preset by the electronic device. User-set prompt words can include at least one of the following: keywords selected by the user through the keyword control, option information selected through the selection control, or information entered through the input control.

[0174] Specifically, the electronic device can randomly select at least one image of the same dimension from the first image set, or select at least one image of the same dimension based on a prompt, and generate an AI avatar for that dimension based on at least one image. The same dimension can include at least one of the following: the same angle or the same angle range, the same pose or similar poses, the same expression or similar expressions. For example, when randomly selecting at least one image, the electronic device can select at least one image of the same angle or the same angle range from the first image set based on the facial features of the first person in each image of the first image set. When selecting at least one image based on a prompt, the electronic device can select at least one image of the same angle or the same angle range from the first image set based on the facial features of the first person in each image of the first image set, meeting the requirements of the prompt. The aforementioned angle can be a facial angle or a body angle (i.e., an overall angle), and the aforementioned angle range can be a facial angle range or a body angle range.

[0175] The at least one model described above may include a model in an electronic device and / or a server. Optionally, when the at least one model described above includes a model in a server, the model in the server can be used to generate the AI ​​avatar. In this scenario, the electronic device may, after selecting at least one image from a first image set based on the method described above, send a prompt and the feature vector of at least one image to the server, and instruct the server to generate an AI avatar based on the prompt and the feature vector of at least one image. The server may, in response to the instruction from the electronic device, generate the AI ​​avatar based on the prompt sent by the electronic device and the feature vector of at least one image, and send the generated AI avatar to the electronic device. The electronic device may display and apply the received AI avatar. In the method described above, the feature vector of at least one image includes the feature vector of each image in the at least one image, and the feature vector of each image can be used to indicate the portrait features of the first person extracted from each image.

[0176] In the above method, the AI ​​image generated by the electronic device can be a static image or a dynamic image. The carrier (or display form) of the AI ​​image generated by the electronic device can be an image or a video; the following embodiments use an image as an example for illustration.

[0177] As an optional implementation, after generating the AI ​​avatar, the electronic device can display an AI avatar display interface. This interface may include the AI ​​avatar generated by the electronic device, as well as a save control for triggering the saving of the AI ​​avatar and / or an application control for triggering the application of the AI ​​avatar. The electronic device can save the generated AI avatar in response to the user clicking the save control (e.g., to an AI album in the image library). The electronic device can also apply the generated AI avatar to the scene specified by the user in response to the user clicking the application control.

[0178] As an alternative implementation, the electronic device can also, in response to a received third-user operation, switch the avatar setting interface to a live view window, displaying a notification message indicating that the AI ​​avatar is being generated. In this scenario, the electronic device can display the AI ​​avatar generation progress in response to the user clicking the live view window. After generating the AI ​​avatar, the electronic device can expand the live view window and display a notification message indicating that the AI ​​avatar generation is complete. The electronic device can then switch to displaying the aforementioned AI avatar display interface in response to the user clicking the expanded live view window.

[0179] For example, after a user clicks the generate control shown in the schematic diagram (b) of Figure 10, the electronic device can switch to displaying the live view window, including the capsule state, as shown in the schematic diagram (a) of Figure 11. After generating the AI ​​avatar, the electronic device can switch from displaying the interface shown in the schematic diagram (a) of Figure 11 to displaying the expanded live view window (i.e., the card state live view window) shown in the schematic diagram (b) of Figure 11, and display a prompt message in the expanded live view window indicating that the AI ​​avatar has been generated. In response to the user's click on the live view window shown in the schematic diagram (b) of Figure 11, the electronic device can switch to displaying the AI ​​avatar display interface shown in Figure 12, which includes the AI ​​avatar generated by the electronic device.

[0180] Phase 5: AI Image Application Phase

[0181] In some embodiments of this application, after generating an AI avatar, the electronic device can display an application scenario selection interface in response to a received fourth user operation (such as clicking the application control as described above). The user can select a scenario to apply the AI ​​avatar to in the application scenario selection interface. For example, the application scenario selection interface may include controls indicating different scenarios where the AI ​​avatar can be applied. The user can use the controls to select whether to apply it to a corresponding scenario. After the user selects a scenario, the electronic device can directly apply the generated AI avatar to that scenario, or it can further generate AI content (such as an AI image) suitable for that scenario based on the generated AI avatar before applying it to that scenario. Of course, the user can also indicate the application scenario of the AI ​​avatar in other ways; the methods of indicating application scenarios are not limited in the embodiments of this application.

[0182] In one example, the application scenario selection interface can be referenced to Figure 13. The electronic device can switch to displaying the application scenario selection interface shown in Figure 13 in response to a user clicking the application control shown in Figure 12. As shown in Figure 13, the application scenario selection interface may include an AI avatar generated by the electronic device, and controls for selecting whether to apply the AI ​​avatar to the phone or wallpaper scenarios. For example, when the user selects to apply the AI ​​avatar to the phone, since the AI ​​avatar shown in Figure 13 is the AI ​​avatar corresponding to the first person (i.e., the first contact), the electronic device can generate the first contact's avatar and incoming call background based on the AI ​​avatar shown in Figure 13. Based on this, as shown in the schematic diagram in Figure 14(a), the electronic device can use the AI ​​avatar shown in Figure 13 as the first contact's avatar. When the first contact calls, the electronic device can display the incoming call interface containing the first contact's AI avatar, as shown in the schematic diagram in Figure 14(b), based on the AI ​​avatar shown in Figure 13.

[0183] In some embodiments of this application, after applying the AI ​​avatar, the electronic device can further transform the AI ​​avatar when transformation conditions are met, or periodically transform the AI ​​avatar. Specifically, the electronic device can generate the transformed AI avatar based on at least one image of the person corresponding to the AI ​​avatar.

