Electronic device and method for regenerating image

Abstract

An electronic device, according to one embodiment, may display, on a display, an image including at least one object. The electronic device, according to one embodiment, may display, on at least a portion of the image, a regeneration object that calls an image regeneration function on the basis of recognition of an object in the displayed image. The electronic device, according to one embodiment, may display, on at least a portion of the display on which the image is displayed, a plurality of image themes determined on the basis of object characteristics recognized from the image, on the basis of a first input for selecting the regeneration object. The electronic device, according to one embodiment, may generate, by using generative artificial intelligence (AI), a plurality of object images corresponding to a first image theme style, on the basis of a second input for selecting a first image theme from among the image themes. The electronic device, according to one embodiment, may display a first object image from among the plurality of generated object images.

Description

Electronic device and method for reproducing images

[0001] The present invention relates to an electronic device and method for reproducing an image.

[0002] Artificial Intelligence (AI) technologies applied to electronic devices are rapidly advancing. In particular, the evolution of AI capabilities is leading to the implementation of generative AI. Generative AI utilizes machine learning and deep learning to generate similar content based on existing content, such as text, audio, and / or images. For example, generative AI can be applied to improving image quality or creating or editing new images based on existing ones.

[0003] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0004] One embodiment proposes an electronic device, method, and recording medium for regenerating an image based on generative AI (e.g., generative AI).

[0005] One embodiment proposes an electronic device, method and recording medium that provide a user interface that supports regenerating a new style of image while maintaining similarity to a facial image.

[0006] One embodiment proposes an electronic device, method and recording medium capable of generating personalized prompts that engage in image generation based on facial / background features within an image, and regenerating / editing the image based on the prompts.

[0007] The problem to be solved in this disclosure is not limited to the problem mentioned above, and may be expanded in various ways without departing from the spirit and scope of this disclosure.

[0008] An electronic device according to one embodiment may include a display. The electronic device according to one embodiment may include a processor. The electronic device according to one embodiment may include a memory that stores instructions executable by the processor. The instructions according to one embodiment, when executed by the processor, may cause the electronic device to display an image including at least one object on the display. The instructions according to one embodiment may cause the electronic device to display a regenerated object that calls an image regeneration function on at least a portion of the image based on an object being recognized in the displayed image. The instructions according to one embodiment may cause the electronic device to display a plurality of image themes determined based on object features recognized from the image on at least a portion of the display on which the image is displayed, based on a first input selecting the regenerated object. The instructions according to one embodiment may cause the electronic device to generate a plurality of object images corresponding to the style of the first image theme using generative artificial intelligence (AI), based on a second input selecting a first image theme from among the image themes. Commands according to one embodiment may cause the electronic device to display a first object image from among the plurality of generated object images.

[0009] A method for supporting image regeneration of an electronic device according to one embodiment may include an operation of displaying an image including at least one person on the display. According to one embodiment, the method may include an operation of displaying a regenerated object that calls an image regeneration function on at least a portion of the image based on an object recognized in the displayed image. According to one embodiment, the method may include an operation of displaying a plurality of image themes determined based on object characteristics recognized from the image on at least a portion of the display on which the image is displayed, based on a first input selecting the regenerated object. According to one embodiment, the method may include an operation of generating a plurality of object images corresponding to the style of the first image theme using generative artificial intelligence (AI), based on a second input selecting a first image theme from among the image themes. According to one embodiment, the method may include an operation of displaying a first object image from among the generated plurality of object images.

[0010] A non-transitory computer-readable medium storing instructions that, when executed by a processor of an electronic device according to one embodiment, cause the processor to perform operations included in a method for supporting image regeneration of the electronic device.

[0011] According to an electronic device, method and recording medium according to one embodiment, an object image having similar object features can be generated based on an image including an object (e.g., a person) through generative artificial intelligence.

[0012] In one embodiment, a personalized prompt can be generated by analyzing an object (e.g., a face) / background in an image to regenerate an object image, and a prompt editing function can be provided to allow a user to delete, add, or edit the prompt, thereby assisting the user in regenerating a desired object image.

[0013] According to one embodiment, a new user experience (UX) can be provided that allows users to easily and intuitively quickly regenerate images by providing various styles of image themes that can configure object images according to object characteristics.

[0014] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0015] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0016] FIG. 1A is a block diagram of an electronic device within a network environment according to various embodiments.

[0017] Figure 1b illustrates the configuration of a generative AI system according to one embodiment.

[0018] FIG. 2 illustrates configurations supporting an image regeneration function included in an electronic device according to one embodiment.

[0019] FIG. 3 illustrates a method for supporting image regeneration of an electronic device according to one embodiment.

[0020] FIGS. 4A and 4B illustrate user interface screens that support image regeneration of an electronic device according to one embodiment.

[0021] FIGS. 5A and 5B illustrate user interface screens that support image regeneration of an electronic device according to one embodiment.

[0022] FIGS. 6 to 8 are drawings for explaining automatic prompt generation and image preprocessing for generating optimal results of an object image according to one embodiment.

[0023] FIGS. 9A and 9B illustrate interface screens that support image reproduction of an electronic device according to one embodiment.

[0024] FIG. 10 illustrates user interface screens that support image regeneration of an electronic device according to one embodiment.

[0025] FIG. 11 illustrates user interface screens that support image regeneration of an electronic device according to one embodiment.

[0026] FIGS. 12A through 12C illustrate user interface screens that support image regeneration of an electronic device according to one embodiment.

[0027] FIGS. 13A and 13B illustrate user interface screens that support image regeneration of an electronic device according to one embodiment.

[0028] FIG. 1A is a block diagram of an electronic device within a network environment, according to one embodiment.

[0029] Referring to FIG. 1A, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160) (or display), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0030] The processor (120) includes at least one processing circuitry, and the at least one processing circuitry may control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) by executing, for example, software (e.g., a program (140)), and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in the volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in the non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0031] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, in the electronic device (101) itself where artificial intelligence is performed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0032] The memory (130) can store various data used by at least one component (e.g., the processor (120) or the sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., the program (140)) and input data or output data for commands related thereto. The memory (130) can include a volatile memory (132) or a non-volatile memory (134). The memory (130) can store instructions executable by the processor (120) or the electronic device (101).

[0033] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0034] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0035] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0036] The display module (160) (or display) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. In one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0037] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0038] The sensor module (176) may include at least one sensor. The sensor module (176) may detect an operating state (e.g., power or temperature) of the electronic device (101) or an external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0039] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0040] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0041] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0042] The camera module (180) includes at least one camera and can capture still images and moving images. In one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0043] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least a part of a power management integrated circuit (PMIC).

[0044] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0045] The communication module (190) includes at least one communication circuit and can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., the electronic device (102), the electronic device (104), or the server (108)), and the performance of communication through the established communication channel. The communication module (190) operates independently from the processor (120) (e.g., an application processor) and can include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) can include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0046] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0047] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0048] In one embodiment, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0049] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0050] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0051] The electronic device (101) according to the embodiments disclosed in this document may take various forms. The electronic device (101) may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a home appliance. The electronic device according to the embodiments of this document is not limited to the aforementioned devices.

[0052] An electronic device (101) according to one embodiment may support a generative AI (generative artificial intelligence) function. The generative AI function may refer to a technology that generates new content based on content and can generate new forms of AI content (or generative content) by utilizing given input data or information. Here, AI content may refer to content (e.g., 3D objects, images, videos, audio, screen information, or text) that is entirely generated (or reconstructed / edited) or partially generated (or reconstructed / edited) based on generative AI.

