Method for generating image on basis of plurality of images, and electronic device therefor

Abstract

In an embodiment of the present disclosure, an electronic device may comprise: a memory; and at least one processor electrically connected to the memory, wherein the memory stores instructions. The instructions, when executed by the at least one processor, may cause the electronic device to: acquire a plurality of images, wherein each of the plurality of images includes metadata including information about an element of interest; generate at least one prompt for image generation by using an artificial intelligence model on the basis of the plurality of images and elements of interest of the plurality of images; and generate at least one image by using a generative artificial intelligence model on the basis of the at least one generated prompt.

Description

Method for generating an image based on multiple images and electronic device therefor

[0001] Embodiments disclosed in this document relate to a method for generating an image based on a plurality of images and an electronic device therefor.

[0002] Generative AI (GAI) is a type of artificial intelligence (AI) system that can generate text, images, and other media in response to prompts. Generative AI learns the patterns and structures of input training data and then generates new data with similar characteristics. Image-generating AI, in particular, uses algorithms such as image classification and object recognition to generate images of various works of art.

[0003] Meanwhile, when synthesizing an image or creating a new image based on multiple images, it is possible to use images of the same subject taken by multiple devices and information about object information, depth, composition, and shooting location included in the image metadata.

[0004] 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 is applicable as prior art in connection with the present disclosure.

[0005] An electronic device according to one embodiment disclosed in the present document includes a memory and at least one processor electrically connected to the memory, wherein the memory can store instructions. The instructions, when executed by the at least one processor, can cause the electronic device to acquire a plurality of images, each of the plurality of images including metadata including information about an element of interest, generate at least one prompt for image generation using an artificial intelligence model based on the plurality of images and the elements of interest of the plurality of images, and generate at least one image using a generative artificial intelligence model based on the generated at least one prompt.

[0006] A method using an electronic device according to an embodiment disclosed in the present document may include an operation of acquiring a plurality of images, each of the plurality of images including metadata including information about an element of interest, an operation of generating at least one prompt for image generation using an artificial intelligence model based on the element of interest of the plurality of images, and an operation of generating at least one image using a generative artificial intelligence model based on the generated at least one prompt.

[0007] A computer-readable storage medium storing instructions according to one embodiment disclosed in the present document, wherein the instructions, when executed by at least one processor, cause the at least one processor to obtain a plurality of images, each of the plurality of images including metadata including information about an element of interest, generate at least one prompt for image generation using an artificial intelligence model based on the plurality of images and the element of interest of each of the plurality of images, and generate at least one image using a generative artificial intelligence model based on the generated at least one prompt.

[0008] FIG. 1 is a block diagram of a system for generating an AI image using multiple images according to one embodiment of the present disclosure.

[0009] FIG. 2 is a block diagram showing the configuration of an electronic device according to one embodiment of the present disclosure.

[0010] FIG. 3 is a block diagram of a module of an electronic device according to one embodiment of the present disclosure.

[0011] FIG. 4 is a schematic flowchart of an operation of an electronic device acquiring an AI-generated image according to one embodiment of the present disclosure.

[0012] FIG. 5 is a flowchart of an operation in which an electronic device generates an AI image and transmits it to an external electronic device according to one embodiment of the present disclosure.

[0013] FIG. 6A is an exemplary diagram of an electronic device according to one embodiment of the present disclosure receiving an image from an external electronic device.

[0014] FIG. 6b is an example of a user interface (UI) of a process in which an electronic device generates an AI image using a received image, according to one embodiment of the present disclosure.

[0015] FIG. 6c is an example diagram of a generated AI image according to one embodiment of the present disclosure.

[0016] FIGS. 7A and 7B are exemplary diagrams of an electronic device generating multiple AI images according to one embodiment of the present disclosure.

[0017] FIGS. 8A and 8B are exemplary diagrams of an electronic device generating multiple AI images according to one embodiment of the present disclosure.

[0018] FIGS. 9A and 9B are exemplary diagrams of an electronic device generating an AI image according to one embodiment of the present disclosure.

[0019] FIG. 10 is an example diagram of an electronic device generating an AI image according to one embodiment of the present disclosure.

[0020] FIGS. 11a, 11b, and 11c are examples of AI image generation in cases where no priority is specified, according to one embodiment of the present disclosure.

[0021] FIG. 12 is a block diagram of an electronic device within a network environment according to various embodiments.

[0022] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0023] Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that various modifications, equivalents, and / or alternatives of the embodiments of the present invention are included.

[0024] FIG. 1 is a block diagram of a system for generating an AI image using multiple images according to one embodiment of the present disclosure.

[0025] Referring to FIG. 1, in one embodiment of the present disclosure, a system for generating an AI image using a plurality of images may include at least one of an electronic device (10), at least one external electronic device (e.g., a first external electronic device (20a), a second external electronic device (20b)), a server (30), or a network (199). For example, the network (199) may include at least one of a 3rd Generation Partnership Project (3GPP) network, a Long Term Evolution (LTE) network, a 5G network, a World Interoperability for Microwave Access (WIMAX) network, the Internet, a Local Area Network (LAN), a Wireless Local Area Network (WLAN), a Wide Area Network (WAN), a Personal Area Network (PAN), a Wi-Fi network, a Bluetooth network, a satellite broadcasting network, an analog broadcasting network, or a Digital Multimedia Broadcasting (DMB) network, but is not limited thereto.

[0026] The system of FIG. 1 may include at least one external electronic device (e.g., a first external electronic device (20a) and / or a second external electronic device (20b)) that transmits at least one image to the electronic device (10). The at least one external electronic device (e.g., the first external electronic device (20a) and / or the second external electronic device (20b)) may communicate with a server (30) and / or the electronic device (10) via a network (199) or via a direct connection. For example, the electronic device (10) and / or at least one external electronic device (e.g., the first external electronic device (20a) and / or the second external electronic device (20b)) may include any electronic device such as a smart phone, a laptop, a desktop, a TV, a smart pad, a tablet PC, a wearable device (e.g., a head-mounted device such as a smart glasses or a head-mounted device (HMD), an electronic garment, an electronic bracelet, an electronic necklace, an electronic appcessory, an electronic tattoo, a smart mirror, or a smart watch), a connected car, a video see through (VST) device, an extended reality (XR) device, or a mobile terminal.

[0027] Hereinafter, a person skilled in the art will understand that the description related to the first external electronic device (20a) can be similarly applied to the second external electronic device (20b). The number of at least one external electronic device (e.g., the first external electronic device (20a) and / or the second external electronic device (20b)) illustrated in FIG. 1 is merely an example, and embodiments of the present disclosure are not limited thereto.

[0028] In one embodiment of the present disclosure, the electronic device (10) can receive an image from a first external electronic device (20a). In one example, the electronic device (10) can receive the image through the first external electronic device (20a) and a network (199). The electronic device (10) can receive the image stored in the first external electronic device (20a) from a server (30). For example, the server (30) can include a server supporting a social network service (SNS) and / or a web server.

[0029] In one example, the first external electronic device (20a) can transmit an image to the server (30). The electronic device (10) can receive the image transmitted by the first external electronic device (20a) from the server (30). The electronic device (10) can transmit an AI image generated using the received image to the first external electronic device (20a). In other words, the electronic device (10) and the first external electronic device (20a) can transmit and receive images (e.g., images stored in the first external electronic device (20a), AI images generated by the electronic device (10)) via the server (30). For example, the electronic device (10) and the first external electronic device (20a) can transmit and receive images using an SNS chat room.

[0030] In one embodiment of the present disclosure, the first external electronic device (20a) may transmit an image including information. For example, the information may include any metadata related to the image. For example, the metadata may include information about at least one of a date (e.g., the date the image was captured), a time (e.g., the time the image was captured), or a location (e.g., the location where the image was captured). For example, the metadata may include information about shooting conditions (e.g., the shooting device, the shooting resolution, the shooting location, the shooting composition, and / or the shooting point of view). For example, the metadata may include information about a user's elements of interest and / or a priority of the elements of interest. For example, elements of interest may include certain areas and / or elements (e.g., objects (e.g., people or buildings), weather, nature, landscape, background) on an image designated by the user.

[0031] In one embodiment of the present disclosure, the electronic device (10) may generate a prompt for image generation. For example, the prompt may include at least one piece of image information and / or text information. In one example, the electronic device (10) may generate the prompt based on the user's interest and / or the priority of the interest. For example, if the user's interest is a specific person in an image, the electronic device (10) may generate a prompt for generating an image including the specific person. For example, if priorities are specified among multiple interest factors in at least one image, the electronic device (10) may generate a prompt for generating an image considering the priorities. For example, if multiple people are specified as interest factors and priorities are determined among the multiple people, the electronic device (10) may generate a prompt to place the person with the highest priority at the center of the generated image.

