Electronic device, method, and non-transitory computer-readable storage medium for obtaining image

Abstract

This electronic device may comprise a memory storing instructions, and at least one processor. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to: on the basis of arranging each of one or more first unit images on a blank image, obtain, according to color values of respective pixels of each of the one or more first unit images, a first composite image including one or more first visual objects representing the one or more first unit images; on the basis of providing the first composite image to an image change model, obtain a second composite image including one or more second visual objects; and obtain one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects from the second composite image.

Description

Electronic device, method, and non-transient computer-readable storage medium for acquiring images

[0001] The present disclosure relates to an electronic device for acquiring an image, a method, and a non-transient computer-readable storage medium.

[0002] With the advancement of electronic devices, technological development related to electronic devices equipped with Artificial Intelligence (AI) technology is currently underway. AI technology may include technologies utilizing neural networks that simulate biological neural networks.

[0003] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0004] An electronic device is provided. The electronic device may include a memory that stores instructions and includes one or more storage media. The electronic device may include at least one processor that includes processing circuitry. The instructions may cause the electronic device to acquire a first composite image including one or more first visual objects representing the one or more first unit images, based on placing each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images, when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to acquire a second composite image including one or more second visual objects, based on providing the first composite image to an image modification model, when executed individually or collectively by the at least one processor. The above instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to obtain one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects in the second composite image.

[0005] A method is provided. The method may be performed in an electronic device. The method may include the operation of obtaining a first composite image comprising one or more first visual objects representing the one or more first unit images, based on placing each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images. The method may include the operation of obtaining a second composite image comprising one or more second visual objects, based on providing the first composite image to an image modification model. The method may include the operation of obtaining one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects in the second composite image.

[0006] A non-transient computer-readable storage medium is provided. The non-transient computer-readable storage medium may store one or more programs. The one or more programs may include instructions that cause the electronic device to obtain a first composite image comprising one or more first visual objects representing the one or more first unit images, based on placing each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to obtain a second composite image comprising one or more second visual objects, based on providing the first composite image to an image modification model when executed by the electronic device. The above one or more programs may include instructions that cause the electronic device to obtain one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects in the second composite image when executed by the electronic device.

[0007] Figure 1 illustrates examples of unit images constituting an object.

[0008] FIG. 2 illustrates an example of a second unit image obtained based on providing a first unit image to an image change model.

[0009] Figure 3 illustrates an example of a simplified block diagram of an electronic device.

[0010] FIG. 4 illustrates examples of operations of an electronic device for acquiring one or more second unit images according to one or more first unit images.

[0011] FIG. 5 illustrates an example of unit images classified according to the color values ​​of each pixel of the unit images.

[0012] FIG. 6 illustrates an example of a visual object within a composite image based on a unit image.

[0013] FIG. 7 illustrates examples of operations of an electronic device that generates a synthetic image to be provided to an image change model.

[0014] FIG. 8 illustrates examples of operations of an electronic device for acquiring unit images based on providing a first composite image to an image change model.

[0015] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit the scope of other embodiments. A singular expression may include a plural expression unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art described in this disclosure. Terms used in this disclosure that are defined in a general dictionary may be interpreted as having the same or similar meaning as they have in the context of the relevant technology, and are not to be interpreted in an ideal or overly formal sense unless explicitly defined in this disclosure. In some cases, even terms defined in this disclosure are not to be interpreted to exclude the embodiments of this disclosure.

[0016] In the various embodiments of the present disclosure described below, a hardware-based approach is described as an example. However, since the various embodiments of the present disclosure include techniques using both hardware and software, the various embodiments of the present disclosure do not exclude a software-based approach.

[0017] Terms used in the following description to refer to data (e.g., data, information, data point, color histogram), values ​​(e.g., color value), operational states (e.g., operation, process), objects (e.g., visual object, element), network entities, and device components are examples provided for the convenience of explanation. Accordingly, the present disclosure is not limited to the terms described below, and other terms having equivalent technical meanings may be used.

[0018] Additionally, in this disclosure, expressions of "greater than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled; however, this is merely for the purpose of expressing an example and does not exclude descriptions of "greater than" or "less than." Conditions described as "greater than" may be replaced with "greater than," conditions described as "less than" may be replaced with "less than," and conditions described as "greater than and less than" may be replaced with "greater than and less than." Furthermore, "A" to "B" below refer to at least one of elements from A (including A) to B (including B). Below, "C" and / or "D" refers to including at least one of "C" or "D," i.e., {"C", "D", "C" and "D"}.