[0053] An electronic device (101) according to one embodiment may support a generative AI function in conjunction with a server (108). At least one of the electronic device (101) or the server (108) according to one embodiment may include the configuration of the generative AI system illustrated in FIG. 1B.

[0054] Figure 1b illustrates the configuration of a generative AI system according to one embodiment.

[0055] Referring to FIG. 1b, the generative AI system may include a user interface (10100), an AI framework (10200), a generative AI model (10300), an application and service component (10400), and a database component (10500).

[0056] A user interface (e.g., a user query / response interface) (10100) according to one embodiment may receive a user query. The user query input may be in the form of natural language, images, and videos. The user interface (10100) may transmit not only data regarding the user query input but also context information to the AI ​​framework (10200). The context information may include various additional information at the time of user input. In addition, the user query input may be in a form that mixes the above-described natural language, images, sounds, and context information. In addition, the user query input may be in a non-natural language form that does not generate natural language, such as a menu selection (e.g., a creation request or a modification request). The user interface (10100) may output the results of a generative artificial intelligence system to the user. The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user.

[0057] An AI framework (10200) according to one embodiment can receive a user query input and coordinate and control each component necessary to perform the user's intention based on the user's query input. The AI ​​framework (10200) can include a prompt design component (10210), an API and plug-in management component (APIs / Plugins Management component) (10230), and an output modification component (10250).

[0058] A user query or action entered in a user interface (10100) according to one embodiment may be transmitted to a prompt design component (10210). The prompt design component (10210) may be used to generate prompts suitable for input into a large language model (LLM) or a large multimodal model (LMM). The prompt design component (10210) may be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The prompt design component (10210) may access a database component (10500) (e.g., a knowledge component) containing user preference data, a prompt library, and prompt examples to generate prompts and pass them to the large language model (LLM) or the large multimodal model (LMM).

[0059] According to one embodiment, the API and plugin management component (10230) can communicate with external information when a request for additional information is made when user input is passed as input to a generative model. The API and plugin management component (10230) establishes a channel for communication with the external application and service component (10400) (e.g., AI Interface) through an application programming interface (API), thereby enabling access to various data sources. In addition, the API and plugin management component (10230) can request an action through the API to perform a final user query, rather than an intermediate result, if the action needs to be performed by the application or service. Information obtained from an external source can be passed as input to the generative model along with the user input.

[0060] An output modification component (10250) according to one embodiment can fine-tune the output of a generative model. For example, the output modification component (10250) can verify that content generated through a language model (LLM) or a large-scale multi-modal model (LMM) is not irrelevant, does not contain biased content, or does not contain harmful content. In addition, the output modification component (10250) can determine to what extent the content matches the result desired by the user and can perform additional processing if necessary. Additionally, the output modification component (10250) can configure and provide hints to the user to avoid undesired output.

[0061] A generative AI model (10300) according to one embodiment generally refers to an artificial intelligence neural network that creates new types of data based on user input information. Models that generate images may typically include generative adversarial networks (GANs) and variational autoencoders (VAEs). For example, the generative AI model may be a diffusion-based generative model that uses VAE and a transformer structure. Furthermore, a language-generating model may refer to a model trained to statistically generate the most appropriate output based on input values. Among generative AI models (10300), language-generating models may be, for example, models such as CHAT-GPT 3 and CHAT-GPT 4. As another example, large multimodal models (LMMs) may be models that recognize various types of data input, such as text, images, and voice, and generate corresponding new data.

[0062] An electronic device (101) according to one embodiment may be implemented to provide a generative AI function (or operation / service) using a part of the AI ​​system of FIG. 1B.

[0063] An electronic device (101) according to one embodiment may provide a function for generating an AI portrait image using a generative AI function. For example, the electronic device (101) may generate an object image (e.g., a portrait image) using the generative AI system of FIG. 1B.

[0064] The electronic device (101) illustrated in FIG. 1A according to various embodiments disclosed below can be implemented, and the same reference numbers are given to components that are substantially the same as the configuration disclosed in FIG. 1A described above, and redundant descriptions of their functions can be omitted.

[0065] FIG. 2 illustrates configurations supporting an image regeneration function included in an electronic device according to one embodiment.

[0066] Referring to FIG. 2, in one embodiment, the electronic device (101) of FIG. 1A may include a prompt manager (210) and an AI image model (220) for supporting an AI image generation function. The AI ​​image model (220) may be an artificial intelligence model that generates an AI image (217) (e.g., an object image, a portrait image) based on an input image (211) and a prompt (215).

[0067] According to one embodiment, the processor (120) of the electronic device (101) can control the overall operation related to object image regeneration (or editing) based on the prompt manager (210) and the AI ​​image model (220).

[0068] A prompt manager (210) according to one embodiment can generate a prompt (215) involved in object image creation and transmit the prompt (215) to an AI image model (220). In FIG. 2, the prompt (215) is exemplarily divided into a feature prompt (215_a) and a theme prompt (215_b), but this is only for explanation purposes, and these can be integrated into a prompt (215).

[0069] A prompt manager (210) according to one embodiment may analyze an input image (211) (e.g., features / facial features of a person included in the image) to generate a personalized prompt (215) related to an object (e.g., a person) included in the image. For example, the prompt manager (210) may analyze facial / background features of the image (211) to generate a prompt (e.g., feature prompt (215_a)) that may be involved in generating an object image (e.g., a portrait image). The prompt manager (210) may determine at least one image theme optimized for (or recommended) a person / face included in the image (211) based on the image analysis result, and generate a prompt (e.g., theme prompt (215_b)) that may be involved in generating / regenerating an object image to which the image theme style is applied.

[0070] A prompt manager (210) according to one embodiment may output a designated prompt (e.g., a template prompt) in relation to an image theme (or style). For example, an image theme may be composed of multiple image themes (e.g., illustration, 3D character, vintage, water color, cartoon, etc.). Each image theme may have different prompts for generating an object image suitable for each theme style. For example, a cartoon-style image theme may require a prompt for changing an input face into a cartoon-style face, and a water color-style image theme may require a prompt for changing an input face into a water color-style face. Prompts related to image themes may be stored in the electronic device (101) in a pre-designated format.

[0071] A prompt manager (210) according to one embodiment may transmit a prompt (e.g., feature prompt (215_a)) generated through image analysis to an AI image model (220). The processor (120) of the electronic device (101) may provide a prompt editing function (e.g., deleting or adding a prompt) to a user interface (UI) related to an object image. For example, the feature prompt (215_a) may be provided as a prompt keyword through a UI screen. When prompt editing is requested by a user, the electronic device (101) may regenerate an object image (e.g., an AI portrait image) generated based on the prompt requested for editing by the user.

[0072] An AI image model (220) according to one embodiment can generate (or regenerate) at least one AI image (217) (e.g., an object image, a portrait image) based on a prompt (215_a, 215_b) transmitted from a prompt manager (210) and an input image (211).

[0073] According to one embodiment, the AI ​​image model (220) can generate at least one object image having the style of the theme applied based on a prompt related to the selected image theme when an image theme is selected by a user.

[0074] According to one embodiment, the prompt manager (210) and the AI ​​image model (220) are described as being implemented in the electronic device (101), but the prompt manager (210) and the AI ​​image model (220) may be implemented in a server device that communicates with the electronic device (101) to provide an object image service to the electronic device (101). As another example, one of the prompt manager (210) and the AI ​​image model (220) may be implemented in the electronic device (101), and the other may be implemented in the server device.

[0075] An electronic device (101) of FIG. 1 according to one embodiment may include a display (e.g., a display module (160)), a processor (120), and a memory (130). The memory (130) may store instructions executable by the processor (120) or the electronic device (101). Operations performed in the electronic device (101) may be executed by the processor (120), which includes various processing circuitry and / or executable program elements.