[0032] In one embodiment of the present disclosure, the electronic device (10) may generate multiple prompts using multiple images. For example, the electronic device (10) may generate multiple prompts corresponding to each of the multiple images based on the elements of interest and / or priorities of the elements of interest of each of the multiple images. For example, the electronic device (10) may generate personalized prompts based on the elements of interest and / or priorities of the elements of interest of each of the multiple users.

[0033] In one embodiment of the present disclosure, if the user does not specify an element of interest and / or a priority of the elements of interest, the electronic device (10) may determine an element of interest and / or a priority of the elements of interest from at least one image using an artificial intelligence model. The electronic device (10) may generate a prompt based on the determined element of interest and / or a priority of the elements of interest.

[0034] In one embodiment of the present disclosure, an electronic device (10) may generate an image. In one example, the electronic device (10) may generate an image using a generative artificial intelligence model. For example, the electronic device (10) may generate an image using a diffusion model and / or a Generative Adversarial Network (GAN). In the present disclosure, an AI image may correspond to a term referring to an image generated (e.g., acquired) by the electronic device (10) using an image-generating artificial intelligence model.

[0035] In one embodiment of the present disclosure, the electronic device (10) may generate at least one image using a generative artificial intelligence model from at least one generated prompt. In one example, the electronic device (10) may generate multiple prompts from multiple images, and then generate multiple images using the multiple prompts. For example, the electronic device (10) may generate personalized images for each of the multiple users using personalized prompts for each of the multiple users.

[0036] In one embodiment of the present disclosure, the electronic device (10) may transmit an image generated using a generative artificial intelligence model to at least one external electronic device (e.g., a first external electronic device (20a), a second external electronic device (20b)) and / or a server (30). In one example, the electronic device (10) may transmit the generated image to the photographing device (e.g., the first external electronic device (20a)) based on information (e.g., identification information) of the photographing device included in information (e.g., metadata) of the generated image. For example, the electronic device (10) may identify the photographing device using the information of the photographing device. The electronic device (10) may communicate with the identified photographing device via a network (199) to transmit the generated image. For example, the electronic device (10) may transmit at least one personalized image to at least one external electronic device corresponding to each of the users.

[0037] The configuration of the system for generating an image using AI described above with reference to FIG. 1 is an example, and embodiments of the present disclosure are not limited thereto. For example, the electronic device (10) may generate an AI image by obtaining an image from a separate external server other than at least one external electronic device (e.g., the first external electronic device (20a), the second external electronic device (20b)). The external server may include a server having an arbitrary database capable of obtaining image information corresponding to a specific image, including the server (30). For example, the network (199) may include a plurality of networks. The network between the electronic device (10) and the server (30) and the network between the at least one external electronic device (e.g., the first external electronic device (20a), the second external electronic device (20b)) and the server (30) may be networks based on different protocols.

[0038] FIG. 2 is a block diagram showing the configuration of an electronic device according to one embodiment of the present disclosure.

[0039] Referring to FIGS. 1 and 2, the electronic device (10) may include at least one processor (e.g., processor (220)), memory (230), display (260), or communication circuit (290).

[0040] In one embodiment of the present disclosure, at least one processor (e.g., processor (220)) may be connected to memory (230), display (260), and communication circuit (290). For example, at least one processor may be electrically connected to components of the electronic device (10). For example, at least one processor may be connected to components of the electronic device (10) by wire or wirelessly. At least one processor may be composed of a single chip or multiple chips. For example, at least one processor may include at least one processing circuitry such as a central processing unit (CPU), an application processor (AP), a microprocessor unit (MPU), a communication processor (CP), a system on chip (SoC), or an integrated circuit (IC).

[0041] In one embodiment of the present disclosure, at least one processor may perform operations necessary for the operation of the electronic device (10). In one example, the operations of the electronic device (10) may be performed by at least one processor executing instructions. Some of the operations of the electronic device (10) may be performed by a first processor executing instructions, and at least some of the remaining operations may be performed by a processor different from the first processor executing instructions. At least one processor may control components of the electronic device (10). For example, the operations of the electronic device (10) described in the present disclosure may be referenced as being performed by at least one processor. For example, the operations of the electronic device (10) may be performed by at least one processor executing instructions stored in the memory (230). At least one processor may be referenced by the processor (1220) of FIG. 12.

[0042] In one embodiment of the present disclosure, the memory (230) may include built-in memory or external memory. For example, the built-in memory may include at least one of a volatile memory (e.g., dynamic random access memory (DRAM), static random access memory (SRAM), or synchronous DRAM (SDRAM)), a nonvolatile memory (e.g., programmable read-only memory (PROM), one time PROM (OTPROM), erasable PROM (EPROM), electrically erasable and PROM (EEPROM), mask ROM, flash ROM, flash memory, a hard drive, or a solid state drive (SSD). The external memory may include at least one of a flash drive (e.g., compact flash), secure digital (SD), micro-SD, mini-SD, extreme digital (xD), multi-media card (MMC), or a memory stick. The memory (230) may be referenced by the memory (1230) of FIG. 12.

[0043] In one embodiment of the present disclosure, the memory (230) may store instructions that can be executed by at least one processor (e.g., processor (271)). The memory (230) may store at least one data related to the operation of the electronic device (10) or a command related to the functional operation of components of the electronic device (10). For example, the memory (230) may store at least one application that is preloaded upon manufacturing the electronic device (10) or downloaded as a third party from an online market (e.g., app store). For example, the at least one application may include a voice recognition application that supports the operation of a voice recognition service.

[0044] In one embodiment of the present disclosure, the display (260) can output various screens. For example, the processor (220) can output various screens (e.g., a main interface screen, a home screen, a system settings screen, or an application execution screen) using the display (260). For example, the processor (220) can provide AI images through the display (260).

[0045] In one embodiment of the present disclosure, the display (260) may be implemented as a touchscreen display including a display panel, a cover glass, and a touch panel (or a touch sensor). The display panel may receive a driving signal corresponding to image information at a specified frame rate and output a related screen based on the driving signal. The cover glass may be positioned above the display panel to transmit light according to the screen output of the display panel. The display (260) may be referenced by the display module (1060) of FIG. 12.

[0046] In one embodiment of the present disclosure, the communication circuit (290) can support communication between the electronic device (10) and at least one external device (e.g., the first external electronic device (20ab), the second external electronic device (20b)) and / or an external server (e.g., the server (30)). For example, the communication circuit (290) can transmit and receive signals or data with the at least one external electronic device by connecting to an external network (e.g., the network (199) of FIG. 1). For example, the communication circuit (290) can establish a network according to a prescribed protocol with the at least one external device and connect to the network based on wired or wireless communication, thereby transmitting and receiving signals or data with the at least one external device. The communication circuit (290) can be referenced by the communication module (1090) of FIG. 12.

[0047] The communication circuit (290) may include at least one circuit for processing a signal. For example, the communication circuit (290) may include at least one converter for frequency modulation of a signal, at least one filter for noise removal of a signal, at least one modem for modulating and / or demodulating a signal, at least one antenna, and / or at least one transceiver. The communication circuit (290) may be controlled based on a signal (e.g., a control signal) from the processor (220), for example.

[0048] In one embodiment of the present disclosure, the electronic device (10) may acquire a plurality of images when at least one instruction stored in the memory (230) is executed by at least one processor. For example, each of the plurality of images may include metadata. For example, the metadata may include information about an element of interest of the user. In one example, the electronic device (10) may receive at least one image from at least one external electronic device (e.g., a first external electronic device (20a), a second external electronic device (20b)) and / or a server (30). The electronic device (10) may also identify at least one image stored in the memory (230). For example, the plurality of images may include at least one received image and / or at least one identified image.

[0049] In one embodiment of the present disclosure, the electronic device (10) may generate at least one prompt for image generation based on a plurality of images and metadata of each of the plurality of images when at least one instruction stored in the memory (230) is executed by at least one processor. For example, the prompt may include image information of the plurality of images and / or information (e.g., text information) about an element of interest. In one example, the electronic device (10) may use an artificial intelligence model to generate a prompt including information about an element of interest of each of the plurality of images. For example, when the element of interest is a specific person, the electronic device (10) may generate a prompt including object information about the specific person. The electronic device (10) may use the plurality of images to generate personalized prompts for each of the plurality of users.

[0050] In one embodiment of the present disclosure, when at least one instruction stored in the memory (230) is executed by at least one processor, the electronic device (10) can obtain at least one AI image based on at least one prompt. In one example, the electronic device (10) can generate an AI image from the prompt using a generative artificial intelligence model. The electronic device (10) can generate at least one personalized image for a plurality of users by generating at least one prompt.