[0019] FIG. 1 illustrates examples of unit images (111, 112) constituting an object (110). The electronic device (101) may include a stationary electronic device such as a server device, a desktop computer, a TV, etc. By example, without limitation, the electronic device (101) may be one of various types of mobile devices such as a laptop, smartphones with various form factors (e.g., a bar-type smartphone, a foldable-type smartphone, or a rollable-type smartphone), a tablet, a cellular phone, and other similar computing devices. For example, the electronic device (101) may be described as a multifunctional device or a user device.

[0020] Referring to FIG. 1, an electronic device (101) may be described as a device available for creating an object (110). For example, the electronic device (101) may create data related to the object (110). For example, the electronic device (101) may perform rendering of the object (110). For example, the object (110) may include a three-dimensional object, a three-dimensional image, and / or a three-dimensional asset. For example, the object (110) may be created in three-dimensional space. For example, the object (110) may be created for three-dimensional graphics such as games and / or animations, but is not limited thereto.

[0021] According to one embodiment, an object (110) may be composed of unit images (111, 112). For example, a region of the object (110) may be represented using unit images (e.g., unit image (111), unit image (112)). For example, an electronic device (101) may create or represent a region of the object (110) using unit images (e.g., unit image (111), unit image (112)). For example, the electronic device (101) may represent the texture of a region, the pattern of a region, the color of a region, and / or the three-dimensionality of a region using unit images (e.g., unit image (111), unit image (112)). For example, an electronic device (101) may repeatedly place, dispose, arrange, cover, overlay, or apply unit images (e.g., unit image (111), unit image (112)) to a part of an object (110). For example, unit images (e.g., unit image (111), unit image (112)) may be referred to as tiling textures and / or terms having an equivalent technical meaning in terms of being repeatedly placed, arranged, covered, overlaid, or applied to a part of an object (110). For example, the electronic device (101) may create a first part of an object (e.g., an outer wall area) using unit images (111). For example, the electronic device (101) may represent a visual object (e.g., a window) placed in the first part of an object (110) using unit images (111). For example, the electronic device (101) can represent the first area of ​​the object (110) (e.g., an exterior wall area) by repeatedly placing, arranging, covering, applying, or applying a unit image (111). For example, the electronic device (101) can create the second area of ​​the object (110) (e.g., a roof area) using a unit image (112).For example, the electronic device (101) can represent a second area of ​​an object (110) by repeatedly placing, arranging, covering, applying, or applying a unit image (111) to a second area of ​​an object (110) (e.g., a roof area).

[0022] According to one embodiment, an electronic device (101) can represent a portion of an object (110) by repeatedly using unit images (e.g., unit image (111), unit image (112)). By representing a portion of an object (110) using unit images (e.g., unit image (111), unit image (112)), the electronic device (101) may require relatively less memory resources. For example, the less memory resources required by the electronic device (101), the shorter the time required to create the object (110).

[0023] FIG. 2 illustrates an example of a second unit image (202) obtained based on providing a first unit image (201) to an image change model (200).

[0024] Referring to FIG. 2, a first unit image (201) may be provided to an image change model (200). The first unit image (201) may be input to the image change model (200). The first unit image (201) may be an example of the unit images (111, 112) of FIG. 1. The image change model (200) may output a second unit image (202) according to the input first unit image (201). For example, the image change model (200) may include an artificial intelligence model trained to output a second unit image (202) according to the input first unit image (201). For example, the image change model (200) may be further provided with a prompt (210). For example, the image change model (200) may output a second unit image (202) according to the first unit image (201) and the prompt (210). For example, the second unit image (202) may be an image that reflects the context of the prompt (210).

[0025] According to one embodiment, the image change model (200) may include a machine learning model, a deep learning model, and / or a generative artificial intelligence model. For example, the image change model (200) may include a model trained to generate a second unit image (202) using a first unit image (201) and a prompt (210). For example, the image change model (200) may be included within the electronic device (101) of FIG. 1. For example, the operations exemplified in FIG. 2 may be performed in the electronic device (101) of FIG. 1, but are not limited thereto. For example, the image change model (200) may be included in an external electronic device (e.g., a server). For example, the electronic device (101) of FIG. 1 may transmit the first unit image (201) and / or the prompt (210) to an external electronic device (e.g., a server) via a communication circuit (not shown). For example, the electronic device (101) can receive a second unit image (202) from an external electronic device (e.g., a server) through a communication circuit.