[0076] An electronic device according to one embodiment may include a display. The electronic device according to one embodiment may include a processor. The electronic device according to one embodiment may include a memory that stores instructions executable by the processor. The instructions according to one embodiment, when executed by the processor, may cause the electronic device to display an image including at least one object on the display. The instructions according to one embodiment may cause the electronic device to display a regenerated object that calls an image regeneration function on at least a portion of the image based on an object being recognized in the displayed image. The instructions according to one embodiment may cause the electronic device to display a plurality of image themes determined based on object features recognized from the image on at least a portion of the display on which the image is displayed, based on a first input selecting the regenerated object. The instructions according to one embodiment may cause the electronic device to generate a plurality of object images corresponding to a first image theme style using generative artificial intelligence (AI), based on an input selecting a first image theme from among the image themes. Commands according to one embodiment may cause the electronic device to display a first object image from among the plurality of generated object images.

[0077] The commands according to one embodiment may cause the electronic device to display the first object image, further displaying at least one indicator indicating that another object image is present below the first object image and a graphic object that visually distinguishes the first image theme selected by the second input from other image themes.

[0078] The commands according to one embodiment may cause the electronic device to change a first object image displayed on the display to a second object image based on a motion input that drags the first object image displayed on the display.

[0079] The commands according to one embodiment may cause the electronic device to display an area frame representing a face area of ​​a person included in an image displayed on the display based on a face being recognized from the image, as an operation of displaying the regenerated object.

[0080] The commands according to one embodiment may cause the electronic device to display guide information indicating that an object image is being generated from the generative AI while generating a plurality of object images corresponding to the image theme.

[0081] The commands according to one embodiment may cause the electronic device to display the first object image, analyze a person and a background from the image, and generate a personalized prompt corresponding to the object and background features based on the image.

[0082] The commands according to one embodiment may cause the electronic device to display prompt editing function items on at least a portion of the display based on the generated prompt.

[0083] The above prompt editing function items according to one embodiment may include at least one of a keyword item, an addition item, or a deletion item corresponding to the prompt.

[0084] The commands according to one embodiment may cause the electronic device to regenerate the first object image using an edited prompt as input data based on an input requesting prompt editing detected through the prompt editing function items.

[0085] The commands according to one embodiment may cause the electronic device to display the prompt editing function items on at least a portion of the display, and to display the keyword items by dividing them into a negative category involved in a feature removal function within an image and a positive category involved in a feature addition or maintenance function within an image.

[0086] The commands according to one embodiment may cause the electronic device to further generate the personalized prompt based on data related to the specific person obtained from the application when a second image including the specific person is selected through an application supporting an image setting function as an operation for generating the personalized prompt.

[0087] An application that supports the image setting according to one embodiment may include at least one of a contact application, a screen setting application, a profile setting application, or a call application.

[0088] According to one embodiment, the commands may cause the electronic device to change the size or background image of the called object image according to the characteristics of the executed application based on at least one of the screen ratio, screen composition, and background characteristics of the executed application when the object image is called through the executed application when the application is executed.

[0089] The embodiments described below may be drawings for explaining operations related to a service for regenerating an image based on artificial intelligence in an electronic device (101). At least two embodiments among the embodiments may be combined and operated. Alternatively, when two embodiments are combined, at least some of the configurations and / or at least some of the operations included in each embodiment may be omitted. Hereinafter, an object (or a specific object, a main object) included in an image is described as an example of a person, and the object image is described as a portrait image, but the present invention is not limited thereto, and the embodiments of the present disclosure may be applied to other objects as well.

[0090] FIG. 3 illustrates a method for supporting image regeneration of an electronic device according to one embodiment.

[0091] The functions or operations described in FIG. 3 may be understood as functions performed by a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1). The processor (120) may execute commands (e.g., instructions) stored in a memory (e.g., memory (130) of FIG. 1) to implement a software module, and may control hardware (e.g., communication module (180) of FIG. 1) associated with the function.

[0092] Referring to FIG. 3, the processor (120) of the electronic device (101) according to one embodiment may display an image including at least one object (e.g., a person or a face) on the display in operation 310.

[0093] For example, the processor (120) may execute an application (e.g., a gallery application, a contact application, etc.) that supports an image list and an image editing function, and may display an image on the display based on an input in which an image including at least one object (e.g., a person or a face) is selected from the image list. The processor (120) may display an image including at least one object (e.g., a person or a face) through a UI screen related to the image.

[0094] In operation 320, the processor (120) may determine whether an object (e.g., a person or a face) is recognized in the displayed image.

[0095] According to one embodiment, the processor (120) may perform object recognition on the image by performing segmentation on the image. As a result of the object recognition, the processor (120) may recognize an object area and separate the object area from the background area.

[0096] According to one embodiment, the processor (120) determines that a face is recognized when the size of an area (or face area) containing facial features in the image is greater than or equal to a specified size, and if the face area is less than or equal to the specified size, the face may not be recognized in the image.

[0097] For example, the processor (120) may determine that a person's face is recognized if the image includes features of the eyes, nose, and mouth, which are major parts of the face, using a face recognition algorithm (e.g., PCA, principal component analysis).

[0098] In operation 330, if an object (e.g., a person or a face) is recognized in the image (e.g., yes in operation 320), the processor (120) may display a generative object (e.g., an AI portrait object) on the UI screen displayed on the display to enter an image regeneration function (e.g., an AI portrait function).

[0099] If the processor (120) does not recognize an object (e.g., a face) in the image (e.g., no in operation 320), the regenerated object (e.g., an AI portrait object) is not displayed, and the process of FIG. 3 may be terminated.

[0100] In operation 335, the processor (120) may detect an input (e.g., a touch or tap) that selects a regenerated object (e.g., an AI portrait object) displayed on the UI screen.

[0101] In some embodiments, operations 330 and 335 may be omitted.

[0102] In operation 340, the processor (120) may display a plurality of image themes (e.g., portrait themes (or portrait theme items)) on at least a portion of a UI screen where an image is displayed based on a detected input selecting a regenerated object (e.g., an AI portrait object).

[0103] For example, the processor (120) may determine (or recommend, select) image themes (e.g., portrait themes) optimized for a recognized object (e.g., a person or a face) based on object and background features (e.g., facial features, color, background complexity) analyzed through image analysis, and may display a plurality of determined image themes (e.g., portrait themes) in an area (e.g., bottom) of an image displayed on a UI screen.

[0104] For example, if the image has bright colors and little facial expression variation, a watercolor-style image theme may be recommended (or selected). If the image includes a person smiling broadly, a caricature-style image theme may be recommended. For another example, if a baby is recognized in the image, a cartoon-style image theme may be recommended.

[0105] In operation 350, the processor (120) may detect an input for selecting a first image theme among a plurality of image themes (e.g., portrait themes) displayed on the display.

[0106] In the 360 ​​motion, the processor (120) can generate at least one object image (e.g., a portrait image) to which the first image theme style is applied using generative AI (artificial intelligence) based on an input for selecting the first image theme.

[0107] According to one embodiment, a processor (120) may generate at least one object image (e.g., a portrait image) based on a prompt related to a first image theme. For example, the processor (120) may output a prompt (e.g., theme prompt (215_b)) for generating an object image in a first image theme style through a prompt manager (210) illustrated in FIG. 2b, and may generate at least one object image to which the first image theme style is applied through an AI image model (220).