[0051] In one embodiment of the present disclosure, when at least one instruction stored in the memory (230) is executed by at least one processor, the electronic device (10) may receive an image by performing short-range communication with at least one external electronic device (e.g., a first external electronic device (20a), a second external electronic device (20b)). In one example, the electronic device (10) may request the establishment of a channel for short-range communication with at least one external electronic device. When the channel for short-range communication is established, the electronic device (10) may transmit a UI (user interface) signal for designating an element of interest to the at least one external electronic device. For example, when the electronic device (10) receives an image from an external user and generates an AI image, the electronic device (10) may transmit a UI signal for designating an element of interest in order to acquire an element of interest of the external user. In this case, the external user may specify the location, priority, and / or background weather of an element of interest or object to be included in the AI ​​image.

[0052] In one embodiment of the present disclosure, the electronic device (10) can identify an element of interest in an image based on a user input (e.g., touch input, voice input) when at least one instruction stored in the memory (230) is executed by at least one processor. In one example, the user of the electronic device (10) can designate an element of interest for at least one image. For example, if an image received from at least one external electronic device does not include information (e.g., metadata) about an element of interest, the user of the electronic device (10) can directly designate an element of interest in the received image. The user can also designate an element of interest in an image stored in the memory (230) to generate an image using AI.

[0053] In one embodiment of the present disclosure, the electronic device (10) may transmit an AI image generated to at least one external electronic device based on metadata when at least one instruction stored in the memory (230) is executed by at least one processor. In one example, the electronic device (10) may transmit the generated AI image to the external electronic device using identification information of the external electronic device included in the metadata. For example, when the external electronic device (20a) transmits an image to the electronic device (10) for generating an AI image, the electronic device (10) may transmit the generated AI image to the external electronic device (20a) upon generating the AI ​​image. In this case, the electronic device (10) may identify the external electronic device (20a) using identification information of the external electronic device (20a) included in the received image. The electronic device (10) may transmit the generated AI image by identifying the external electronic device (20a).

[0054] In one example, when the electronic device (10) receives images from multiple external electronic devices (e.g., external electronic device (20a) and / or external electronic device (20b)), it can generate personalized AI images for each external electronic device. The electronic device (10) can transmit the generated AI images to the external electronic devices corresponding to the personalized AI images.

[0055] In one embodiment of the present disclosure, the electronic device (10) may identify priorities among elements of interest in each of a plurality of images based on user input when at least one instruction stored in the memory (230) is executed by at least one processor. In one example, the user of the electronic device (10) may designate priorities among elements of interest in each of the plurality of images. In this case, the electronic device (10) may identify priorities among elements of interest based on the user input and reflect the priorities in prompt generation. For example, the user may designate priorities among people designated as elements of interest in the plurality of images. In this case, the electronic device (10) may generate a prompt that generates an AI image such that a person with a high priority is positioned at the center of the image. Priorities may also be designated by each user of at least one external electronic device. For example, at least one image received by the electronic device (10) from at least one external electronic device may include information (e.g., metadata) including priorities among elements of interest.

[0056] In one embodiment of the present disclosure, the electronic device (10) may determine an element of interest and / or a priority of at least one image when at least one instruction stored in the memory (230) is executed by at least one processor. For example, if information (e.g., metadata) of at least one image does not include information on the element of interest and / or information on the priority, the electronic device (10) may determine an element of interest and / or a priority of the element of interest from at least one image using an artificial intelligence model. For example, if a first image including a person and a landmark and a second image including clear weather are acquired, the electronic device (10) may determine the person and landmark of the first image and the clear weather of the second image as elements of interest. In this case, the electronic device (10) may generate an AI image including the person and landmark of the first image in the clear weather of the second image.

[0057] Each of the components of the electronic device (10) described above may include a single or multiple entities, and some of the multiple entities may be separately arranged in other components. In one embodiment, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added.

[0058] FIG. 3 is a block diagram of a module of an electronic device according to one embodiment of the present disclosure.

[0059] In one embodiment of the present disclosure, referring to FIG. 3, the electronic device (10) may include at least one of a communication module (320), an image management module (330), an image analysis module (340), a prompt generation module (350), or an image generation module (360).

[0060] In one embodiment of the present disclosure, the communication module (320) may include an image receiving module (321) and / or an image transmitting module (323). In one example, the image receiving module (321) may receive an image from at least one external electronic device (e.g., the external electronic device (20a) and the second external electronic device (20b) of FIG. 1). For example, the image receiving module (321) may receive an image including information (e.g., metadata) from at least one external electronic device. For example, the metadata may include at least one of information (e.g., identification information) of the at least one external electronic device that transmitted the image, information about elements of interest considered when generating an AI image, or information about priorities. For example, the image receiving module (321) may store identification information of each device in order to generate an AI image and transmit it to at least one external electronic device. The image transmitting module (323) may transmit the generated AI image to at least one external electronic device using the stored identification information of each device.

[0061] In one embodiment of the present disclosure, the image management module (330) may include a feature control module (331) and / or a priority control module (333). In one example, the feature control module (331) may extract elements of interest utilized in generating an AI image from at least one image. For example, the elements of interest may be set by each user of an external electronic device transmitting the image (e.g., a first external electronic device (20a), a second external electronic device (20b)), or may be directly set by a user of an electronic device generating an AI image (e.g., an electronic device (10)).

[0062] The feature control module (331) can identify elements of interest from an image using an artificial intelligence model. For example, elements of interest may include people, buildings, landscapes, and / or nature. The image management module (330) can analyze features and elements within each image. For example, the image management module (330) can identify information about objects, regions, outline information, background, time, weather, lighting, and / or location of the image.

[0063] In one example, the priority control module (333) can control the priorities of elements of interest when generating an AI image. For example, when generating an AI image, the priority control module (333) can cause the AI ​​image to be generated according to priorities individually designated by multiple external users. For example, when generating an AI image by receiving multiple images from multiple external electronic devices, the priority control module (333) can identify information regarding priorities contained in the metadata of each of the multiple images. For example, in order to generate an AI image, each of a plurality of external users may set different priorities for objects (e.g., people, buildings), backgrounds, and / or compositions (e.g., point of view) included in each image when transmitting images to the electronic device (10). The priority control module (333) may generate a plurality of AI images using information about each identified priority. In one example, if no priority is specified, the priority control module (333) may determine priorities from a plurality of images using an artificial intelligence model. For example, if no priority is specified, the priority control module (333) may determine priorities from a person object and other object information, background information, composition information, time information, and weather information of a first image, and a person object and other object information, background information, and / or resolution information of a second image using an artificial intelligence model.

[0064] In one embodiment of the present disclosure, the image analysis module (340) may include a depth analysis module (341), a region analysis module (343), a viewpoint analysis module (345), and / or a feature point analysis module (347). In one example, the depth analysis module (341) may calculate the depth of an image to obtain information about the depth. The electronic device (10) may generate an AI image using the depth value calculated by the depth analysis module (341). For example, the depth analysis module (341) may obtain a depth value for an element of interest of each image. The region analysis module (343) may identify each region of the image to obtain information about the region. For example, the region analysis module (343) may obtain region information about each object and / or background of the image through object outline recognition (e.g., object segmentation). For example, the electronic device (10) can identify an area where feature points match between multiple photos using area information. The viewpoint analysis module (345) can identify information about the point of view of the image. For example, the electronic device (10) can determine the viewpoint of the generated AI image using the viewpoint information of the image identified by the viewpoint analysis module (345). The feature point analysis module (347) can analyze feature points of the image to obtain information about the feature points. For example, the feature point analysis module (347) can obtain information about feature points of an element of interest extracted by the feature control module (331). The electronic device (10) can generate an AI image using the information about the feature points.

[0065] In one embodiment of the present disclosure, the prompt generation module (350) may generate a prompt for AI image generation. In one example, the prompt generation module (350) may generate a prompt by inputting information on elements of interest extracted by the feature control module (331), information on priorities identified by the priority control module (333), and / or information on depth, area, viewpoint, and feature points of each image analyzed by the image analysis module (340). The generated prompt may include image information and / or text information. For example, the image information may include information on each image utilized in AI image generation. For example, the image information may include information representing images received from an external electronic device and / or images stored in the electronic device. For example, the text information may include information on elements of interest and / or information on priorities. For example, the text information may include information on viewpoints.

[0066] In one embodiment of the present disclosure, the image generation module (360) can generate an AI image using the generated prompt. For example, the image generation module (360) can generate an AI image by inputting the generated prompt into a generative artificial intelligence model. The image generation module (360) can generate a partial image or an image using the prompt. The image generation module (360) can also generate an image using the generated partial image and the image utilized when generating the prompt.

[0067] Each component of the modules of the electronic device (10) described above may include a single or multiple entities, and some of the multiple entities may be separately arranged in other components. In one embodiment, at least one module or operation among the aforementioned modules may be omitted, or at least one other module or operation may be added.