[0184] The method for electronic devices to automatically transform AI content generated based on AI images is similar to the method for electronic devices to automatically transform AI images. For ease of description, the following embodiments use AI images as an example to illustrate the AI ​​content generated based on AI images.

[0185] For example, the transformations made by electronic devices to AI images or AI avatars may include at least one of the following:

[0186] 1) Change the background.

[0187] 2) Change the theme or style.

[0188] 3) Change the atmosphere.

[0189] 4) Change at least one of the following aspects of the character: posture, movement, clothing, hairstyle, makeup, or expression.

[0190] 5) Dynamic and static transformation.

[0191] Of course, electronic devices can also adopt other feasible transformation methods depending on the actual situation.

[0192] For example, the above-mentioned transformation conditions can be set based on at least one of the following reference items: time, location, and event. Time can include a specific point in time, a date, or a longer time period. Events can include weather changes, changes in a person's mood, changes in environmental atmosphere, schedules, exercise, etc. For example, transformation conditions can include arriving at a set time, being on a set date, being at a set location, detecting a weather change, being in a set exercise mode, detecting a change in exercise state, etc., and no specific limitations are made in this embodiment.

[0193] In one example, after setting the generated AI avatar as wallpaper, the electronic device can automatically change the wallpaper based on changes in holidays, weather, exercise modes, etc. For example, taking the electronic device generating and displaying the wallpaper shown in Figure 15 based on the AI ​​avatar generated according to the aforementioned method as an example, after displaying the wallpaper shown in Figure 15, the electronic device can change the wallpaper to a yoga-themed wallpaper when it detects that the exercise mode is yoga mode. For example, it can change the actions and clothing of the AI ​​avatar shown in Figure 15 to the actions and clothing of a person doing yoga, and then automatically change from displaying the wallpaper shown in Figure 15 to displaying the wallpaper shown in Figure 16.

[0194] In another example, after an electronic device sets the generated AI avatar as its wallpaper, if the person in the wallpaper is a user associated with the electronic device (i.e., the device owner), the electronic device can automatically change the wallpaper to a birthday theme on that user's birthday. For example, the action of the person in the wallpaper can be changed to eating cake or blowing out candles. The action of the person in the wallpaper can also be changed at different times on the user's birthday. When the person in the wallpaper is not a user associated with the electronic device (i.e., the device owner), the electronic device can automatically change the action of the person in the wallpaper to sending a cake, singing a birthday song, or other birthday wishes on the birthday of the user associated with the electronic device.

[0195] In some embodiments of this application, taking the application of an AI image to wallpaper as an example, the electronic device can also display at least one associated control corresponding to a reference item in the wallpaper management or control interface. The associated control can be used to control whether the wallpaper automatically changes based on the reference item, that is, to control whether the wallpaper's changing conditions are related to the reference item. For example, as shown in Figure 17, the electronic device can display a weather-related control corresponding to a weather reference item and a date-related control corresponding to a date reference item. After the user selects an associated date reference item by operating the date-related control, the electronic device can automatically change the wallpaper based on the date, such as performing the aforementioned processing of changing the wallpaper based on a birthday.

[0196] In the method provided by the above embodiments, the user only needs to select the character for which an AI avatar needs to be generated once to activate the AI ​​avatar generation function. Furthermore, the electronic device can construct prompt controls based on specific scenarios, visualizing and simplifying the selection of prompt words. Users can easily select or input prompt words for generating the AI ​​avatar and generate rich effects based on these prompts. Therefore, the above method can reduce the cost and complexity of the AI ​​avatar generation process, and improve generation efficiency and quality.

[0197] The above method will be illustrated by examples 2 through 7 below.

[0198] Example 2: Generating emojis

[0199] In one example, an electronic device can generate emojis in social situations based on the aforementioned AI image generation method. Specifically, the process may include:

[0200] A1: As shown in the schematic diagram in Figure 18(a), the electronic device can display a first control for initiating AI avatar generation during user chat. It can also switch to displaying the avatar display interface shown in Figure 4 in response to the user clicking the first control.

[0201] A2: The electronic device can respond to the user's click on the character avatar 1 shown in Figure 4 and switch to display the image settings interface.

[0202] Optionally, the first person corresponding to avatar 1 can be the user chatting with the other end of the chat. The avatar settings interface can be found in the avatar settings interface described in the preceding embodiments, and will not be detailed here.

[0203] A3: The electronic device determines the prompt words based on user operations. This process can be implemented with reference to the method described in stage 3 above, and will not be detailed here. For example, as shown in the schematic diagram in Figure 18(b), the keyword indicated by the keyword control 1 selected by the user can come from the information entered by the user during chat (which can be used as context), that is, the electronic device can use the information entered by the user during chat as keywords; the image style selected by the user can be a 3D style. Therefore, the prompt words determined by the electronic device based on user operations can include "happy" and "3D style".

[0204] A4: The electronic device can respond to the user's click on the generation control shown in the schematic diagram (b) of Figure 18, and use the AI ​​model to generate an AI image of Person 1 based on the determined prompt words ("happy" and "3D style") and images in the image set of Person 1, and display the AI ​​image of Person 1 in the AI ​​image display interface shown in the schematic diagram (c) of Figure 18. This process can be implemented with reference to the method described in stage 4 above, and will not be described in detail here.

[0205] A5: The electronic device can respond to the user's click on the application control shown in the schematic diagram (c) of Figure 18, generate the AI ​​image shown in the schematic diagram (d) of Figure 18 based on the AI ​​image of Person 1, and send it to the chat interface.

[0206] In the above method, electronic devices can generate emojis for specific characters based on user input and selection of prompts, as well as the character selected by the user, in social situations. Users can select the character they want to generate emojis for through the emoji generation entry point (i.e., the first control) during chat, and utilize the AI ​​character generation function provided by the electronic device to generate emojis for that character. Therefore, the above method is highly practical and can improve the user experience.