[0108] According to one embodiment, the processor (120) may generate a personalized prompt (e.g., feature prompt (215_a)) related to a portrait based on the characteristics of a person / background of an image as a result of image analysis, and may generate at least one object image to which a first image theme style is applied using the generated prompt. A specific description related to the personalized prompt (e.g., feature prompt (215_a)) will be described with reference to FIG. 6.

[0109] According to one embodiment, a processor (120) may generate at least one object image by using as input to an AI image model (220) at least one of a prompt for generating an object image in a first image theme style (e.g., theme prompt (215_b)) and a personalized prompt (e.g., feature prompt (215_a)).

[0110] According to one embodiment, the processor (120) may display information (or a screen) on the display while generating object images (e.g., portrait images) in relation to the selected first image theme.

[0111] In operation 370, the processor (120) can display at least one generated object image (e.g., a portrait image) on the display.

[0112] For example, the processor (120) may display an image displayed on the UI screen as one of at least one object image generated. If multiple object images are generated, the processor (120) may display an indicator on the UI screen indicating that there is an object image different from the first object image displayed.

[0113] Although not shown in FIG. 3, according to one embodiment, the processor (120) may include an action of providing, on a UI screen, edit items (e.g., prompt keyword items, deletion items, and addition items) that can edit a prompt generated by an image analysis result (e.g., a personalized prompt based on face / background features (e.g., feature prompt (215_a))) and an action of regenerating an object image generated based on a prompt editing request.

[0114] According to one embodiment, an operation supporting object image creation or / and editing in an electronic device (101) may be supported in an image editing function or / and a profile editing function, but is not limited thereto, and image editing, image regeneration and / or editing operations may be supported in a function / application related to image attachment, sharing or transmission.

[0115] The following drawings 4a, 4b, 5a, and 5b illustrate examples of calling a function for regenerating / editing an object image from an image using an image editing function, but are not limited thereto. The display format of the user interface (UI) screen described in the following embodiments is merely an example and may be changed according to design or settings.

[0116] FIGS. 4A and 4B illustrate user interface screens that support image regeneration of an electronic device according to one embodiment.

[0117] Referring to FIGS. 4A and 4B , an electronic device (101) (or a processor (120)) according to one embodiment selects an image (411) including at least one person and then, based on an input that calls an image regeneration (e.g., generative AI) function, displays a UI screen (410) that supports an image (411) regeneration function. <401> As shown in , it can be displayed on a display (e.g., display module (160) of FIG. 1). <401> It may be a screen by the operation 310 to 330 of Fig. 3.

[0118] For example, the electronic device (101) may display a user interface (UI) screen (410) based on an input for selecting an image from an image list (e.g., a gallery function, a contact's profile function) or an input for calling an image regeneration function (e.g., a generative AI function / service) in an image editing screen.

[0119] The UI screen (410) may include at least one of a regeneration object (412) (e.g., generate object, AI execution object) that executes (or requests) to regenerate an image based on an image (411) displayed on the display and / or a service object (413) (e.g., generative portrait object, portrait service object) that calls an image theme service and an image regeneration service. For example, the regeneration object (413) may be displayed overlapping at least a portion of the displayed image (411), but is not limited thereto.

[0120] According to one embodiment, the electronic device (101) may display a theme object (413) when a face is recognized from an image (411) displayed on the display. The electronic device (101) may recognize a face from an image when the size of an area (hereinafter, “face area”) including facial features (e.g., eyes, nose, mouth, etc.) from the image is greater than or equal to a specified size, and may fail to recognize the face when the size of the face area is less than or equal to the specified size. When face recognition from the image (411) fails, the theme object (413) may not be displayed on the UI screen (410) or may be displayed as inactive (e.g., shaded). When a face is recognized from the image (411), the regenerated object (412) may be inactive and the theme object (413) may be displayed as active. The electronic device (101) may induce a user selection input for the theme object (413) due to the inactive display of the regenerated object (412).

[0121] <401> The UI screen (410) may be a screen that recognizes a face area (e.g., a first face area and a second face area) larger than a size specified in the image (411) and displays a theme object (413). The electronic device (101) detects an input (413_5) for selecting a theme object (e.g., 413). <402> As shown in , a UI screen (410) may be displayed in which a plurality of image themes (e.g., portrait image themes) (420) recommended (or selected) corresponding to a face included in an image (411) are displayed. <402> The UI screen (410) shown in may display an area frame (422) defining a face area recognized in an image (411) and guide information (e.g., select a style you wish to apply) (423) that guides theme selection when the regenerated object (412) disappears.

[0122] For example, if the image (411) includes a first person and a second person, the electronic device (101) can recognize a first face area and a second face area in the image (411), display a first area frame (4221) in the first face area, and display a second area frame (4222) in the second face area.

[0123] According to one embodiment, when an image includes multiple people, the electronic device (101) may designate at least one person by an input of selecting an area frame (422) and generate an object image corresponding to the designated at least one person. For example, when a user selects (e.g., long press, single touch input) a first area frame (4221) on a UI screen (410), the electronic device (101) may create a portrait image using the first person (e.g., female), or when a second area frame (4222) is selected, the electronic device (101) may create a portrait image using the second person (e.g., male). As another example, when a user selects (e.g., multi-touch) the first area frame (4221) and the second area frame (4222) on the UI screen (410), the electronic device (101) may also create portrait images using both the first person and the second person.

[0124] According to one embodiment, the electronic device (101) may graphically process an area frame selected by the user in the image (411) so that it is visually distinct from an area frame not selected by the user (e.g., a first area frame (4221) selected by the user is displayed with a first thickness, and a second area frame (4222) is displayed with a second thickness that is thinner than the first thickness).

[0125] According to one embodiment, the electronic device (101) may provide a function of displaying an area frame (422) corresponding to a person selected by the user when the user selects and designates a face area of ​​a person included in an image (411) by a touch gesture (e.g., a drag input).

[0126] <402> In the UI screen (410) shown in , the display position of the image themes (420) can be changed by a movement input (e.g., touch and drag, swipe) moving in one direction. <402> It may be a screen by the 340 operation of Fig. 3.

[0127] An electronic device (101) according to one embodiment may support multiple image themes in relation to theme styles. For example, the electronic device (101) may determine at least one image theme having a style recommended (or optimized / suitable) for facial features among image themes through image analysis (e.g., facial features), and may provide the determined image themes through a UI screen (410).

[0128] An electronic device (101) according to one embodiment may analyze the AI ​​content creation history of users among a plurality of image themes and preferentially select an image theme with high preference.

[0129] The electronic device (101) detects an input (421_5) for selecting a first image theme (421) among the image themes displayed on the UI screen (410). <403> As shown in , a UI screen (410) on which a regenerated object (412) is displayed can be displayed. <403> In the UI screen (410), the regenerated object (412) may be displayed again, and a graphic object (430) (e.g., a border display) may be displayed to visually distinguish the selected first image theme (421) from other unselected image themes. <403> It may be a screen by the 350 operation of Fig. 3.

[0130] The electronic device (101) requests the generative AI to generate an object image corresponding to the first image theme (421) selected based on the displayed image (411) based on the input (412_5) that selects the regenerated object (412) being detected, <404> As shown in , a UI screen (440) can be displayed that displays text and visual information (440) guiding that an object image is being created. <404> It can be a screen by the 360 ​​motion of Fig. 3. <404> In the UI screen (410), the image (411) displayed on the display may be blurred, but this is only an example.

[0131] The electronic device (101) can generate at least one object image (e.g., a portrait image) in which a first image theme style is applied to a person included in the image based on generative AI.