[0068] FIG. 4 is a schematic flowchart of an operation of an electronic device acquiring an AI-generated image according to one embodiment of the present disclosure.

[0069] Referring to FIG. 4, in operation 410, an electronic device (e.g., the electronic device (10) of FIG. 1) according to an embodiment of the present disclosure may acquire multiple images. In one example, the electronic device (10) may acquire at least one image from at least one external electronic device (e.g., the first external electronic device (20a) and the second external electronic device (20b) of FIG. 1). The electronic device (10) may also acquire an image from a separate external server (e.g., the server (30) of FIG. 1). The electronic device (10) may also generate an AI image using an image stored in a memory (e.g., the memory (230) of FIG. 2).

[0070] In operation 420, an electronic device (10) according to one embodiment of the present disclosure may generate a prompt for AI image generation. In one example, the electronic device (10) may generate the prompt based on a plurality of acquired images. For example, the electronic device (10) may generate at least one prompt using information (e.g., metadata) included in the plurality of acquired images.

[0071] In operation 430, an electronic device (10) according to an embodiment of the present disclosure may generate an AI image. In one example, the electronic device (10) may generate the AI ​​image using a generative artificial intelligence model by using the generated prompt as input. For example, the electronic device (10) may generate the AI ​​image using a diffusion model and / or a Generative Adversarial Network (GAN).

[0072] FIG. 5 is a flowchart of an operation in which an electronic device generates an AI image and transmits it to an external electronic device according to one embodiment of the present disclosure.

[0073] Referring to FIGS. 3 and 5, in operation 510, an electronic device (e.g., electronic device (10) of FIG. 1) according to one embodiment of the present disclosure may receive an image from at least one external electronic device (e.g., first external electronic device (20a), second external electronic device (20b) of FIG. 1). In one example, the electronic device (10) may receive an image directly from the at least one external electronic device or from an external server (e.g., server (30) of FIG. 1).

[0074] In one embodiment of the present disclosure, the electronic device (10) may receive an image containing metadata. For example, the metadata may include at least one of information regarding the date, time, location, or shooting conditions (e.g., shooting device, shooting resolution, shooting location, shooting composition, and shooting point of view) of the photograph. For example, the metadata may include information regarding a user's elements of interest and / or priorities of the elements of interest. For example, elements of interest may include certain areas and / or elements (e.g., objects such as people or buildings, weather, nature, landscape, and / or background) on an image designated by the user.

[0075] In operation 520, the electronic device (10) according to one embodiment of the present disclosure may identify an element of interest or a priority between elements of interest from at least one received image. In one example, the electronic device (10) may identify information about the element of interest or priority of each image from the acquired image using the image management module (330) and / or the image analysis module (340). If the priority is not specified, the electronic device (10) may determine a priority from elements of at least one image using the priority control module (333). For example, the elements of the image may include a point of view (e.g., composition), a background, time, weather, lighting location, and / or an object (e.g., a person, a building) of the image.

[0076] In operation 530, an electronic device (10) according to an embodiment of the present disclosure may identify additional information for generating a prompt. In one example, the electronic device (10) may identify information regarding at least one of feature point matching, depth, area, or point of view (e.g., composition) from at least one acquired image. For example, the electronic device (10) may identify point of view information of each image and apply the identified point of view to the generated AI image. For example, the electronic device (10) may apply the depth information of each image to the placement of a person or building within the AI ​​image.

[0077] In operation 540, an electronic device (10) according to an embodiment of the present disclosure may generate a prompt and an AI image. In one example, the electronic device (10) may generate a prompt for generating an AI image. The electronic device (10) may generate at least one prompt for generating an image based on a plurality of images and information (e.g., metadata) of each of the images. For example, the prompt may include image information of the plurality of images and / or information (e.g., text information) about an element of interest. For example, the prompt may include information about the composition (e.g., point of view), depth, lighting, and / or resolution of the AI ​​image to be generated. For example, the prompt may include image information of the plurality of images.

[0078] In one example, the electronic device (10) may generate a prompt including information about an element of interest of each of a plurality of images using an artificial intelligence model. For example, if the element of interest is a specific person, the electronic device (10) may generate a prompt including object information about the specific person. The electronic device (10) may generate a personalized prompt for each of at least one external electronic device. For example, the electronic device (10) may generate at least one personalized prompt using information about an element of interest and / or priority included in each metadata based on each image received from at least one external electronic device.

[0079] In one example, the electronic device (10) may generate a prompt considering the capability (e.g., resolution) of the external electronic device that will receive the AI ​​image. For example, if the capability of the external electronic device that will receive the AI ​​image is an electronic device that can display up to FHD (Full High Definition), the electronic device (10) may generate a prompt for generating an AI image with a resolution of FHD. For example, when the electronic device (10) receives an image containing information on the interests and / or priorities of a first external user from a first external electronic device (20a) that can display in FHD, the interests and / or priorities of the first external user may be reflected and a first prompt for generating an AI image with a resolution of FHD may be generated.

[0080] In one example, the electronic device (10) may generate a prompt for AI image generation using a first image (e.g., corresponding to an image received from a first external electronic device (20a)), a second image (e.g., corresponding to an image received from a second external electronic device (20b)), and a third image (e.g., an image stored in the electronic device (10). For example, the first image, the second image, and the third image may correspond to images that were taken at the same location but differ in at least one of a person, a composition, a point of view, a time of taking the picture, or a background.

[0081] For example, the first external user can designate the person object and building object of the first image, the person object of the second image, the person object and background area of ​​the third image as elements of interest. In addition, the first external user can designate the following information as priority: “1) position the person object of the first image in a group shot with the person object of the second image and the person object of the third image side by side, centered on the person object of the first image, 2) make the person object of the second image and the person object of the third image look in the same direction (e.g., composition), 3) face the sunlight of a clear day together with the background of the third image, 4) position the building object of the first image behind the person object, and 5) compose the image so that the side of the tower is visible.” In this case, the first prompt for generating the first AI image of the first external user can include text information regarding 1) to 5) above and image information of the first image, the second image, and the third image. Additionally, the first prompt may further include text information indicating that the resolution of the first AI image is FHD.

[0082] In one example, the electronic device (10) may generate an AI image using a generative artificial intelligence model. For example, the electronic device (10) may generate an AI image using a diffusion model and / or Generative Adversarial Networks (GANs). The electronic device (10) may generate at least one AI image using the generative artificial intelligence model from at least one generated prompt. In one example, the electronic device (10) may generate a plurality of prompts from a plurality of images and then generate a plurality of AI images. For example, the electronic device (10) may generate personalized AI images using personalized prompts for each of a plurality of users.

[0083] In operation 550, the electronic device (10) according to one embodiment of the present disclosure may transmit at least one generated AI image to at least one external electronic device. In one example, when the electronic device (10) generates an AI image, it may transmit the generated AI image to the external electronic device that transmitted the image. For example, when the electronic device (10) receives an image containing information on the interests and / or priorities of a first external user from a first external electronic device (20a), the electronic device (10) may generate a first AI image reflecting the interests and / or priorities of the first external user and transmit the first AI image to the first external electronic device (20a). At this time, the electronic device (10) may utilize terminal information (e.g., identification information) of the first external electronic device (20a) included in the metadata of the image transmitted by the first external electronic device (20a).

[0084] FIG. 6A is an exemplary diagram of an electronic device according to one embodiment of the present disclosure receiving an image from an external electronic device.

[0085] Referring to FIG. 6A, in one embodiment of the present disclosure, the electronic device (10) may receive images from a first external electronic device (20a), a second external electronic device (20b), and a third external electronic device (20c). A first image of the first external electronic device (20a) (e.g., a first image (601) to be described later in FIG. 6B) may include a first person object (21a) and a first building object (22a). A second image of the second external electronic device (20b) (e.g., a second image (602) to be described later in FIG. 6B) may include a second person object (21b) and a second building object (22b). A third image of the third external electronic device (20c) (e.g., a third image (603) to be described later in FIG. 6B) may include a third person object (21c) and a third building object (22c). A fourth image stored in the electronic device (10) (e.g., a fourth image (600) described later in FIG. 6b) may include a fourth person object (11) and a fourth building object (12). The electronic device (10) may receive the first image, the second image, and the third image from a first external electronic device (20a), a second external electronic device (20b), and a third external electronic device (20c), respectively. The first building object (22a), the second building object (22b), the third building object (22c), and the fourth building object (12) may correspond to the same building. For example, the first image, the second image, the third image, and the fourth image may correspond to photos taken at different points of view, times, and / or locations of the same building, respectively.