[0026] According to one embodiment, the image modification model (200) may include an artificial neural network model comprising a plurality of layers and / or operations (or computations). As an example, but not limited to, the image modification model (200) may include one of a feedforward neural network (FNN), a deep neural network (DNN), a convolutional neural network (CNN), a region with convolutional neural network (R-CNN), a region proposal network (RPN), a recurrent neural network (RNN), a stacking-based deep neural network (S-DNN), a state-space dynamic neural network (S-SDNN), a deconvolution network, a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), deep Q-networks, a fully convolutional network, a long short-term memory (LSTM) network, a classification network, or a combination of two or more of these. However, it is not limited thereto. The image change model (200) within the electronic device (101) may include a hardware structure or a software structure that is additional (or alternative) to the hardware structure.

[0027] According to one embodiment, the image change model (200) may include a diffusion model. The diffusion model may be an example of a generative artificial intelligence model. For example, the diffusion model may be described as a generative artificial intelligence model for generating an image (e.g., a second unit image (202)) by receiving (or inputting) an image (e.g., a first unit image (201)) and a prompt (e.g., a prompt (210)). For example, the diffusion model may include a variational autoencoder (VAE), a variational autodecoder (VAD), a conditioning, and / or a noise predictor. For example, the electronic device (101) may perform forward diffusion using the diffusion model. For example, the electronic device (101) can input original data based on a variant autoencoder (VAE) and generate latent variables by performing forward diffusion. For example, the latent variables may be defined as random vectors following a standard normal distribution. For example, the electronic device (101) can generate noise data (e.g., random noise) by combining the latent variables generated based on conditioning with time steps by performing forward diffusion. For example, the electronic device (101) may provide a first unit image (201) (e.g., a 512x512 pixel image) to the diffusion model to perform forward diffusion. For example, the variant autoencoder of the diffusion model may convert the first unit image (201) into a vector indicating a downsized image (e.g., a 64x64 pixel image corresponding to the first unit image (201)) by reducing (or downsizing) the first unit image (201).For example, a vector indicating a downsized image (e.g., a 64x64 pixel image corresponding to the first unit image (201)) may be composed of numbers describing the downsized image.

[0028] For example, the noise predictor of the diffusion model may add (or inject, or generate) noise to a vector indicating a downsized image (e.g., a 64x64 pixel image corresponding to the first unit image (201)) by performing forward diffusion. For example, a vector function may be used to perform forward diffusion. For example, the diffusion model may generate a vector indicating a first noise image, a vector indicating a second noise image, and / or a vector indicating a final noise image by adding noise at each step of forward diffusion. For example, the vectors may be used to model changes in data according to the degree of noise.

[0029] For example, the noise predictor of the diffusion model can remove noise from the final noise image by performing reverse diffusion on a vector indicating the final noise image. For example, a convolutional neural network (CNN) model (e.g., U-net) may be used to perform reverse diffusion. For example, the electronic device (101) can predict latent variables based on the input of noise data and time steps based on the noise predictor by performing reverse diffusion. For example, the electronic device (101) can restore the original data by inputting the predicted latent variables and time steps based on the variant autodecoder (VAD) of the reverse diffusion. For example, the diffusion model can predict the noise to be removed within the final noise image. For example, the diffusion model can remove noise at each step of the reverse diffusion by removing the predicted noise (or by performing denoising). For example, a vector function may be used to perform reverse diffusion. For example, the diffusion model can generate a vector indicating a third noise image, a vector indicating a fourth noise image, and / or a vector indicating a final image by removing noise for each step of the reverse diffusion. For example, the final image may correspond to a second unit image (202). For example, the conditional part of the diffusion model may provide a prompt (210) to the noise predictor to control the noise predictor according to each step of the reverse diffusion. For example, the diffusion model may generate a second unit image (202) by reflecting the context indicated by the prompt (210). For example, by repeatedly performing forward diffusion and reverse diffusion, the diffusion model may learn the distribution of the original data.For example, a variant autodecoder of the diffusion model can output the second unit image (202) by expanding (or restoring) a vector indicating the final image (e.g., an image corresponding to the second unit image (202)) to the second unit image (202) (e.g., a 512x512 pixel image).

[0030] According to one embodiment, since the diffusion model is based on a probabilistic process (e.g., forward diffusion, reverse diffusion), the style (or theme) of the output image (e.g., second unit image (202)) output by the diffusion model may differ each time, even if the same input conditions (e.g., a prompt (210) indicating the same content) are provided. For example, the electronic device (101) can obtain each of the multiple second unit images (e.g., second unit image (202)) by providing each of the multiple first unit images (e.g., unit images (111, 112), first unit image (201)) to the image change model (200) along with a prompt (210) indicating a specific color (e.g., blue, pink). Each of the multiple second unit images may have different specific color values ​​(e.g., RGB (red-green-blue) values), different saturation, and / or different textures, even though the same content prompt (210) is provided. For example, there may be relatively little similarity (or consistency) in style among the multiple second unit images. For example, if there is relatively little similarity (or consistency) in style among the multiple second unit images, a three-dimensional object (e.g., object (111)) composed of the multiple second unit images may appear unnatural to the user. For example, a method to increase the similarity (or consistency) in style among the multiple second unit images may be required. Additionally, the time required to acquire each of a plurality of second unit images (e.g., second unit image (202)) by providing each of a plurality of first unit images (e.g., unit images (111, 112), first unit image (201)) to the image change model (200) may increase as the number of the plurality of first unit images increases. For example, a method to reduce the time required to acquire each of the plurality of second unit images may be required.