[0132] The electronic device (101) is based on the generation of at least one object image. <405> As shown in , the generated object image can be displayed. The example screens in Fig. 4b are examples in which multiple object images are generated, but are not limited thereto. <405> The UI screen (410) may display a first object image (450) as a representative among multiple object images generated, an indicator (451) indicating that there are other object images, and a storage object (e.g., DONE object) (455) for storing the object image.

[0133] <405> may be a screen by the operation 370 of Fig. 3. The number of indicators (451) may be changed according to the number of object images generated. The indicator (451) that guides the position of the image currently displayed on the display may be graphically processed to be visually distinguished from other indicator shapes (e.g., a black colored indicator). For example, when a region where an object image is displayed is touched and dragged or swiped, <405> The UI screen (410) can be switched to the second image, the third image… the Nth image.

[0134] The electronic device (101) stores the displayed first object image (450) based on the detection of an input (455_5) selecting a storage item (455), <406> As illustrated, an image editing UI screen (460) of a first object image (450) may be displayed on the display. The image editing UI screen (460) may display an object image to be edited (e.g., the first object image (450)) and may display various functional items related to the editing function. For example, the functional items may include a size adjustment item (461) for adjusting the size of an image, a filter effect item (462) for supporting the application of a filter effect (e.g., auto, warm, calm, bright, winter, pink rose, ivory, soft, kiss me, black and white, B&W, vignetting) to an image, a brightness adjustment item (463) for adjusting the brightness of an image, a text function item (464) for supporting text input, rotation items (465) for supporting changing the rotation axis of an image, and an image regeneration object (466), but these are merely examples and are not limited thereto. Although not shown in the drawing, the image editing UI screen (460) may further include a drawing item that supports drawing input to an image and a sticker item that supports inserting stickers into an image.

[0135] According to some embodiments, the electronic device (101) <405> Add an edit menu item to one area of ​​the UI screen and based on user input selecting the edit menu item. <406> It can also be implemented to allow entry into the editing UI screen.

[0136] FIGS. 5A and 5B illustrate user interface screens that support image regeneration of an electronic device according to one embodiment.

[0137] Referring to FIGS. 5A and 5B , an electronic device (101) according to one embodiment may generate a personalized prompt (e.g., feature prompt (215_a) of FIG. 2) related to an object image based on facial / background features of an image including at least one person, and may support a prompt editing function by providing keywords (hereinafter, prompt keywords) or prompt editing function items corresponding to the prompt to a user interface (UI). The electronic device (101) may support at least partial regeneration of a theme image by transmitting the prompt keywords edited by the user to a generative AI.

[0138] The prompt editing function items (530) illustrated in FIGS. 5a and 5b may also be provided in the UI screen (410) illustrated in FIGS. 4a and 4b. For example, the UI screen (510) illustrated in FIGS. 5a and 5b <403> and <405> It can be provided between the UI screens (410). The prompt editing function items (530) can be provided through the UI screen displayed at a time when prompt editing is possible before or after theme image creation, but are not limited thereto.

[0139] An electronic device (101) according to one embodiment generates an object image (e.g., a portrait image) corresponding to a first image theme (521). <501> The UI screen (510) shown in can be displayed on the display.

[0140] <501> The UI screen (510) shown in may be a screen in which prompt editing items (530) are placed between object images (511) and image themes (520), and a regeneration object (525) for image regeneration (e.g., the regeneration object (412) of FIG. 4a) is displayed.

[0141] According to one embodiment, the electronic device (101) may configure keyword items (5311, 5321) corresponding to personalized prompts (e.g., feature prompt (215_a) of FIG. 2) generated based on facial / background features extracted through image analysis. The keyword items (5311, 5321) may vary depending on the image analysis results.

[0142] For example, keyword items (5311, 5321) may be displayed by dividing them into a positive category (5310) involved in the addition function of a feature and a negative category (5320) involved in the removal function of a feature. Keyword items (5311) included in the positive category (5310) are prompt keywords that add or maintain features to an object image (e.g., a portrait image (511)), and an addition (+) item (5312) may support a user to add a prompt keyword to add a feature. Keyword items (5321) included in the negative category (5320) are prompt keywords that remove features from an image, and an addition (+) item (5322) may support a user to add a prompt keyword to remove a feature. Keyword items (5311, 5321) may have their display positions changed or moved to other categories by a movement input (e.g., swipe, drag) after selecting a keyword item. For example, if a keyword item included in a negative category (5320) is moved to a positive category (5310) or a keyword item included in a positive category (5310) is moved to a negative category (5320), the moved keyword item may be applied as a prompt for a function added to the changed category.

[0143] The user can add or remove features from the displayed object image by manipulating the prompt editing items (530).

[0144] For example, if a user wants to remove a darkened skin tone from an object image (511) displayed on a UI screen (510), the user can select the dark skin tone item included in the negative category (5320). The electronic device (101) <502> As shown in , an input (545) selecting a dark skin tone item can be detected.

[0145] The electronic device (101) detects an input (545) selecting a dark skin tone item. <503> As shown in , a UI screen (510) may be displayed with a delete indicator (5325) that allows the dark skin tone item to be deleted.

[0146] If the user wants to remove any other features other than the displayed keyword items (5321), <504> As shown, the user can select an additional (+) item (5322) included in the negative category (5320).

[0147] The electronic device (101) detects an input to select an additional (+) item (5322). <505> As illustrated, a keyboard UI (560) may be displayed on the display to generate additional prompts. The electronic device (101) may register a prompt entered through the keyboard UI (560) as a new keyword item in the negative category (5320).

[0148] The electronic device (101) can regenerate an object image by inputting a prompt for keyword items (5311) included in a positive category (5310) involved in an additional feature function and keyword items (5321) included in a negative category (5320) involved in a feature removal function based on an input for selecting a regenerated object (525) after editing keyword items (5311, 5321).

[0149] An electronic device (101) according to one embodiment may support a function of first reflecting keyword items selected by a user input based on a first image selected from an image list, and then generating an object image to which a selected image theme is applied based on a generated second image (e.g., a preview image). For example, when a first image selected through an image list of a gallery app is displayed, the electronic device (101) may display keyword items involved in a prompt based on a category as illustrated in FIG. 5A based on a result of analyzing the first image. The electronic device (101) may generate a prompt to generate an object image including keyword items edited by the user, and may regenerate a second image (e.g., a preview image) for the first image using a generative AI with the generated prompt as input. The electronic device (101) may display at least one image theme selected based on the result of analyzing the second image on the display. When a user selects one of the image themes while a second image (e.g., a preview image) is displayed and requests image reproduction, the electronic device (101) can generate an object image (e.g., a portrait image) reflecting the selected image theme style based on the second image.

[0150] In an embodiment, an electronic device (101) may support a function of generating an object image (or profile image, portrait image) that matches the nature of a chat room by additionally reflecting information obtainable from the application (e.g., chat room information such as topic, title, conversation history, and relationship with chat room participants) in the case of an application (e.g., SNS app) that supports multiple multi-profiles that can be used depending on the situation.

[0151] FIGS. 6 to 8 are drawings for explaining automatic prompt generation and image preprocessing for generating optimal results of an object image according to one embodiment.

[0152] Referring to FIGS. 6 to 8, an electronic device (101) according to one embodiment may support a function of automatically generating a prompt for generating an object image based on at least one of an input image (610), a generation style (640), and an application (650) in use, and / or an image preprocessing function. For example, the electronic device (101) may transmit an image (e.g., an image including at least one person, a face area, and / or an image with a face area cropped) as an input image through the prompt manager (210) illustrated in FIG. 2, and may obtain a prompt (e.g., a feature prompt, a theme prompt) generated through image analysis as output data.