[0086] In one example, the first image, the second image, and the third image may each include information (e.g., metadata). For example, the metadata may include a phone number, an email address, and / or identification information of a user of each external electronic device (the first external electronic device (20a), the second external electronic device (20b), and the third external electronic device (20c)). In addition, the metadata may include information about elements of interest and priorities. Individual elements of interest of each image (the first image, the second image, and the third image) may be specified by detecting an outline and information of the corresponding element of interest or directly setting an area in each external electronic device (the first external electronic device (20a), the second external electronic device (20b), and the third external electronic device (20c)). In addition, priorities may also be specified in each external electronic device (the first external electronic device (20a), the second external electronic device (20b), and the third external electronic device (20c)). Additionally, the elements of interest or priorities of each image may be set and specified in the electronic device (10) that generates the AI ​​image.

[0087] FIG. 6b is an example of a user interface (UI) of a process in which an electronic device generates an AI image using a received image, according to one embodiment of the present disclosure.

[0088] Referring to FIGS. 6A and 6B , the electronic device (10) may generate a prompt for image generation after acquiring a first image (601), a second image (602), a third image (603), and a fourth image (600). For example, the first image (601) may include a first person object (21a) and a first building object (22a), the second image (602) may include a second person object (21b) and a second building object (22b), the third image (603) may include a third person object (21c) and a third building object (22c), and the fourth image (600) may correspond to an image including a fourth person object (11) and a fourth building object (12), respectively.

[0089] In one example, the electronic device (10) may generate a prompt by reflecting information about the elements of interest and priorities of each of the first image (601), the second image (602), the third image (603), and the fourth image (600). During the process of generating the AI ​​image, the electronic device (10) may display the first image (601), the second image (602), the third image (603), the fourth image (600), and text information (610) titled “Generating AI Image.” The electronic device (10) may generate a plurality of AI images using the first image (601), the second image (602), the third image (603), and the fourth image (600). For example, each of the plurality of AI images may be a personalized AI image generated by setting the elements of interest and priority information included in each metadata for each received image.

[0090] FIG. 6c is an example diagram of a generated AI image according to one embodiment of the present disclosure.

[0091] Referring to FIGS. 6A to 6C, the electronic device (10) may generate an AI image based on a first image (601), a second image (602), a third image (603), and a fourth image (600). For example, the prompt for generating an AI image illustrated in FIG. 6C may include image information for elements of interest including a first person object (21a) of the first image (601), a second person object (21b) and a second building object (22b) of the second image (602), a third person object (21c) of the third image (603), and a fourth person object (11) of the fourth image (600). In addition, for example, the prompt for generating an AI image illustrated in FIG. 6C may include text information for positioning the first to fourth person objects side by side in a group photo in the same composition as the composition of the second image (602).

[0092] FIGS. 7A and 7B are exemplary diagrams of an electronic device generating multiple AI images according to one embodiment of the present disclosure.

[0093] Referring to FIGS. 6a, 6b, and 7a, in one embodiment of the present disclosure, the electronic device (10) may receive a first image (601) and a third image (603) from a first external electronic device (20a) and a third external electronic device (20c), respectively. The electronic device (10) may store a fifth image (700). For example, the fifth image (700) may be a fourth image with a weather element (13) added. For example, the fifth image may include a fourth person object (11), a fourth building object (12), and a weather element (13).

[0094] In one example, each user can transmit metadata containing information about their interests and / or priorities. Additionally, each external user can include textual information about their images in the metadata. For example, the textual information for an image may include textual information corresponding to the people, buildings, weather elements, composition, and / or background contained in the image.

[0095] In one example, each external user may include text information about another external user's images in the metadata. For example, the first external user of the first external electronic device (20a) may designate the first person object (21a) and the first building object (22a) as elements of interest. In addition, the first external user may include text information in the metadata of the first image (601) that includes the person objects of each image (e.g., the first person object (21a), the third person object (21c), and the fourth person object (11)) side by side as a group photo in the composition of the first image (601) and includes the weather element (13) of the fifth image.

[0096] Likewise, a third external user of a third external electronic device (20c) may designate a third person object (21c) and a third building object (22c) as elements of interest. In addition, the third external user may include text information in the metadata of the third image (603) that includes the person objects of each image (e.g., the first person object (21a), the third person object (21c), and the fourth person object (11)) side by side as a group photo in the composition of the third image (603) and includes the weather element (13) of the fifth image.

[0097] In one embodiment of the present disclosure, the electronic device (10) may generate multiple prompts based on received images. In one example, after receiving the first image (601) and the third image (603), the electronic device (10) may analyze each image and information (e.g., metadata) included in each image to generate a prompt tailored to the request of each user. For example, the first prompt tailored to the request of the first external user may include image information of each image (the first image (601), the third image (603), and the fifth image (700)), information about elements of interest designated by the first external user, and information about priorities. The information about elements of interest of the first external user may include information about a first person object (21a) and a building object (22a). Information about the priority of the first external user may include text information that includes each person object (e.g., the first person object (21a), the third person object (21c), the fourth person object (11)) and the weather element (13) in the composition of the first image (601). For example, a third prompt corresponding to a request of the third external user may include image information of each image (the first image (601), the third image (603), the fifth image (700)), information about the interest element designated by the third external user, and information about the priority. Information about the interest element of the third external user may include information about the third person object (21c) and the building object (22c). Information about the priority of the third external user may include text information that includes each person object (e.g., the first person object (21a), the third person object (21c), the fourth person object (11)) and the weather element (13) in the composition of the third image (603).

[0098] Referring to FIGS. 6A to 7B , in one embodiment of the present disclosure, the electronic device (10) may generate a plurality of AI images (e.g., a first AI image (701), a second AI image (703)). For example, the electronic device (10) may generate the AI ​​images by using the generated prompts (e.g., a first prompt, a third prompt) as inputs of a generative artificial intelligence model. In one example, the electronic device (10) may generate the first AI image (701) using the first prompt that takes into account the interests and priorities of the first external user. For example, the first AI image (701) may include a first person object (21a), a third person object (21c), a fourth person object (11), a first building object (22a), and a weather element (13) in the composition of the first image (601). The electronic device (10) may generate the third AI image (703) using the third prompt that takes into account the interests and priorities of the third external user. For example, the third AI image (703) may include a first person object (21a), a third person object (21c), a fourth person object (11), a third building object (22c), and a weather element (13) in the composition of the third image (603).

[0099] In one embodiment of the present disclosure, the electronic device (10) can transmit a plurality of generated AI images to external users, respectively. For example, the electronic device (10) can transmit a first AI image (701), generated in consideration of the interests and priorities of a first external user, to a first external electronic device (20a) of the first external user. For example, the electronic device (10) can transmit a third AI image (703), generated in consideration of the interests and priorities of a third external user, to a third external electronic device (20c) of the third external user.

[0100] FIGS. 8A and 8B are exemplary diagrams of an electronic device generating multiple AI images according to one embodiment of the present disclosure.

[0101] Referring to FIGS. 6A, 6B, and 8A, in one embodiment of the present disclosure, the electronic device (10) may receive a first image (601) and a third image (603) from a first external electronic device (20A) and a third external electronic device (20C), respectively. The electronic device (10) may store a fifth image (700). For example, the fifth image (700) may be a fourth image with a weather element (13) added. For example, the fifth image may include a fourth person object (11), a fourth building object (12), and a weather element (13). In one example, each user may transmit an image without specifying an element of interest and / or a priority. For example, the first external user may transmit the first image (601) without including information about the element of interest and / or a priority in the metadata. In such a case, the electronic device (10), which is a terminal that generates AI images, can designate elements of interest and / or priorities for each external user. For example, the electronic device (10) can identify information about elements of interest and / or priorities from a plurality of images (e.g., a first image (601), a third image (603), and a fifth image (700)) through user input.

[0102] For example, the electronic device (10) may identify a first person object (21a) and a first building object (22a) as elements of interest from the first image (601). In addition, the electronic device (10) may include information about the priority of the first external user in the first prompt. For example, the electronic device (10) may include text information that includes only the weather element (13) of the fifth image in the composition of the first image (601). Similarly, the electronic device (10) may identify a third person object (21c) and a third building object (22c) as elements of interest from the third image (603). In addition, the electronic device (10) may include information about the priority of the third external user in the third prompt. For example, the electronic device (10) may include text information that includes only the weather element (13) of the fifth image in the composition of the third image (603).

[0103] In one embodiment of the present disclosure, the electronic device (10) may generate a plurality of prompts (e.g., a first prompt, a third prompt) based on the received image and user input. In one example, after receiving the first image (601) and the third image (603), the electronic device (10) may analyze the elements of interest and priorities according to the user input to generate the plurality of prompts. For example, the first prompt corresponding to the request of the first external user may include image information of the first image (601) and the fifth image (700), information about the elements of interest designated for the first external user, and information about the priorities. The information about the elements of interest designated for the first external user may include information about the first person object (21a) and the building object (22a). The information about the priorities designated for the first external user may include text information that includes a weather element (13) in the composition of the first image (601). For example, a third prompt corresponding to a request from a third external user may include image information of the third image (603) and the fifth image (700), information about an element of interest designated for the third external user, and information about a priority. The information about an element of interest designated for the third external user may include information about a third person object (21c) and a building object (22c). The information about a priority designated for the first external user may include text information that includes a weather element (13) in the composition of the third image (603).