[0207] Example 3: AI-powered virtual try-on

[0208] In one example, an electronic device can generate an AI avatar of a person trying on clothing during a shopping trip, based on the aforementioned AI avatar generation method. Specifically, the process may include:

[0209] B1: As shown in the schematic diagram in Figure 19(a), the electronic device can display a first control for initiating AI avatar generation on the product page of clothing 1. In response to the user clicking the first control, it can switch to displaying the avatar display interface shown in Figure 4.

[0210] B2: The electronic device can respond to the user's click on the character avatar 1 shown in Figure 4 and switch to display the image settings interface.

[0211] The image settings interface can be referred to in the aforementioned embodiments, and will not be described in detail here.

[0212] B3: The electronic device determines the prompt word based on user operation. This process can be implemented with reference to the method described in stage 3 above, and will not be detailed here. For example, as shown in the schematic diagram in Figure 19(b), the user can select clothing 1 through the keyword control (or clothing 2 through the selection control). Therefore, the prompt word determined by the electronic device based on user operation can include images of clothing 1 and clothing 2.

[0213] B4: The electronic device can respond to the user's click on the generation control shown in the schematic diagram in Figure 19(b), and using the AI ​​model, based on the determined prompt words (i.e., images of clothing 1 and clothing 2) and images from the image set of person 1, generate an AI image of person 1 wearing clothing 1 and clothing 2, and display the generated AI image in the AI ​​image display interface shown in the schematic diagram in Figure 19(c). This process can be implemented with reference to the method described in stage 4 above, and will not be described in detail here.

[0214] B5: The electronic device can save the generated AI image in response to the user clicking the save control shown in the schematic diagram (c) in Figure 19.

[0215] Optionally, subsequent electronic devices can also recommend the generated AI avatar and clothing (e.g., clothing 1 and clothing 2) to users via widgets or cards.

[0216] Based on the above method, when users browse clothing products, they can use the AI ​​image generation function of electronic devices to generate an AI image of the person trying on the clothing, thereby improving the user's browsing experience.

[0217] Example 4: AI Makeup Try-on

[0218] In one example, an electronic device can generate an AI-generated makeup effect for a person based on the aforementioned AI image generation method. Specifically, this process may include:

[0219] C1: As shown in the schematic diagram in Figure 20(a), the electronic device can display a first control for initiating AI avatar generation when the user browses makeup recommendations. It can also switch to displaying the avatar display interface shown in Figure 4 in response to the user clicking the first control.

[0220] C2: The electronic device can respond to the user's click on the character avatar 1 shown in Figure 4 and switch to display the image settings interface.

[0221] The image settings interface can be referred to in the aforementioned embodiments, and will not be described in detail here.

[0222] C3: The electronic device determines the prompt word based on user operation. This process can be implemented with reference to the method described in stage 3 above, and will not be detailed here. For example, as shown in the schematic diagram in Figure 20(b), the user can select makeup 1 from three makeup looks recommended by the electronic device through a selection control. Therefore, the prompt word determined by the electronic device based on user operation can include makeup 1. Among them, the three makeup looks can be the makeup looks recommended in the makeup recommendation content (which can be used as context) displayed before the electronic device displays the image settings interface.

[0223] C4: The electronic device can respond to the user's click on the generation control shown in the schematic diagram (b) of Figure 20, and use the AI ​​model to generate an AI image of Person 1 based on the determined prompt word (makeup 1) and the images in the image set of Person 1. The AI ​​image of Person 1 using makeup 1 is then displayed in the AI ​​image display interface shown in the schematic diagram (c) of Figure 20. This process can be implemented with reference to the method described in stage 4 above, and will not be described in detail here.

[0224] Example 5: Editing an image

[0225] In one example, an electronic device can perform image editing based on the AI ​​image generation method described above. Specifically, the process may include:

[0226] D1: As shown in the schematic diagram in Figure 21(a), the electronic device can display a first control for initiating AI avatar generation when the user triggers the addition or selection of an image. It can also switch to displaying the avatar display interface shown in Figure 4 in response to the user clicking the first control.

[0227] D2: The electronic device can respond to the user's click on the character avatar 1 shown in Figure 4 and switch to display the image settings interface.

[0228] The image settings interface can be referred to in the aforementioned embodiments, and will not be described in detail here.

[0229] D3: The electronic device determines the prompt word based on user operation. This process can be implemented with reference to the method described in stage 3 above, and will not be detailed here. In the first example, as shown in the schematic diagram in Figure 21(b), the user can select background image 1 from the background images recommended by the electronic device through the selection control. Therefore, the prompt word determined by the electronic device based on user operation may include "Use background image 1 as the background". In the second example, as shown in the schematic diagram in Figure 22(a), the user can select background image 2 from the background images recommended by the electronic device through the selection control. Therefore, the prompt word determined by the electronic device based on user operation may include "Use background image 2 as the background". In the first and second examples, the background image recommended by the electronic device may be an image associated with the image displayed before the electronic device displays the image settings interface (e.g., an image taken at the same location as the image displayed before the electronic device displays the image settings interface). For example, background images 1 to 3 may be images in the electronic device that were taken at the same location as any of the images 1 to 3 shown in the schematic diagram in Figure 21(a).

[0230] D4: The electronic device can respond to the user's click on the generate control shown in the schematic diagram (b) of Figure 21, and use the AI ​​model to generate a fused image of the AI ​​image of person 1 and background image 1 (e.g., a fused image with the environment in background image 1 as the background and the AI ​​image of person 1 as the foreground) based on the determined prompt ("use background image 1 as the background") and the images in the image set of person 1. This fused image is then displayed in the AI ​​image display interface shown in the schematic diagram (c) of Figure 21. Alternatively, the electronic device can respond to the user's click on the generate control shown in the schematic diagram (a) of Figure 22, and use the AI ​​model to generate a fused image of the AI ​​image of person 1 and background image 1 (e.g., a photo of the user and person 1 in background image 2) based on the determined prompt ("use background image 2 as the background") and the images in the image set of person 1. This fused image is then displayed in the AI ​​image display interface shown in the schematic diagram (b) of Figure 22. The above process can be implemented with reference to the method described in stage 4 above, and will not be detailed here.