[0153] The input image (610) can be used to generate (or automatically generate) a personalized prompt (e.g., feature prompt (215_a) of FIG. 2) or to determine an image theme through image analysis or face / background analysis. The input image (610) can be analyzed into features of a main object (e.g., a person) (620) and features of a background (630). The main object (620) can be divided into facial feature points (621), object brightness (622), and hairstyle (623), but is not limited thereto. The facial feature points (621) can be analyzed for elements such as the presence or absence of double eyelids, skin color, skin freckles, the presence or absence of moles, lip color / shape, eyebrow color / shape, and facial expression, but this is only described as an example. In some embodiments, elements for distinguishing between men and women and estimating age through facial recognition included in the image can also be used to generate prompts.

[0154] For example, if a double eyelid exists on the face, the electronic device (101) may provide an editing option to maintain the double eyelid by adding a keyword item corresponding to the prompt “no double eyelid” to a negative category (e.g., negative category (5320) of FIG. 5A). Conversely, if the prompt keyword “double eyelid” is added to the negative category, this may be understood as an editing option to remove the characteristic of the double eyelid. As another example, if a face has freckles, the electronic device may provide an editing option to remove the characteristic of the freckles by adding “red spots” to the negative category.

[0155] Face brightness (622) can be analyzed based on the luminance characteristics of an image or / and object (e.g., a person or face region). For example, if the subject's face resolution is high but the face is dark, a prompt to brighten the entire image may be generated in the positive category, or a prompt to darken the lighting may be generated in the negative category.

[0156] Hair style (623) is analyzed based on factors such as hair features, for example, long hair, short hair, media hair, perm, and straight, and prompts related to hair features can be generated.

[0157] Background (630) features can be analyzed by dividing them into background brightness (631) and background complexity (632). If the complexity of the background excluding the person in the image is high, a prompt may be generated to remove the background and process only the subject.

[0158] The generation style (640) may be used to analyze facial features included in an image to determine an image theme suitable (or optimized, recommended) for the facial features, and to generate a prompt related to the determined image theme (e.g., theme prompt (215_b) of FIG. 2) or output a prompt specified in the image theme style (e.g., template prompt). In some embodiments, the prompt related to the image theme may be stored in the electronic device (101) in a pre-specified form.

[0159] In one embodiment, an image theme (e.g., illustration, 3D character, vintage, water color, cartoon, etc.) may be composed of multiple image themes. The prompts for creating object images may be different for each image theme. For example, an object image of a cartoon theme may require a prompt to change an input image into a cartoon-style face, and an object image of a water color theme may require a prompt to change an input face image into a water color-style face.

[0160] According to one embodiment, the electronic device (101) can determine or recommend an optimal style image theme according to facial features based on various analysis factors such as subject, color, background complexity, etc. through image analysis.

[0161] Figure 7 shows screens showing object images generated in response to image themes recommended based on the images.

[0162] <701> As shown in the first image (710), when the image color is bright and there is not much change in facial expression, the watercolor style is selected (or recommended) as the image theme, and a prompt to create a first object image (715) corresponding to the watercolor style can be created or specified. <702> As shown in the second image (720), when a person laughing loudly is included, a caricature style is selected, and a prompt to create a second object image (725) corresponding to the caricature style can be created or specified. <703> In case of image noise (noise) as shown in the third image (730), a prompt is provided to create a third object image (735) corresponding to the vintage style, or <704> When a highly saturated color such as red exists on the face, as in the fourth image (740) shown in , a prompt may be created or specified to create a fourth object image (745) corresponding to the illustration style.

[0163] The application in use (650) may be used to call an image regeneration service or perform preprocessing on an object image according to the characteristics of the application in use, or, when data / information on a person recognized from an image is collected through the application, may be used to generate a prompt based on the data / information on the person.

[0164] According to one embodiment, the electronic device (101) can generate an object image through the embodiments of FIGS. 3 to 5b, and reprocess / regenerate the generated object image according to application characteristics / electronic device status.

[0165] FIG. 8 is an example screen in which margins are created in the upper, lower, left, and right directions within the image according to the characteristics of the screen ratio displayed on the electronic device (101) in order to display the created image (e.g., a portrait image). As an example, when registering an object image (e.g., a portrait image) as a profile card of a contact application, text related to profile information (e.g., a name or contact information of the face) must be displayed at the top, so the object image can be reprocessed so that the face and text do not overlap.

[0166] For example, (a) of FIG. 8 is an image (810) illustrating a margin generated for displaying a profile card in a bar type electronic device. (b) of FIG. 8 is an image (811) illustrating a margin generated for displaying a profile card in a flip type electronic device (101). (c) of FIG. 8 is an image (812) illustrating a margin generated for displaying a profile card in a portrait mode of a tablet electronic device. (d) of FIG. 8 is an image (813) illustrating a margin generated for displaying a profile card in a landscape mode of a bar type electronic device. (e) of FIG. 8 is an image (814) illustrating a margin generated for displaying a profile card in a landscape mode of a fold type electronic device. Figure 8 (f) is an image (815) illustrating a margin generated to display a profile card in landscape mode of a tablet electronic device. The electronic device (101) can be reprocessed to display an object image generated by taking the above-described margin into consideration.

[0167] According to one embodiment, the electronic device (101) may support a function of reprocessing an object image generated on the entire screen to have a background that matches the object image when the object image is called in the wallpaper function.

[0168] According to one embodiment, when an electronic device (101) calls a sticker or emoticon creation object image, it may support a function of reprocessing the object image at a 1:1 ratio, or, when a background is created, a function of removing the background and filling in a background color, or a function of creating a background effect.

[0169] FIGS. 9A and 9B illustrate interface screens that support image reproduction of an electronic device according to one embodiment.

[0170] Referring to FIGS. 9A and 9B , an electronic device (101) according to one embodiment can call an image regeneration function or enter a function for creating and editing an object image through various applications. In the examples of FIGS. 9A and 9B , the function for creating and editing an object image is entered through a contact application, but this is merely an example, and embodiments of the present disclosure can be applied to other applications as well.

[0171] <901> As illustrated, the electronic device (101) may display the other party's contact setting UI (use interface) screen (910) on the display. The contact setting UI screen (910) may include a profile item (911) and a work information item (920). The contact setting UI screen (910) includes setting items related to name for name setting, phonetic name for voice call setting, nickname for nickname setting, phone for phone number setting, email for email address setting, groups for group setting, address for address setting, important dates for important date setting, relationships, notes, and website, but this is only an example and is not limited thereto.

[0172] When an input is detected to select a job information item (920), the electronic device (101) <902> As shown in , the substructure of the work info item (920) (e.g., job title item (921), department item (922), company item (923)) can be displayed. The user can store the other party's job information, department information, and company information through the job title item (921), department item (922), and company item (923), and can also store information related to the other party through other setting items.

[0173] The electronic device (101) can enable the user to enter an image editing function or an object image creation / editing function based on the other party's image (913) selected through the profile item (911). For example, the electronic device (101) can call and display an image list based on the selection of the profile item (911), and select the other party's image (913) from the image list. The electronic device (101) can induce the user to call the image regeneration function by providing an image editing function item or a regeneration object (e.g., a regeneration object (413) of FIG. 4A) to at least a portion of the selected image (e.g., the other party's image (913)).

[0174] When the user selects an image editing function item or a regenerated object, the electronic device (101) calls the portrait image creation / editing function. <903> The UI screen (930) shown in can be displayed on the display. For example, the UI screen (930) can include a counterpart image (913), a prompt keyword (931) / additional (+) item (932) of a positive category, a prompt keyword (941) / additional (+) item (942) of a negative category, and image themes (920). <903> The UI screen (930) shown in Fig. 4a is only an example. <402> The UI configuration shown in or FIG. 5a <501> It may be displayed as a UI configuration as shown in .