[0104] Referring to FIGS. 6a, 6b, 8a, and 8b, in one embodiment of the present disclosure, the electronic device (10) may generate a plurality of AI images (e.g., a first AI image (801), a second AI image (803)). For example, the electronic device (10) may generate the AI ​​images by using the generated prompts (e.g., the first prompt, the third prompt) as inputs of a generative artificial intelligence model. In one example, the electronic device (10) may generate the first AI image (801) using the first prompt, considering the interest elements and priorities specified for the first external user. For example, the first AI image (801) may include a first person object (21a), a first building object (22a), and a weather element (13) in the composition of the first image (601). The electronic device (10) may generate the third AI image (803) using the third prompt, considering the interest elements and priorities specified for the third external user. For example, the third AI image (803) may include a first person object (21c), a third building object (22c), and a weather element (13) in the composition of the third image (603).

[0105] In one embodiment of the present disclosure, the electronic device (10) can transmit a plurality of generated AI images to external users, respectively. For example, the electronic device (10) can transmit a first AI image (801) to a first external electronic device (20a) of a first external user. For example, the electronic device (10) can transmit a third AI image (803) to a third external electronic device (20c) of a third external user.

[0106] FIGS. 9A and 9B are exemplary diagrams of an electronic device generating an AI image according to one embodiment of the present disclosure.

[0107] Referring to FIGS. 6A, 6B, and 9A, in one embodiment of the present disclosure, the electronic device (10) can obtain a plurality of images (e.g., a first image (601), a second image (602), a third image (603)) from a plurality of external users (e.g., a first external user (901), a second external user (902), a third external user (903)) through a group chat room of a messenger or an application. Each of the plurality of external users can also transmit a request through the group chat room, together with or after transmitting the image. For example, the request can include text information associated with the designation of an element of interest. For example, referring to FIG. 9A, the third external user (903) can transmit a third image (603) and text information associated with the designation of an element of interest (e.g., “Make me stand out”) through the group chat room.

[0108] In one embodiment of the present disclosure, the electronic device (10) can download multiple images transmitted by multiple external users through a group chat room. The user of the electronic device (10) can directly designate an element of interest corresponding to the requests of the multiple external users. In one example, the user of the electronic device (10) can designate a third person object (21c) included in a third image (603) in response to the request of a third external user (903) that says, “Make me stand out.” For example, referring to FIGS. 9A and 9B , the electronic device (10) can indicate the designated element of interest using a first affordance (905). The electronic device (10) can generate an AI image using the first image (601), the second image (602), the third image (603) received from the multiple external users, and the fourth image (600) stored in the electronic device (10).

[0109] In one embodiment of the present disclosure, the electronic device (10) may generate a prompt for AI image generation using a user-specified element of interest and a plurality of images (e.g., a first image (601), a second image (602), a third image (603), and a fourth image (600)). For example, the prompt for AI image generation illustrated in FIG. 9b may include image information corresponding to a third person object (21c) and a third building object (22c) of the third image (603), a first person object (21a) of the first image (601), a second person object (21b) of the second image (602), and a fourth person object (11) of the fourth image (600). In addition, for example, the prompt for generating an AI image illustrated in FIG. 9B may include text information to position the first to fourth person objects side by side in a group photo in the same composition as the composition of the third image (603), include the third building object (22c) in the background, and position the third person object (21c) at the very front or center. In one embodiment of the present disclosure, the electronic device (10) may generate at least one candidate AI image using the generated prompt. In the process of generating the at least one candidate AI image, the electronic device (10) may output text information (610) titled “Generating AI Image.” In one example, the user of the electronic device (10) may select one AI image from among the at least one candidate AI image. For example, the user of the electronic device (10) may select the AI ​​image (900). In response to the user selection, the electronic device (10) may generate and store the AI ​​image (900). The electronic device (10) can transmit the generated AI image (900) to multiple external users through a group chat room.

[0110] FIG. 10 is an example diagram of an electronic device generating an AI image according to one embodiment of the present disclosure.

[0111] Referring to FIGS. 6a, 6b, 9a, 9b, and 10, the electronic device (10) may designate a plurality of person objects as elements of interest. In one example, the electronic device (10) may directly designate a plurality of person objects as elements of interest among the person objects (e.g., a first person object (21a), a second person object (21b), a third person object (21c), and a fourth person object (11)) included in the plurality of images (e.g., a first image (601), a second image (602), a third image (603), and a fourth image (600)). For example, a user of the electronic device (10) may directly designate the second person object (21b) and the third person object (21c) as elements of interest. For example, as illustrated in FIG. 10, the electronic device (10) can represent a designated element of interest using a first affordance (1005) and a second affordance (1010).

[0112] In one embodiment of the present disclosure, the electronic device (10) may generate a prompt using a designated element of interest and a plurality of images. For example, the prompt for AI image generation illustrated in FIG. 10 may include image information corresponding to a second person object (22b) and a second building object (22b), a first person object (21a), a third person object (21c), and a fourth person object (11). In addition, for example, the prompt for AI image generation illustrated in FIG. 10 may include text information for positioning the first to fourth person objects side by side in a group shot in the same composition as the second image (602), including the second building object (22b) in the background, and positioning the second person object (21b) and the third person object (21c) in front or in the center of other person objects (e.g., the first person object (21a), the fourth person object (11)). The electronic device (10) can generate an AI image (1000) from the generated prompt using an image-generating artificial intelligence model. The generated AI image (1000) can include a second person object (21b) and a third person object (21c) positioned in front of other person objects (e.g., a first person object (21a), a fourth person object (11)) and positioned relatively larger.

[0113] FIGS. 11A to 11C are examples of AI image generation in a case where no priority is specified, according to one embodiment of the present disclosure.

[0114] FIG. 11A illustrates a case where multiple objects are not all captured in the camera frame of one terminal (e.g., electronic device (10), first external electronic device (20a)). Referring to FIG. 11A, in one embodiment of the present disclosure, the electronic device (10) and the second external electronic device (20a) can capture multiple objects from different directions. In one example, the electronic device (10) can capture multiple objects existing in a first range (1110). The second external electronic device (20a) can capture multiple objects existing in a second range (1120). The first image (1100) of FIG. 11B may correspond to an image captured by the electronic device (10) of multiple objects in the first range (1110). The second image (1101) of FIG. 11B may correspond to an image captured by the electronic device (10) of multiple objects in the second range (1120). The second external electronic device (20a) can transmit a second image (1101) capturing a plurality of objects in the second range (1120) to the electronic device (10). The second external electronic device (20a) can transmit the second image (1101) without specifying an element of interest and / or priority.

[0115] FIG. 11B illustrates a user interface (UI) representing a process in which an electronic device (10) receives a second image (1101) from a first external electronic device (20a) and generates an AI image. Referring to FIGS. 11A and 11B , in one embodiment of the present disclosure, the electronic device (10) may generate an AI image using a plurality of images. The electronic device (10) may generate a prompt for generating the AI ​​image. During the process of generating the AI ​​image, the electronic device (10) may output the first image (1100), the second image (1101), and text information (610) titled “Generating AI Image.”

[0116] In one embodiment of the present disclosure, if a plurality of images do not include information on elements of interest and / or priorities, the electronic device (10) may determine elements of interest and / or priorities using an AI model. The electronic device (10) may assign the same or different priorities to each of the plurality of objects included in the first image (1100) and the second image (1101). For example, the electronic device may identify object information and image elements such as area, composition, resolution, etc. shown in each image, and the priorities among the identified elements may be determined by an AI analysis model. The electronic device (10) may generate a prompt based on the priorities of each determined object. For example, the electronic device (10) may assign the highest priority to an object included in both the first image (1100) and the second image (1101) and generate a prompt. For example, the object with the highest priority may be positioned at the center of the generated AI image.

[0117] FIG. 11C illustrates that the electronic device (10) generates an AI image (1102) using the first image (1100) and the second image (1101). Referring to FIGS. 11A to 11C , the electronic device (10) may generate the AI ​​image (1102) based on the generated prompt. The prompt may include information about the first image (100) and the second image (1101). In addition, the electronic device (10) may determine priorities for a plurality of objects using an artificial intelligence model. The prompt may include information about the determined priorities. For example, the prompt may include text information that instructs the user to position a plurality of objects centered around a beverage object (1199). The generated AI image (1102) may correspond to an image captured by a single terminal of a plurality of objects that are in a range that is difficult to capture with a single terminal (e.g., the electronic device (10), the first external electronic device (20a)). The generated AI image (1102) may include a first partial image (1180) including a plurality of objects in a first range (1110) and a second partial image (1190) including a plurality of objects in a second range (1120). The electronic device (10) may transmit the generated AI image (1102) to a first external electronic device (20a).