[0031] In the present disclosure, techniques for increasing the similarity (or consistency) of styles between a plurality of second unit images obtained according to a plurality of first unit images and / or techniques for reducing the time required to obtain each of the plurality of second unit images may be described. An electronic device (101) may execute a method of obtaining a composite image based on placing a plurality of first unit images on a blank image. An electronic device (101) may execute a method of obtaining a plurality of second unit images based on providing the composite image to an image alteration model (200). Such methods will be described and illustrated with reference to FIGS. 4, FIGS. 5, FIGS. 6, FIGS. 7, and / or FIGS. 8. For example, the electronic device (101) may include components for providing such methods. Such components will be described and illustrated in more detail with reference to FIGS. 3.

[0032] FIG. 3 illustrates an example of a simplified block diagram of an electronic device (301). The electronic device (301) may be included in the electronic device (101) of FIG. 1.

[0033] Referring to FIG. 3, the electronic device (301) may include at least one processor (300) and / or memory (310). For example, at least one processor (300) and / or memory (310) may be electronically and / or operably coupled with each other by a communication bus. Hereinafter, operably coupled hardware components may mean that a direct or indirect connection between hardware components is established wired or wirelessly so that a second hardware component is controlled by a first hardware component among the hardware components. Although the hardware components illustrated in FIG. 3 are illustrated based on different blocks, the present disclosure is not limited thereto.

[0034] At least one processor (300) may include a hardware component for processing data based on executing instructions. At least one processor (300) may be configured to execute instructions stored in memory (310) individually or collectively. At least one processor (300) may include a processing circuit. For example, the hardware component for processing data may include an arithmetic and logic unit (ALU), a floating point unit (FPU), and a field programmable gate array (FPGA). For example, the hardware component for processing data may include a central processing unit (CPU), a graphic processing unit (GPU), a display processing unit (DPU), a neural processing unit (NPU), a digital signal processor (DSP), an application processor (AP), and / or a microcontroller (MCU). At least one processor (300) may include one or more cores. For example, at least one processor (300) may have the structure of a multi-core processor such as a dual core, quad core, or hexa core.

[0035] Memory (310) may include a hardware component for storing data and / or instructions that are input to and / or output from at least one processor (300). Memory (310) may include one or more storage media. Memory (310) may include volatile memory, such as random-access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM). Volatile memory may include at least one of dynamic RAM (DRAM), static RAM (SRAM), cache RAM, or pseudo SRAM (PSRAM). Non-volatile memory may include at least one of programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), flash memory, hard disk, compact disk, or embedded multimedia card (EMMC).

[0036] According to one embodiment, within the memory (310) of the electronic device (301), one or more instructions (or commands) representing operations and / or operations to be performed on data by at least one processor (300) of the electronic device (301) may be stored. A set of one or more instructions may be referred to as a program, firmware, operating system, process, routine, sub-routine and / or application. For example, one or more instructions may be included in or stored in one or more storage media within the memory (310).

[0037] FIG. 4 illustrates examples of operations of an electronic device (e.g., electronic device (301)) for acquiring one or more second unit images according to one or more first unit images.

[0038] Referring to FIG. 4, in operation 401, an electronic device (301) (e.g., at least one processor (300)) may obtain a first composite image comprising one or more first visual objects based on placing each of one or more first unit images on a blank image according to the color values ​​of the pixels of each of one or more first unit images. For example, one or more first visual objects may correspond to one or more first unit images. For example, one or more first visual objects may represent one or more first unit images. For example, a visual object (e.g., included in one or more first visual objects) may include the same visual composition as a unit image (e.g., included in one or more first unit images).