[0231] D5: The electronic device can respond to the user's click on the application control shown in the schematic diagram (c) of Figure 21 and display the interface shown in the schematic diagram (d) of Figure 21, that is, the generated fused image shown in the schematic diagram (c) of Figure 21 as the image added or selected by the user.

[0232] In the above method, when editing an image, the user can combine people and scenery to generate a portrait image that matches the scenery, or combine people to generate a group photo.

[0233] Example 6: Group Photo Generation

[0234] In one example, an electronic device can generate a fused image based on the AI ​​image generation method described above. Specifically, the process may include:

[0235] E1: As shown in the schematic diagram in Figure 23(a), the electronic device can display a first control for initiating AI avatar generation while playing a movie or TV show. It can also switch to displaying the avatar display interface shown in Figure 4 in response to the user clicking the first control.

[0236] E2: The electronic device can respond to the user's click on the character avatar 1 shown in Figure 4 and switch to display the image settings interface.

[0237] The image settings interface can be referred to in the aforementioned embodiments, and will not be described in detail here.

[0238] E3: The electronic device determines the prompt word based on user operation. This process can be implemented with reference to the method described in stage 3 above, and will not be detailed here. In the first example, as shown in the schematic diagram in Figure 23(b), the electronic device can display the selection control corresponding to the setting item "Take a photo with a character". The user can select character 1 from the movie characters recommended by the electronic device through the selection control. Therefore, the prompt word determined by the electronic device based on user operation can include "Take a photo with character 1". Here, the movie characters recommended by the electronic device can be characters in the movie works played before the electronic device displays the image setting interface. In this scenario, the movie works can serve as context.

[0239] E4: The electronic device can respond to the user's click on the generation control shown in the schematic diagram (b) of Figure 23, and use the AI ​​model to generate an AI image of character 1 and a photo image of character 1 based on the determined prompt ("take a photo with character 1") and the images in the image set of character 1, and display the photo image in the AI ​​image display interface shown in the schematic diagram (c) of Figure 23. The above process can be implemented with reference to the method described in stage 4 above, and will not be described in detail here.

[0240] E5: The electronic device can respond to the user's click on the application control shown in the schematic diagram (c) of Figure 23, and display the interface shown in the schematic diagram (d) of Figure 23, that is, generate a group photo image of Person 1 and Role 1. The electronic device can then save or share the group photo image based on the user's operation.

[0241] Figure 24 is a schematic diagram of the architecture of a possible display system to which the method provided in the above embodiments of this application is applicable. This display system can be deployed in an electronic device. As shown in Figure 24, the display system may include a gallery application, a first application, system services, and an AI model.

[0242] The image library application can be used to save and manage images. Optionally, the images referenced by the electronic device in generating the AI ​​avatar can come from the image library application. In this embodiment, the image library application can also be used to provide a control entry point for AI avatar generation, which can be implemented by referring to the first possible method described in stage 1 of the foregoing embodiments, and will not be detailed here.

[0243] The first application can be a system application or a third-party application of the electronic device, excluding the gallery application. The first application can provide a control entry point for AI avatar generation, which can be implemented using the second possible method described in stage 1 of the aforementioned embodiments, and will not be detailed here. The first application can also utilize AI avatars generated by the electronic device, such as setting user avatars or wallpapers, which can be implemented using the method described in stage 5 of the aforementioned embodiments, and will not be detailed here.

[0244] As shown in Figure 24, the data required for electronically generating an AI avatar may include images from a gallery, as well as contextual and / or situational information. The contextual information can be referred to the description in the preceding embodiments, and will not be repeated here. Optionally, the contextual and situational information may come from the first application and / or other sensors in the electronic device.

[0245] AI models can be used for data processing in the AI ​​avatar generation process. For example, AI models can be used to select images and generate AI avatars. As shown in Figure 24, AI models can include AI models deployed in electronic devices and / or AI models deployed on servers (such as cloud servers).

[0246] The system service is primarily used to generate and display AI avatars based on the methods described in the foregoing embodiments. Optionally, the system service can also be used to provide a control entry point for AI avatar generation, which can be implemented using the third possible method described in stage 1 of the foregoing embodiments, and will not be detailed here.

[0247] In some embodiments of this application, as shown in FIG24, the system service may include an AI algorithm module, a media analysis module, a reference information extraction module, and a generation module.

[0248] The AI ​​algorithm module can provide algorithms for image analysis and processing, such as face recognition algorithms, expression recognition algorithms, face feature extraction algorithms, portrait feature extraction algorithms, occlusion recognition algorithms, and quality judgment algorithms.

[0249] As shown in Figure 24, the media analysis module may include a feature analysis module and a media library. The feature analysis module can be used to call the algorithms provided by the AI ​​algorithm module to extract features (such as portrait features) from the images in the image library and store the extracted feature data in the media library.

[0250] The reference information extraction module can be used to collect or extract contextual or situational information. The contextual and / or situational information extracted by the reference information extraction module can be used to generate keywords, prompts, etc. for system services, and can also be used to determine the transformation conditions for automatic transformation and the AI ​​image after automatic transformation.

[0251] The generation module can be a system service, system control, system application, or other form of module. As shown in Figure 24, the generation control module may include an interaction module, a data processing module, a scheduling module, and a transformation module. The interaction module can be used to implement functions related to user interaction, such as receiving instructions or operations, and displaying the user interface (UI). The data processing module can be used to select at least one image from all images of the same user for generating the AI ​​avatar, based on the feature data of images stored in the media library. The scheduling module can be used to determine and schedule the AI ​​model used to generate the AI ​​avatar, and to generate the AI ​​avatar using the scheduled AI model. The transformation module can be used to automatically transform the AI ​​avatar, wherein the transformed AI avatar can be determined based on contextual or situational information provided by the reference information extraction module.