[0118] FIG. 12 is a block diagram of an electronic device within a network environment according to various embodiments.

[0119] FIG. 12 is a block diagram of an electronic device (1201) within a network environment (1200) according to various embodiments. Referring to FIG. 12 , in the network environment (1200), the electronic device (1201) may communicate with the electronic device (1202) via a first network (1298) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (1204) or the server (1208) via a second network (1299) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (1201) may communicate with the electronic device (1204) via the server (1208). According to one embodiment, the electronic device (1201) may include a processor (1220), a memory (1230), an input module (1250), an audio output module (1255), a display module (1260), an audio module (1270), a sensor module (1276), an interface (1277), a connection terminal (1278), a haptic module (1279), a camera module (1280), a power management module (1288), a battery (1289), a communication module (1290), a subscriber identification module (1296), or an antenna module (1297). In some embodiments, the electronic device (1201) may omit at least one of these components (e.g., the connection terminal (1278)), or may have one or more other components added. In some embodiments, some of these components (e.g., sensor module (1276), camera module (1280), or antenna module (1297)) may be integrated into a single component (e.g., display module (1260)).

[0120] The processor (1220) may control at least one other component (e.g., hardware or software component) of the electronic device (1201) connected to the processor (1220) by executing, for example, software (e.g., program (1240)), and may perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (1220) may store commands or data received from other components (e.g., sensor module (1276) or communication module (1290)) in volatile memory (1232), process the commands or data stored in volatile memory (1232), and store result data in non-volatile memory (1234). According to one embodiment, the processor (1220) may include a main processor (1221) (e.g., a central processing unit or an application processor) or an auxiliary processor (1223) (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 (1221). For example, when the electronic device (1201) includes the main processor (1221) and the auxiliary processor (1223), the auxiliary processor (1223) may be configured to use less power than the main processor (1221) or to be specialized for a given function. The auxiliary processor (1223) may be implemented separately from the main processor (1221) or as a part thereof.

[0121] The auxiliary processor (1223) may control at least a portion of functions or states associated with at least one component (e.g., a display module (1260), a sensor module (1276), or a communication module (1290)) of the electronic device (1201), for example, on behalf of the main processor (1221) while the main processor (1221) is in an inactive (e.g., sleep) state, or together with the main processor (1221) while the main processor (1221) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (1223) (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 (1280) or a communication module (1290)). In one embodiment, the auxiliary processor (1223) (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, on the electronic device (1201) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (1208)). 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.

[0122] The memory (1230) can store various data used by at least one component (e.g., the processor (1220) or the sensor module (1276)) of the electronic device (1201). The data can include, for example, software (e.g., the program (1240)) and input data or output data for commands related thereto. The memory (1230) can include a volatile memory (1232) or a non-volatile memory (1234).

[0123] The program (1240) may be stored as software in memory (1230) and may include, for example, an operating system (1242), middleware (1244), or an application (1246).

[0124] The input module (1250) can receive commands or data to be used in a component of the electronic device (1201) (e.g., a processor (1220)) from an external source (e.g., a user) of the electronic device (1201). The input module (1250) 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).

[0125] The audio output module (1255) can output audio signals to the outside of the electronic device (1201). The audio output module (1255) 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.

[0126] The display module (1260) can visually provide information to an external party (e.g., a user) of the electronic device (1201). The display module (1260) 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 (1260) 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.

[0127] The audio module (1270) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (1270) can acquire sound through the input module (1250), output sound through the sound output module (1255), or an external electronic device (e.g., electronic device (1202)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (1201).

[0128] The sensor module (1276) can detect the operating status (e.g., power or temperature) of the electronic device (1201) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (1276) can 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.

[0129] The interface (1277) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (1201) with an external electronic device (e.g., the electronic device (1202)). In one embodiment, the interface (1277) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0130] The connection terminal (1278) may include a connector through which the electronic device (1201) may be physically connected to an external electronic device (e.g., the electronic device (1202)). In one embodiment, the connection terminal (1278) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0131] The haptic module (1279) 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 (1279) may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0132] The camera module (1280) can capture still images and videos. According to one embodiment, the camera module (1280) may include one or more lenses, image sensors, image signal processors, or flashes.

[0133] The power management module (1288) can manage the power supplied to the electronic device (1201). According to one embodiment, the power management module (1288) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0134] A battery (1289) may power at least one component of the electronic device (1201). In one embodiment, the battery (1289) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0135] The communication module (1290) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (1201) and an external electronic device (e.g., electronic device (1202), electronic device (1204), or server (1208)), and the performance of communication through the established communication channel. The communication module (1290) may operate independently from the processor (1220) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (1290) may include a wireless communication module (1292) (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 (1294) (e.g., a local area network (LAN) communication module, or a power line communication module). Any of these communication modules may communicate with an external electronic device (1204) via a first network (1298) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (1299) (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 may 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 (1292) may use subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (1296) to verify or authenticate the electronic device (1201) within a communication network such as the first network (1298) or the second network (1299).

[0136] The wireless communication module (1292) 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 (1292) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (1292) can support various technologies for securing performance in high-frequency bands, 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 (1292) can support various requirements specified in the electronic device (1201), an external electronic device (e.g., the electronic device (1204)), or a network system (e.g., the second network (1299)). According to one embodiment, the wireless communication module (1292) may 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.

[0137] The antenna module (1297) 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 (1297) 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 (1297) 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 (1298) or the second network (1299), may be selected from the plurality of antennas by, for example, the communication module (1290). A signal or power may be transmitted or received between the communication module (1290) and an external electronic device via the at least one selected 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 (1297).

[0138] According to various embodiments, the antenna module (1297) 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.

[0139] 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)).

[0140] According to one embodiment, commands or data may be transmitted or received between the electronic device (1201) and an external electronic device (1204) via a server (1208) connected to a second network (1299). Each of the external electronic devices (1202 or 1204) may be the same or a different type of device as the electronic device (1201). According to one embodiment, all or part of the operations executed in the electronic device (1201) may be executed in one or more of the external electronic devices (1202, 1204, or 1208). For example, when the electronic device (1201) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (1201) 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 (1201). The electronic device (1201) 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 (1201) may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (1204) may include an Internet of Things (IoT) device. The server (1208) may be an intelligent server utilizing machine learning and / or a neural network.According to one embodiment, an external electronic device (1204) or server (1208) may be included within the second network (1299). The electronic device (1201) may be applied to intelligent services (e.g., smart homes, smart cities, smart cars, or healthcare) based on 5G communication technology and IoT-related technology.

[0141] An electronic device according to one embodiment of the present disclosure includes a memory and at least one processor electrically connected to the memory, wherein the memory is capable of storing instructions.

[0142] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to acquire a plurality of images.

[0143] Each of the plurality of images according to one embodiment of the present disclosure may include metadata including information about an element of interest.

[0144] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to generate at least one prompt for image generation using an artificial intelligence model based on the plurality of images and elements of interest of each of the plurality of images.

[0145] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to generate at least one image using a generative artificial intelligence model based on the at least one generated prompt.

[0146] An electronic device according to one embodiment of the present disclosure, wherein the at least one prompt includes image information for the plurality of images and text information for elements of interest in the plurality of images.

[0147] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to receive at least one external image from at least one external electronic device.

[0148] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to identify an element of interest associated with a user image stored in the memory based on a user input of a user of the electronic device.

[0149] The plurality of images according to one embodiment of the present disclosure may include at least one external image and the user image.

[0150] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to request establishment of a channel for short-range communication with the at least one external electronic device through the communication circuit.

[0151] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to transmit a signal to the at least one external electronic device to display a user interface (UI) for designating an element of interest based on the establishment of the channel.

[0152] According to one embodiment of the present disclosure, the metadata of the at least one external image may include identification information of the at least one external electronic device that transmitted the at least one image.

[0153] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to transmit the at least one generated image to the at least one external electronic device using the identification information.

[0154] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may obtain a user input associated with an element of interest of the plurality of images from a user of the electronic device, and identify the element of interest of the plurality of images based on the obtained user input.

[0155] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to identify priorities among elements of interest of the plurality of images based on the user input.

[0156] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to generate the at least one prompt further including information about the identified priority.

[0157] The instructions according to one embodiment of the present disclosure, when executed by the at least one processor, may cause the electronic device to obtain at least one external image including metadata that does not include information about an element of interest, and to identify the element of interest in the at least one external image using an artificial intelligence model.