[0175] The electronic device (101) selects a first image theme (921) through a UI screen (930), and generates an object image (923) with the first theme style applied based on the counterpart image based on an AI generation request. <904> As shown in , the UI screen in which the counterpart image is converted into an object image can be displayed. The electronic device (101) <904> The object image (923) shown in can be saved / set as the other party's profile image.

[0176] FIG. 10 illustrates user interface screens that support image regeneration of an electronic device according to one embodiment.

[0177] Referring to FIG. 10, an electronic device (101) according to one embodiment may provide a regenerated object that induces object image creation and editing on various user interface (UI) screens for object image application. The UI screens may vary depending on the electronic device settings.

[0178] for example, <1001> The profile editing UI screen (1010) illustrated in may display a regeneration object (1015) that induces the execution of an image regeneration service on at least a portion of a profile image (1011). The user may select the regeneration object (1015) to set the profile image (1011) as an object image (e.g., a portrait image). For another example, <1002> The profile editing UI screen (1020) illustrated in can display an image editing object (1025) that executes an image editing function at the bottom of a profile image (1021). A user can enter the image regeneration function / service through the image editing object (1025) and change the profile image (1021) to a portrait image.

[0179] An electronic device according to one embodiment is (101). <1003> The call reception UI screen (1030) shown in <1004> A regeneration object (1035, 1045) that induces entry into an image regeneration service can be provided on the call outgoing UI screen (1040) illustrated in . The user can change the background image when receiving a call to a portrait image through the regeneration object (1035) displayed on the call incoming UI screen (1030), or change the background image when receiving a call to a portrait image through the regeneration object (1045) displayed on the call outgoing UI screen (1040).

[0180] FIG. 11 illustrates user interface screens that support image regeneration of an electronic device according to one embodiment.

[0181] Referring to FIG. 11, an electronic device (101) according to one embodiment may provide visual representations of a plurality of image theme items (e.g., image theme items (420, 520) of FIGS. 4A, 4B, 5A, and 5B) related to an object image in various forms. For example, <1101> The UI screen (1110) shown in is an example in which a portrait theme item (1115) is displayed in thumbnail format at the bottom of a portrait image (1111). <1102> The UI screen (1120) illustrated in is an example in which a portrait theme item (1125) is displayed in text format at the bottom of a portrait image (1121). Although not illustrated in the drawing, the UI screens (1110, 1120) illustrated in FIG. 11 may further include regenerative objects (e.g., regenerative objects (412, 525) of FIGS. 4a, 4b, 5a, and 5b) and prompt edit items (e.g., prompt edit items (530) of FIGS. 5a and 5b) described in the above-described embodiments.

[0182] FIGS. 12A through 12C illustrate user interface screens that support image regeneration of an electronic device according to one embodiment.

[0183] Referring to FIGS. 12A and 12B, an electronic device (101) according to one embodiment can set an object image based on image reproduction in a profile image of a contact application.

[0184] <1201> As illustrated, the electronic device (101) can display a contact setting UI screen (1210) of a specific person on the display. Based on an input of selecting an “Add Profile Card” object (1211) on the contact setting UI screen of a specific person, the electronic device (101) <1202> As illustrated, a gallery item (1212) may be displayed for selecting an image to be used as a profile card. A user may select the gallery item (1212) to call up an image list for selecting an image. The image list may prioritize displaying images classified by a specific name (e.g., tag information or metadata classification) in the gallery based on the contact name.

[0185] When a user selects any one image (1220) containing a specific person from the list of images, the electronic device (101) <1203> As shown in , the image (1220) selected for setting the profile card can be displayed. <1203> The UI screen (1210) shown in may include a selected image (1220), a service object (1222) for calling an image regeneration service, a function object (1223) for applying a filter effect, and a function object (1224) related to a preview. The filter effect is a filter effect to be applied to the image (1220), and may include, for example, at least one of blur, black and white, black and white, black and white background, color, ink, pastel, and oil painting effects. The service object (1222) may be an execution object that enters an object image (e.g., a portrait image) regeneration service for the image (1220) displayed on the UI screen (1210). When a user selects the service object (1222), the electronic device (101) <1204> The UI screen (1210) shown in can be displayed.

[0186] <1204> The UI screen (1210) illustrated in may include a plurality of image themes (e.g., portrait image themes) (1230) recommended (or selected) based on the person characteristics included in the selected image (1220), and a regeneration object (1231) requesting image regeneration execution. For example, the plurality of image themes (1230) (or theme items) may include at least one of a comic style, a 3D character style, a watercolor style, and a sketch style. Each image theme (1230) may include a representative thumbnail or / and text indicating in which style the theme is generated.

[0187] The user <1204> When a watercolor-style image theme is selected in the UI screen (1210) shown in , and then a regenerated object (1231) is selected, the electronic device (101) can generate at least one object image (e.g., a portrait image) reflecting the watercolor style based on the face area included in the selected image. The electronic device (101) can generate at least one object image (e.g., a portrait image) reflecting the watercolor style based on the object image generation. <1205> As illustrated, guide text and visual information (1235) that guide the generation of an object image may be displayed. The guide text and visual information (1235) may also be displayed through an animation effect. The guide text may be text such as, for example, 'Refining the details of the image... ', 'Reborn as a work of art... ', 'Adding style and feel... ', 'Identifying facial features... ', but these are only examples. According to one embodiment, the guide text may further include theme style information selected by the user. For example, the guide text may be expressed as, 'Adding comic style and feel... ', 'Reborn as a 3D character work of art... '.

[0188] The electronic device (101) is based on the completion of the creation of a watercolor-style object image. <1206> As illustrated, a first object image (1240) among at least one object image (e.g., a portrait image) generated in a watercolor style can be displayed. <1206> The UI screen (1210) illustrated in may include a first object image (1240), an indicator (1250) indicating that there are other object images than the first object image (1240), and a completion item (1255) for adding the image displayed on the UI screen to a profile card. The indicator (150) may further include an indicator indicating that there is a screen for regenerating the object image, and the indicator indicating that there is a screen for regenerating the object image may be expressed in a form that is distinct from the indicator indicating that there are other object images.

[0189] When the user performs a swipe gesture input in a specified direction while the first object image (1240) is displayed, the electronic device (101) <1207> As shown in , a second object image (1241) created in a different watercolor style can be displayed. If the user continues to perform a swipe gesture input in a specified direction, the UI screen <1208> As shown in , the third object image (1242) is displayed or <1209> As shown in , the screen can be changed to display the fourth object image (1243).

[0190] If the user continues to swipe in a specified direction, the electronic device (110) may display an object (1244) for regenerating an object image, as illustrated in <1219_1>. If the user selects an object (1244) for regenerating an object image, the electronic device (101) may regenerate an object image based on the selected image (1220).

[0191] FIGS. 13A and 13B illustrate user interface screens that support image regeneration of an electronic device according to one embodiment.

[0192] Referring to FIGS. 13a and 13b, an electronic device (101) according to one embodiment can generate an object image by reflecting information about an application running in a profile image, and set the generated object image as a profile image.