[0252] Based on the system architecture shown in Figure 24, in the first possible solution, the methods described in stages 1 to 5 can be completed collaboratively by the image library application and the system service. In this scenario, the image library application can provide a control entry point for image and AI avatar generation, as well as for saving and displaying the generated AI avatars. The system service can be used to generate and display AI avatars. Specifically, the image library application can invoke the system service in response to a received first user operation (refer to the corresponding description in stage 1). After the system service is invoked, it can display the avatar selection interface as described in stage 1, generate and display AI avatars as described in stages 2 to 4, and feed the generated AI avatars back to the image library application, which can then save and display the generated AI avatars.

[0253] Based on the system architecture shown in Figure 24, in the second possible solution, the methods described in stages 1 to 5 can be collaboratively completed by the gallery application, the first application, and the system service. In this scenario, the gallery application can be used to provide images. The first application can be used to provide the control entry point for AI image generation and the AI ​​image generated by the application. The system service can be used to generate the AI ​​image. Specifically, after the system service is activated in response to the received first user operation (refer to the corresponding description in stage 1), it can display the avatar selection interface according to the method described in stage 1, and generate and display the AI ​​image according to the methods described in stages 2 to 4. The system service can also feed back the generated AI image to the first application. Alternatively, the system service can store the generated AI image in a designated storage area in the electronic device, and the first application can retrieve the AI ​​image generated by the system service from this designated storage area. The first application can apply the AI ​​image generated by the system service according to the method described in stage 5. In the above process, the first application can grant permissions to the system service, allowing the system service to read context information and situational information from the first application. The images acquired and processed by the system service during the generation of the AI ​​image can come from the gallery application. In this scenario, the reference information extraction module can collect contextual information according to a set method (e.g., periodically). When the reference information extraction module collects new contextual information, it can determine whether to generate a new AI avatar. If a new AI avatar needs to be generated, the generation module can generate a new AI avatar according to the method provided in the aforementioned embodiments and store the new AI avatar in a set storage area. The first application can query the set storage area for a new AI avatar according to a set method (e.g., periodically). If a new AI avatar is found, the first application can determine whether to update the AI ​​avatar, and when an update is needed, use the found new AI avatar to update the previously used AI avatar.

[0254] In the two possible solutions described above, the method for generating AI avatars through the system services of electronic devices can be implemented by referring to the method described in stage 4, which will not be repeated here.

[0255] In some embodiments of this application, when the electronic device is implemented using the structure shown in FIG2, the above-mentioned gallery application and first application can be deployed in the application layer shown in FIG2, and the above-mentioned system services and AI model can be deployed in the application framework layer shown in FIG2.

[0256] It should be understood that the display system architecture described above is merely an example. In practical applications, modules can be added or removed, or modules can be split or merged. This application does not impose specific limitations. The division of functional modules in the display system architecture described above is illustrative and only represents a logical functional division. In actual implementation, there may be other division methods, and the specific functions performed by each functional module may also be divided in other ways. For example, electronic devices may be divided into more or fewer functional services according to other factors, or the functions of each service may be divided in other ways, or they may not be divided into functional services but work as a whole. The names of the functional modules described above are merely examples, and the names of the functional modules in the embodiments of this application are not limited.

[0257] It should be noted that the application scenarios provided in the above embodiments are merely illustrative examples of the applicable scenarios of the embodiments of this application, and do not limit the applicable scenarios of the solutions of this application. Some methods or the same technical concepts provided in any of the above embodiments can also be applied in other embodiments or other scenarios, or can be combined with the methods provided in other embodiments. Specifically, they can be applied in combination with specific embodiments or specific scenarios, and will not be listed and described one by one in this application.

[0258] Based on the above embodiments and the same technical concept, this application also provides a method for AI content generation, as shown in FIG25, which may include:

[0259] S2501: The electronic device receives a first operation; wherein the first operation is used to select a first object among at least one object.

[0260] The first object can be a person, animal, or other object. The same applies to at least one object.

[0261] In some embodiments of this application, before receiving a first operation, the electronic device may display a first interface in response to a received third operation; wherein the first interface may include an element for selecting each object corresponding to each of at least one object; the first operation may be an operation performed on a first element included in a second interface, the first element being an element for selecting the first object corresponding to the first object. Optionally, the first element may also be used to indicate the first object. For example, the first element may be an image of the first object.

[0262] In one example, the first interface can be seen in the interface shown in Figure 4.

[0263] In some embodiments of this application, the third operation can be an operation performed on a third interface. The third interface can be an interface provided by a system service or application in an electronic device. Optionally, the third interface includes a fourth control, and the third operation can specifically be an operation performed on the fourth control. The fourth control is used to trigger the generation of AI content.

[0264] In one example, the third interface can be referred to as shown in Figure 5, Figure 7, or Figure 8, and the seventh control can be referred to as shown in Figure 5, Figure 6, Figure 7, or Figure 8 as the first control.

[0265] Optionally, the above method can be implemented by referring to the method described in stages 1 to 2 of the foregoing embodiments, which will not be described in detail here.

[0266] S2502: The electronic device determines one or more images containing the first object based on the selected first object.

[0267] In some embodiments of this application, the electronic device can select one or more images that meet target conditions from images containing a first object (e.g., all images containing the first object). Optionally, the target conditions may include: the included first object meets target features, or other default conditions. Target features may include at least one of the following: a first face angle or a first face angle range; a first pose; a first expression. Optionally, the target features may be determined based on generation requirements. For example, when the user-set generation requirements indicate the generation of an AI image in profile (e.g., a profile face or a side profile), the target features may include the angle or angle range corresponding to the profile.