[0158] A method using an electronic device according to one embodiment of the present disclosure includes an operation of acquiring a plurality of images, each of which may include metadata including information about an element of interest.

[0159] A method using an electronic device according to one embodiment of the present disclosure may include an operation of generating at least one prompt for image generation using an artificial intelligence model based on the plurality of images and elements of interest of each of the plurality of images.

[0160] A method using an electronic device according to one embodiment of the present disclosure may include an operation of generating at least one image using a generative artificial intelligence model based on at least one generated prompt.

[0161] In a method using an electronic device according to one embodiment of the present disclosure, the at least one prompt may include image information about the plurality of images and text information about elements of interest of the plurality of images.

[0162] A method using an electronic device according to one embodiment of the present disclosure may include an operation of receiving at least one external image from at least one external electronic device.

[0163] A method using an electronic device according to one embodiment of the present disclosure may include an operation of identifying an element of interest associated with a user image stored in the electronic device based on a user input of a user of the electronic device.

[0164] In a method using an electronic device according to one embodiment of the present disclosure, the plurality of images may include at least one external image and the user image.

[0165] A method using an electronic device according to one embodiment of the present disclosure may include an operation of requesting establishment of a channel for short-range communication with at least one external electronic device.

[0166] A method using an electronic device according to one embodiment of the present disclosure may include an operation of transmitting a signal to display a user interface (UI) for designating an element of interest on at least one external electronic device based on establishment of the channel.

[0167] A method using an electronic device according to one embodiment of the present disclosure may include metadata of the at least one external image including identification information of the at least one external electronic device that transmitted the at least one image.

[0168] A method using an electronic device according to one embodiment of the present disclosure may include an operation of transmitting at least one image generated using the identification information to at least one external electronic device.

[0169] A method using an electronic device according to one embodiment of the present disclosure may include an operation of obtaining a user input associated with an element of interest of the plurality of images from a user of the electronic device, and an operation of identifying an element of interest of the plurality of images based on the obtained user input.

[0170] A method using an electronic device according to one embodiment of the present disclosure may include an operation of identifying priorities among elements of interest of the plurality of images based on the user input.

[0171] A method using an electronic device according to one embodiment of the present disclosure may include generating at least one prompt further including information about the identified priority.

[0172] A method using an electronic device according to one embodiment of the present disclosure may further include an operation of acquiring at least one external image including metadata that does not include information about an element of interest, and an operation of identifying an element of interest in the at least one external image using an artificial intelligence model.

[0173] A computer-readable storage medium storing instructions according to one embodiment of the present disclosure, wherein the instructions, when executed by at least one processor, cause the at least one processor to obtain a plurality of images, each of the plurality of images including metadata including information about an element of interest.

[0174] A computer-readable storage medium storing instructions according to one embodiment of the present disclosure, wherein the instructions, when executed by at least one processor, enable the at least one processor to identify an element of interest in the plurality of images.

[0175] A computer-readable storage medium storing instructions according to one embodiment of the present disclosure, wherein the instructions, when executed by at least one processor, cause the at least one processor to generate at least one prompt for image generation using an artificial intelligence model based on the plurality of images and elements of interest of each of the plurality of images.

[0176] A computer-readable storage medium storing instructions according to one embodiment of the present disclosure, wherein the instructions, when executed by at least one processor, cause the at least one processor to generate at least one image using a generative artificial intelligence model based on the at least one generated prompt.

[0177] In a computer-readable storage medium storing instructions according to one embodiment of the present disclosure, the at least one prompt may include image information for the plurality of images and text information for elements of interest in the plurality of images.

[0178] A computer-readable storage medium storing instructions according to one embodiment of the present disclosure, wherein the instructions, when executed by at least one processor, cause the at least one processor to receive at least one external image from at least one external electronic device.

[0179] A computer-readable storage medium storing instructions according to one embodiment of the present disclosure, wherein the instructions, when executed by at least one processor, cause the at least one processor to identify an element of interest associated with a user image stored in the computer-readable storage medium based on a user input of the user.

[0180] In a computer-readable storage medium storing instructions according to one embodiment of the present disclosure, the plurality of images may include at least one external image and the user image.

[0181] In a computer-readable storage medium storing instructions according to one embodiment of the present disclosure, the instructions, when executed by at least one processor, may cause the at least one processor to request establishment of a channel for short-range communication with the at least one external electronic device.

[0182] In a computer-readable storage medium storing instructions according to one embodiment of the present disclosure, the instructions, when executed by at least one processor, may cause the at least one processor to transmit a signal to the at least one external electronic device to display a user interface (UI) for designating an element of interest based on the establishment of the channel.

[0183] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0184] The various 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 should be understood 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 the 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" can include any one of the items listed together in the corresponding phrase among those phrases, 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 component (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.

[0185] The term "module" used in various 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).

[0186] Various embodiments of the present document may be implemented as software (e.g., a program (1240)) including one or more instructions stored in a storage medium (e.g., an internal memory (1236) or an external memory (1238)) readable by a machine (e.g., an electronic device (1201)). For example, a processor (e.g., a processor (1220)) of the machine (e.g., an electronic device (1201)) 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.

[0187] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as included in a computer program product. The computer program product may be traded as a commodity between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0188] According to various embodiments, 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 various embodiments, 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 such a 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 various embodiments, 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, memory; and comprising at least one processor electrically connected to said memory; The above memory stores instructions, When the above instructions are executed by the at least one processor, the electronic device: Acquire a plurality of images, each of the plurality of images including metadata including information about an element of interest, Based on the plurality of images and the elements of interest of the plurality of images, generating at least one prompt for image generation using an artificial intelligence model, and An electronic device configured to generate at least one image using a generative artificial intelligence model based on at least one generated prompt.

2. In claim 1, An electronic device, wherein said at least one prompt includes image information for said plurality of images and text information about elements of interest in said plurality of images.

3. In claim 2, further comprising a communication circuit; When the above instructions are executed by the at least one processor, the electronic device: receiving at least one external image from at least one external electronic device; Based on user input of the user of the electronic device, identify elements of interest associated with user images stored in the memory; An electronic device, wherein said plurality of images include at least one external image and said user image.

4. In claim 3, When the above instructions are executed by the at least one processor, the electronic device: Requesting establishment of a channel for short-range communication to at least one external electronic device through the above communication circuit, An electronic device, based on the establishment of the above channel, for transmitting a signal to at least one external electronic device to display a user interface (UI) for designating an element of interest.

5. In claim 3 or 4, The metadata of said at least one external image includes identification information of said at least one external electronic device that transmitted said at least one external image, When the above instructions are executed by the at least one processor, the electronic device: An electronic device that uses the above identification information to transmit at least one image generated to at least one external electronic device.

6. In claim 2, When the above instructions are executed by the at least one processor, the electronic device: Obtaining user input associated with elements of interest of said plurality of images from a user of said electronic device, An electronic device for identifying elements of interest in the plurality of images based on the acquired user input.

7. In claim 6, When the above instructions are executed by the at least one processor, the electronic device: Based on the above user input, identify priorities among the elements of interest of the multiple images, An electronic device configured to generate at least one prompt further comprising information about the identified priority.

8. In claim 2, When the above instructions are executed by the at least one processor, the electronic device: Obtain at least one external image, An electronic device that identifies elements of interest in at least one external image using an artificial intelligence model.

9. In a method using an electronic device, An operation of acquiring a plurality of images, each of the plurality of images including metadata including information about an element of interest; An operation of generating at least one prompt for image generation using an artificial intelligence model based on the plurality of images and elements of interest of the plurality of images; and A method comprising: generating at least one image using a generative artificial intelligence model based on at least one generated prompt.

10. In claim 9, A method wherein said at least one prompt includes image information for said plurality of images and text information about elements of interest in said plurality of images.

11. In claim 10, An operation of receiving at least one external image from at least one external electronic device; and Further comprising an operation of identifying an element of interest associated with a user image stored in the electronic device based on a user input of a user of the electronic device; A method wherein said plurality of images include at least one external image and said user image.

12. In claim 11, An operation for requesting establishment of a channel for short-range communication with at least one external electronic device; and A method further comprising: an operation of transmitting a signal to at least one external electronic device to display a UI for designating an element of interest based on the establishment of the channel.

13. In claim 11 or 12, The metadata of said at least one external image includes identification information of said at least one external electronic device that transmitted said at least one external image, The method further comprises an operation of transmitting the at least one generated image to the at least one external electronic device using the identification information.

14. In claim 10, An operation of obtaining user input associated with elements of interest of said plurality of images from a user of said electronic device; and A method further comprising: an operation of identifying elements of interest of the plurality of images based on the acquired user input.

15. In claim 14, An operation of identifying priorities among elements of interest of the plurality of images based on the user input; and A method further comprising the action of generating at least one prompt further including information about the identified priority.

Images