[0193] For example, the electronic device (101) runs a health / wellness application (hereinafter, app). <1301> A UI screen (1310) related to the user can be displayed based on an input for selecting a user setting item (1311) shown in . <1301> The UI screen (1310) shown in may include a profile image item (1312) and information (1313) related to the user's exercise activity / record. When the user selects an editing item (1314) for editing the profile image, the electronic device (101) <1302> As shown in , a UI screen (1310) for profile settings can be displayed. <1302> When the user selects a gallery item (1315) to add a profile image in the UI screen (1310) shown in , the electronic device (101) may run the gallery app to provide an image list. When the user selects an image (1320) to be added as a profile image from the image list, the electronic device (101) <1303> As shown in , the selected image (1320) can be displayed on the display. The electronic device (101) can display a UI screen (1310) including text (1321) for specifying a face area within the image in at least a part of the selected image (1320) and a service object (1322) for calling an image regeneration service. When the user selects the service object (1322), the electronic device (101) <1304> As illustrated, a plurality of recommended image themes (1330) may be displayed based on facial characteristics recognized in an image (1320). The plurality of image themes (1330) may include at least one theme from among a comic style, a 3D character style, a watercolor style, and a sketch style, but are not limited thereto. A facial area designated or recognized by a user through a touch gesture in the image may be displayed with an area frame (1323).When a user selects a regeneration object (1331) that requests image regeneration after selecting one image theme (e.g., 3D character and sketch style), the electronic device (101) can generate at least one object image (e.g., portrait image) to which the style of the selected image theme is applied. The electronic device (101) can generate the object image (e.g., portrait image) by further including (or reflecting) information about the running app, for example, information (1313) related to the user's exercise activity / record (e.g., bicycle exercise record), in the prompt.

[0194] The electronic device (101) is based on the object image being generated. <1305> As illustrated, a first object image (1340) among at least one object image (e.g., a portrait image) may be displayed. For example, the first object image (1340) may be an object image created in a 3D character and sketch style of a person in the selected image (1320) riding a bicycle. <1305> The UI screen shown in may include a first object image (1340), an indicator (1350) indicating that there are object images other than the first object image (1340), and a completion item (1355) for adding the image displayed on the UI screen to a profile card.

[0195] When the user selects the completion item (1355), the electronic device (101) sets the first object image (1340) as the profile image, <1306> You can return to the UI screen (1310) shown in . <1306> The UI screen (1310) shown in may be a screen changed to a first object image (1340) in which a user profile is created.

[0196] A method for supporting image regeneration of an electronic device according to one embodiment may include displaying an image including at least one person on the display. The method according to one embodiment may include displaying a regenerated object that calls an image regeneration function on at least a portion of the image based on an object recognized in the displayed image. The method according to one embodiment may include displaying, based on a first input selecting the regenerated object, a plurality of image themes determined based on object features recognized from the image on at least a portion of the display on which the image is displayed. The method according to one embodiment may include generating, based on a second input selecting a first image theme from among the image themes, a plurality of object images corresponding to the style of the first image theme using generative artificial intelligence (AI). The method according to one embodiment may include displaying a first object image from among the plurality of generated object images. It should be understood that the embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but rather to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B," "at least one of A and B," "at least one of A or B," "A, B, or C," "at least one of A, B, and C," and "at least one of A, B, or C" may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof.Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0197] The term "module" used in the embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0198] One embodiment of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0199] According to one embodiment, the method according to one embodiment disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0200] According to one embodiment, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to one embodiment, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to one embodiment, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In electronic devices, display; A processor comprising processing circuitry; A memory that stores instructions executable by the processor, The above instructions, when executed by the processor, cause the electronic device to: Displaying an image containing at least one object on the display, Displaying a regenerated object that calls an image regeneration function on at least a portion of the image based on the object being recognized in the image displayed above, Based on a first input selecting the above regenerated object, displaying a plurality of image themes determined based on object features recognized from the image on at least a portion of the display on which the image is displayed, Based on a second input that selects a first image theme among the above image themes, a plurality of object images corresponding to the first image theme style are generated using generative AI (artificial intelligence), An electronic device that displays a first object image among the plurality of object images generated above.

2. In paragraph 1, The above commands are operations for the electronic device to display the first object image, An electronic device further displaying at least one indicator indicating that there is another object image below the first object image and a graphic object visually distinguishing the first image theme selected by the second input from other image themes.

3. In paragraph 1, The above commands cause the electronic device to: An electronic device that changes a first object image displayed on the display to a second object image based on a motion input that drags the first object image displayed on the display.

4. In paragraph 1, The above commands are actions that cause the electronic device to display the regenerated object, An electronic device that displays an area frame designating an object area included in an image based on an object recognized from an image displayed on the display.

5. In paragraph 1, The above commands cause the electronic device to: An electronic device that displays guide information indicating that object images are being generated from the generating AI while generating a plurality of object images corresponding to the first image theme.

6. In paragraph 1, The above commands are operations for the electronic device to display the first object image, Analyze objects and backgrounds from the image and generate personalized prompts corresponding to object and background features based on the image, Displaying prompt editing function items based on the generated prompt on at least a portion of the display, An electronic device wherein the above prompt editing function items include at least one of a keyword item, an addition item, or a deletion item corresponding to the prompt.

7. In paragraph 6, The above commands cause the electronic device to: An electronic device that regenerates the first object image using the edited prompt as input data based on the input requesting prompt editing detected through the above prompt editing function items.

8. In paragraph 6, The above commands cause the electronic device to display the prompt editing function items on at least a portion of the display, An electronic device that displays the above keyword items by dividing them into a negative category that is involved in the function of removing features within an image and a positive category that is involved in the function of adding or maintaining features within an image.

9. In paragraph 6, The above commands are actions that cause the electronic device to generate the personalized prompt, An electronic device that, when a second image containing a specific person is selected through an application that supports an image setting function, further generates the personalized prompt based on data related to the specific person obtained from the application.

10. In paragraph 8, An electronic device that includes at least one of a contacts application, a screen settings application, a profile settings application, or a call application, wherein the application supports the above image settings.

11. In paragraph 8, The above commands cause the electronic device to: An electronic device that, when executing an application, calls the object image through the executed application, and changes the size or background image of the called object image according to the characteristics of the executed application based on at least one of the screen ratio, screen composition, and background characteristics of the executed application.

12. In a method for supporting image reproduction of an electronic device, An action of displaying an image containing at least one person; An action of displaying a regeneration object that calls an image regeneration function on at least a portion of the image based on a face being recognized in the image displayed above; An operation of displaying a plurality of image themes determined based on human features recognized from the image on at least a portion of a display on which the image is displayed, based on a first input selecting the regenerated object; An operation of generating a plurality of object images corresponding to the first image theme style using generative AI (artificial intelligence) based on a second input that selects a first image theme among the above image themes; and A method including an action of displaying a first object image among the plurality of object images generated above.

13. In paragraph 12, The action of displaying the first object image is: A method characterized in that it further displays at least one indicator indicating that there is another object image below the first object image and a graphic object that visually distinguishes the first image theme selected by the second input from other image themes.

14. In paragraph 12, A method further comprising, after the operation of displaying the first object image, an operation of changing the first object image displayed on the display to a second object image based on a motion input of dragging the first object image displayed on the display.

15. A non-transitory computer-readable medium storing instructions that, when executed by a processor of an electronic device, cause the processor to perform operations, The above instructions, when executed by the processor, cause the electronic device to: The act of displaying an image containing at least one object; An action of displaying a regenerated object that calls an image regeneration function on at least a portion of the image based on the object being recognized in the image displayed above; An operation of displaying a plurality of image themes determined based on object features recognized from the image on at least a portion of a display on which the image is displayed, based on a first input selecting the regenerated object; An operation of generating a plurality of object images corresponding to the first image theme style using generative AI (artificial intelligence) based on a second input that selects a first image theme among the above image themes; and A recording medium that performs an operation of displaying a first object image among the plurality of object images generated above.

Images