[0268] Optionally, the method for the electronic device to determine one or more images can refer to the method for selecting at least one image described in stage 4 of the foregoing embodiments, and will not be repeated here.

[0269] S2503: The electronic device acquires the first artificial intelligence (AI) content of the first object; wherein the first AI content is generated based on the one or more images, and the first AI content includes the first AI image of the first object.

[0270] Optionally, before acquiring the first AI content, the electronic device may also receive user-defined generation requirements; wherein, the generation requirements are used to indicate the requirements for generating the AI ​​content of the first object. Based on this method, the first AI content can also be generated based on the user-defined generation requirements, that is, the first AI content can be generated based on the user-defined generation requirements and one or more images determined above.

[0271] For ease of description, the following embodiments will be illustrated by taking the generation of the first AI content based on the user-set generation requirements and one or more images determined above as an example.

[0272] Optionally, the generation requirements can be used as prompts when generating AI content for the first object.

[0273] In some embodiments of this application, the electronic device may receive a generation request set by the user in at least one of the following ways:

[0274] Method 1: The electronic device can display a first control for instructing the electronic device to automatically generate first recommendation information, and receive a second operation applied to the first control; wherein the second operation can be used to instruct the first recommendation information to be included in the generation requirements.

[0275] Optionally, the electronic device may also display a fifth control for instructing the electronic device to automatically generate second recommendation information, and receive a sixth operation applied to the fifth control; wherein the sixth operation may be used to instruct the second recommendation information to be included in the generation requirement. Similarly, the electronic device may recommend at least one piece of recommendation information to the user, and set the recommendation information selected by the user from at least one piece of recommendation information to be included in the generation requirement.

[0276] The first control mentioned above can be referred to the keyword control described in the previous embodiment, and the various recommendation information mentioned above can be referred to the keywords described in the previous embodiment. They will not be described in detail here.

[0277] In one example, the first control can be referred to as the keyword control 1 shown in the schematic diagram of Figure 18(b), and the first recommendation information can be referred to as the keyword "happy" shown in the schematic diagram of Figure 18(b).

[0278] In some embodiments of this application, the electronic device may generate first recommendation information based on first reference information, wherein the first reference information may include at least one of the following:

[0279] 1) The identity information of the first object.

[0280] For example, the identity of the first contact person mentioned in the scenario of Example 1.

[0281] 2) The facial features of the first subject.

[0282] 3) The relationship characteristics between the first object and other objects.

[0283] For example, in the scenario of Example 1, the degree of intimacy between the first contact person and the owner of the device.

[0284] 4) Media content displayed before receiving the first operation.

[0285] For example, the product image shown in Figure 19(a) in the scenario of Example 3, or the video content shown in Figure 23(a) in the scenario of Example 6.

[0286] 5) Information received from user input before receiving the first operation.

[0287] For example, the user-input text (“happy”) shown in the schematic diagram of Figure 18(a) in the scenario of Example 2.

[0288] 6) Location information of electronic devices.

[0289] Optionally, the electronic device can obtain some or all of the information in the first reference information through system services (for example, it can obtain some or all of the information in the first reference information through the reference information extraction module shown in Figure 24), or it can obtain some or all of the information in the first reference information in an application running before receiving the first operation. No specific restrictions are made in this embodiment.

[0290] Method 2: Display a second control, and in response to an operation performed on the second control, display multiple settings of the first setting item, and receive a fifth operation for selecting at least one setting among the multiple settings; wherein the fifth operation is also used to indicate that at least one setting is included in the generation requirement.

[0291] Optionally, the electronic device may also, in response to an operation acting on a sixth control, display multiple settings of the second setting item and receive a seventh operation for selecting at least one setting from the multiple settings of the second setting item; wherein the seventh operation is further used to instruct that at least one setting be included in the generation requirement. Similarly, the electronic device may display at least one control for selecting generation settings and include at least one setting selected by the user based on at least one control in the generation requirement.

[0292] The second control mentioned above can be referred to the selection control described in the previous embodiment, and the first setting item mentioned above can be referred to the style setting item described in the previous embodiment, etc., and will not be described in detail here.

[0293] In one example, the second control can refer to the selection control 1 shown in Figure 9, the first setting can refer to the style setting shown in Figure 9, and the multiple settings of the first setting can refer to the specific settings such as realistic, cartoon, 3D, etc. shown in the schematic diagram (a) in Figure 10.

[0294] Method 3: Receive information input by the user through a third control displayed on an electronic device, which is used to include in the generation requirements.

[0295] For example, the third control can refer to the input control 1 shown in FIG9. Of course, other display methods can also be used. No specific limitations are made in this embodiment.

[0296] Optionally, the above method can be implemented with reference to the method described in stage 3 of the foregoing embodiments, which will not be described in detail here.

[0297] In some embodiments of this application, the first AI content is any one of the following: a static image, a dynamic image, or a video. Of course, the first AI content can also be other types of content, which will not be listed here. The description of the AI ​​image can be found in the foregoing embodiments and will not be repeated here.

[0298] For example, the interface containing the first AI content can be seen in Figure 12.

[0299] Optionally, when generating the first AI content, the electronic device may further extract some features from the features (or feature vectors or feature information) of one or more images, and generate the first content based on the generation requirements and the extracted features. For example, taking multiple images as an example, some features (e.g., facial expression-related features) may be extracted from the features of one image, and some features (e.g., angle-related features) may be extracted from another image. Features of some images in the multiple images may also be omitted.

[0300] In some embodiments of this application, the electronic device can generate the first AI content itself or through a server. If the first AI content is generated through a server, the electronic device can send a generation request and feature vectors of each of one or more images to the server, instructing the server to generate AI content based on the generation request and the feature vectors of each of the one or more images. The electronic device can receive the first AI content generated by the server based on the generation request and the feature vectors of each of the one or more images. As an optional implementation, the electronic device can send a generation request to the server, which may carry the generation request and the feature vectors of each of the one or more images. The generation request can be used to request the server to generate AI content based on the generation request and the feature vectors of each of the one or more images.

[0301] Optionally, the method for generating the first AI content can also be implemented by referring to the method described in stage 4 of the foregoing embodiments, and will not be described in detail here. The method for displaying the first AI content can also be implemented by referring to the method described in stage 5 of the foregoing embodiments, and will not be described in detail here.

[0302] Optionally, after step S2503, the following step may also be included: the electronic device displays the first AI content. Optionally, the electronic device can display the first AI content through system services or applications. For example, the generation effect of the first AI content can be displayed through system services, or the first AI content applied to a specific application scenario can be displayed through applications. For details, please refer to the description in the foregoing embodiments, which will not be elaborated here.

[0303] In some embodiments of this application, the electronic device can also acquire second AI content of the first object. The second AI content may be generated by the electronic device based on at least one image containing the first object when set conditions are met, and the second AI content includes a second AI image of the first object. Optionally, after acquiring the second AI content, the electronic device can display the second AI content, for example, it can use the second AI content to update the already displayed first AI content. Optionally, the second AI content can also be generated based on set conditions. Optionally, the set conditions may include at least one of the following: reaching a set time; being at a set location; detecting a set event.

[0304] For example, the first AI content can be referenced to the wallpaper shown in Figure 15, and the second AI content can be referenced to the wallpaper shown in Figure 16.

[0305] In the above method, the setting conditions can be referred to the transformation conditions described in the foregoing embodiments, and will not be elaborated here.

[0306] In some embodiments of this application, after acquiring first AI content, the electronic device may receive a fourth operation and, in response to the fourth operation, apply the first AI content to at least one scenario before displaying the first AI content. The fourth operation instructs the first AI content to be applied to at least one scenario. Subsequently, when in any of the at least one scenario, the electronic device may display the first AI content.

[0307] For example, applying the first AI content to at least one scenario may specifically include at least one of the following: setting the first AI content as wallpaper; setting the first AI content as avatar; adding the first AI content to an emoji pack.

[0308] For example, any of the above scenarios can be a wallpaper display scenario, an avatar display scenario, or an emoji display scenario. In this example, the specific way the electronic device displays the first AI content can include: when any scenario is a wallpaper display scenario, displaying the first AI content as wallpaper; or, when any scenario is an avatar display scenario, displaying the first AI content as an avatar; or, when any scenario is an emoji display scenario, displaying the first AI content as an emoji.

[0309] For example, the fourth operation can be described in the example corresponding to Figure 13, which describes the operation performed on the interface shown in Figure 13.

[0310] The specific steps performed by the electronic device in the above method can be found in the relevant descriptions in the foregoing embodiments, and will not be repeated here.

[0311] Based on the above embodiments and the same technical concept, this application also provides a method for AI content generation, as shown in FIG26, which may include:

[0312] S2601: A first application in an electronic device displays a first interface; wherein the first interface includes a first control, which is used to trigger the generation of AI content.

[0313] The first interface and the first control can be referred to the third interface and the fourth control described in the corresponding method of Figure 25, respectively, and will not be described in detail here.

[0314] S2602: In response to an operation performed on a first control, the first application generates first AI content through a system service in the electronic device; wherein the first AI content is generated by the system service based on one or more images containing a first object, the first AI content includes a first AI image of the first object, the first object is an object selected by the user from at least one object, and the one or more images are determined by the system service based on the selected first object.

[0315] Optionally, the first AI content may also be generated based on user-defined generation requirements, which indicate the requirements for generating the AI ​​content for the first object.

[0316] The first object, the first AI content, the generation requirements set by the user, and the method for generating the first AI content can all be implemented using the relevant methods described in the corresponding method of Figure 25, and will not be repeated here.

[0317] Optionally, in the above method, the first application can invoke (or launch or call) a system service in response to an operation performed on the first control. After the system service is invoked (or launched or called), it can generate first AI content based on the method described in the foregoing embodiments. Optionally, after the system service generates the first AI content based on the method described in the foregoing embodiments, it can store the first AI content in a designated storage area in the electronic device, and the first application can retrieve the first AI content generated and stored by the system service from the designated storage area in the electronic device. Alternatively, after the system service generates the first AI content based on the method described in the foregoing embodiments, it can directly send the first AI content to the first application.

[0318] S2603: The first application displays the first AI content.

[0319] In some embodiments of this application, the first application may further acquire second AI content generated by the system service when set conditions are met, and update the first AI content to the second AI content. The second AI content is generated by the system service based on at least one image containing the first object when the set conditions are met, and the second AI content includes a second AI image of the first object. Optionally, the second AI content may also be generated based on the set conditions.

[0320] The process of setting conditions and generating second AI content when the system service meets the set conditions can be implemented by referring to the relevant methods in the corresponding method in Figure 25, and will not be elaborated here.

[0321] Optionally, the above method can also be implemented using the second possible scheme described in the corresponding method of Figure 24, which will not be repeated here.

[0322] The specific steps performed by the electronic device in the above method can be found in the relevant descriptions in the foregoing embodiments, and will not be repeated here.

[0323] Based on the above embodiments and the same technical concept, this application also provides an electronic device for implementing the method for AI content generation provided in this application. As shown in FIG27, the electronic device 2700 may include: a memory 2701, one or more processors 2702, and one or more computer programs (not shown in the figure). The above-mentioned devices can be coupled through one or more communication buses 2703. Optionally, the electronic device 2700 may also include a display screen 2704.

[0324] The memory 2701 stores one or more computer programs (code), and the one or more computer programs include computer instructions; one or more processors 2702 call the computer instructions stored in the memory 2701, causing the electronic device 2700 to execute the method for AI content generation provided in the embodiments of this application.

[0325] In a specific implementation, memory 2701 may include high-speed random access memory, and may also include non-volatile memory, such as one or more disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. Memory 2701 may store an operating system (hereinafter referred to as the system), such as embedded operating systems like Android, iOS, Windows, or Linux. Memory 2701 can be used to store implementation programs of the embodiments of this application. Memory 2701 may also store network communication programs, which can be used to communicate with one or more additional devices, one or more user devices, or one or more network devices.

[0326] One or more processors 2702 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs according to the present application.

[0327] Display screen 2704 is used to display application interfaces and other related user interfaces.

[0328] It should be noted that Figure 27 is only one implementation of the electronic device 2700 provided in this application embodiment. In actual applications, the electronic device 2700 may include more or fewer components. For details, please refer to the specific structure and description shown in Figure 1. No limitations are imposed here.

[0329] Based on the above embodiments and the same technical concept, this application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method provided in the above embodiments.

[0330] Based on the above embodiments and the same technical concept, this application also provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are run on a computer, the computer performs the method provided in the above embodiments.

[0331] Based on the above embodiments and the same technical concept, this application also provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are run on a computer, the computer performs the method provided in the above embodiments.

[0332] The methods provided in this application can be implemented, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, they can be implemented, in whole or in part, in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs), or semiconductor media (e.g., SSDs), etc.

[0333] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for artificial intelligence, AI, content generation, applied to an electronic device, comprising: The method includes: ​ Receive a first operation; wherein the first operation is used to select a first object among at least one object; Determine one or more images containing the first object based on the selected first object; Obtain the first AI content of the first object; wherein the first AI content is generated based on the one or more images, and the first AI content includes the first AI image of the first object.

2. The method of claim 1, wherein, The method further includes: Receive user-defined generation requirements; wherein the generation requirements are used to indicate the requirements for generating AI content for the first object; The first AI content is also generated based on the generation requirements.

3. The method of claim 1 or 2, wherein, The first AI content is any one of the following: still image, moving image, video.

4. The method according to any one of claims 1 to 3, characterized in that, The first object is a person or an animal.

5. The method according to any one of claims 1 to 4, characterized in that, The acquisition of the first artificial intelligence (AI) content of the first object includes: The first AI content is generated based on the one or more images; or Obtain the first AI content generated by the server based on the one or more images.

6. The method of claim 5, wherein, The acquisition server generates the first AI content based on the one or more images, including: Send the feature vector of each of the one or more images to the server, and instruct the server to generate AI content based on the feature vector of each of the one or more images; Receive the first AI content generated by the server based on the feature vector of each of the one or more images, sent by the server.

7. The method according to any one of claims 1 to 6, characterized in that, The generation requirements set by the receiving user include: Displays the first recommendation information automatically generated by the electronic device; Receive a second operation; wherein the second operation is used to instruct the first recommendation information to be included in the generation requirement.

8. The method of claim 7, wherein, The first recommendation information is generated based on the first reference information, which includes at least one of the following: The identity information of the first object; The facial features of the first object; The relationship characteristics between the first object and other objects; Media content displayed before receiving the first operation; Information input by the user received before the first operation; The location information of the electronic device.

9. The method according to any one of claims 1 to 8, characterized in that, The step of determining one or more images containing the first object based on the selected first object includes: Select one or more images from the images containing the first object that match the target features.

10. The method of claim 9, wherein, The target feature includes at least one of the following: First face angle or first face angle range; First stance; First expression.

11. The method of claim 9 or 10, wherein, Some or all of the target features are determined based on the requirements for instructing the generation of the AI ​​content for the first object.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: Obtain the second AI content of the first object; wherein the second AI content is generated based on at least one image containing the first object when set conditions are met, and the second AI content includes the second AI image of the first object.

13. The method of claim 12, wherein, The second AI content is also generated based on the set conditions.

14. The method of claim 12 or 13, wherein, The setting conditions include at least one of the following: The set time has arrived; Located at the designated location; A set event has been detected.

15. The method according to any one of claims 1 to 14, wherein The method further includes: In response to the received third operation, a first interface is displayed; wherein the first interface includes an element for selecting each of the at least one object; The first operation is an operation performed on a first element included in the second interface, where the first element is the element corresponding to the first object used to select the first object.

16. The method of claim 15, wherein, The first element is also used to indicate the first object.

17. The method of claim 15 or 16, wherein, The first element is the avatar of the first object.

18. The method of any one of claims 1 to 17, wherein, After obtaining the first AI content of the first object, the method further includes: Display the content of the first AI.

19. The method of claim 18, wherein, Before displaying the first AI content, the method further includes: Receive a fourth operation; wherein the fourth operation is used to instruct the first AI content to be applied to at least one scenario; The display of the first AI content includes: The first AI content is displayed when the user is in any of the at least one scenario.

20. The method of claim 19, wherein, Applying the first AI content to at least one scenario includes at least one of the following: Set the first AI content as wallpaper; Set the first AI content as the profile picture; Add the first AI content to the emoji pack.

21. The method of claim 19 or 20, wherein, The scenario can be a wallpaper display scenario, an avatar display scenario, or an emoticon display scenario; The display of the first AI content includes: When any of the scenarios is a wallpaper display scenario, the first AI content is displayed as wallpaper; or When any of the scenarios is an avatar display scenario, the first AI content is displayed as an avatar; or When any of the scenarios is an emoji display scenario, the first AI content is displayed as an emoji.

22. An electronic device, comprising: The electronic device includes a memory and one or more processors; The memory is used to store computer program code, which includes computer instructions; when the computer instructions are executed by the one or more processors, the electronic device performs the method as described in any one of claims 1 to 21.

23. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when run on an electronic device, causes the electronic device to perform the method as described in any one of claims 1 to 21.

24. A computer program product, characterised in that, The computer program product includes a computer program or instructions that, when executed on an electronic device, cause the electronic device to perform the method as described in any one of claims 1 to 21.

Images