[0039] According to one embodiment, a blank image may be described as a work area (or reference image) for generating a new image. For example, the blank image may represent a basic background area of ​​a generated image. For example, the blank image may be empty. For example, the blank image may be a single-color image. As an example, but not limited to, the color of the blank image may be set according to the color values ​​of the pixels of one or more first unit images. For example, the color of the blank image may be a color according to the average value of the color values ​​of the pixels of one or more first unit images. For example, the color of the blank image may be a color according to the median value of the color values ​​of the pixels of one or more first unit images. For example, the blank image may be referred to as a canvas image and / or other terms having an equivalent technical meaning. The size of the blank image may be a size that can be provided to the image change model (200). The above size may be determined according to the structure of the image change model (200) and / or the learning settings of the image change model (200).

[0040] According to one embodiment, the electronic device (301) can identify the color of each pixel of one or more first unit images. For example, the electronic device (301) can identify the color histogram of each of one or more first unit images. For example, the 'calcHist' function of OpenCV (open source computer vision library) can be used to identify the color histogram of each of one or more first unit images. For example, the electronic device (301) can identify the color value distribution of each pixel of one or more first unit images. The electronic device (301) can classify one or more first unit images according to the color values ​​of each pixel of one or more first unit images. The electronic device (301) can perform clustering on one or more first unit images according to the color values ​​of each pixel of one or more first unit images. For example, the electronic device (301) can identify a first portion of one or more first unit images and a second portion of one or more first unit images according to the color values ​​of the pixels of each of one or more first unit images. An operation of the electronic device (301) classifying the first unit images according to the color values ​​of the pixels of each of one or more first unit images will be described and illustrated with reference to FIG. 5.

[0041] According to one embodiment, the electronic device (301) may place each of one or more first unit images on a blank image according to the color values ​​of the pixels of each of one or more first unit images. For example, a bin packing algorithm may be used to place each of one or more first unit images on a blank image. For example, the electronic device (301) may place a first portion of one or more first unit images and a second portion of said one or more first unit images, identified according to the color values ​​of the pixels of each of one or more first unit images, on a blank image. According to one embodiment, the electronic device (301) may place the first portion on a blank image and then place the second portion on a blank image according to a determination that the number of unit images included in the first portion is greater than the number of unit images included in the second portion. For example, the electronic device (301) may generate or acquire a first composite image including one or more first visual objects by changing the size of each of one or more first unit images placed on a blank image. For example, acquiring the first composite image will be described and illustrated with reference to FIG. 7.

[0042] In operation 403, an electronic device (301) (e.g., at least one processor (300)) may acquire a second synthetic image containing one or more second visual objects based on providing a first synthetic image containing one or more first visual objects to an image change model (e.g., image change model (200)). For example, one or more second visual objects may be output or generated by the image change model (200) as one or more first visual objects are provided to the image change model (200). For example, the image change model (200) may include a machine learning model, a deep learning model, and / or a generative artificial intelligence model. For example, the image change model (200) may include a diffusion model. For example, the descriptions of the image change model (200) in FIG. 2 may be referenced for the image change model (200). For example, the electronic device (301) may provide the first synthetic image and a prompt to the image change model (200). The electronic device (301) can acquire or generate a second composite image using an image change model (200). For example, the prompt may include conditions for outputting a second composite image according to a first composite image. For example, the prompt may be generated by a user.

[0043] In operation 405, an electronic device (301) (e.g., at least one processor (300)) may acquire one or more second unit images based on performing a crop for each of one or more second visual objects in a second composite image. For example, the electronic device (301) may acquire one or more second unit images based on extracting one or more second visual objects in a second composite image. For example, the electronic device (301) may acquire one or more second unit images based on performing a capture for each of one or more second visual objects in a second composite image.

[0044] According to one embodiment, the electronic device (301) can obtain one or more second unit images by changing the size of each of one or more second visual objects that have been cropped. For example, the electronic device (301) can obtain one or more second unit images by changing the size of each of one or more extracted second visual objects. For example, the electronic device (301) can obtain one or more second unit images by changing the size of each of one or more second visual objects that have been captured.

[0045] According to one embodiment, the time required to acquire one or more second unit images by providing a first composite image including one or more first visual objects to an image change model (200) may be shorter than the time required to acquire one or more second unit images by providing each of the one or more first unit images to the image change model (200). For example, the number of times the image change model (200) is used in the method of providing a first composite image including one or more first visual objects to an image change model (200) may be less than the number of times the image change model (200) is used in the method of providing each of the one or more first unit images to an image change model (200).

[0046] According to one embodiment, the similarity (or consistency) between one or more second unit images obtained by providing a first composite image including one or more first visual objects to an image change model (200) may be higher than the similarity (or consistency) between one or more second unit images obtained by providing each of one or more first unit images to the image change model (200).

[0047] FIG. 5 illustrates an example of unit images (501) classified according to the color values ​​of each pixel of the unit images (501). The unit images (501) may be an example of one or more first unit images of FIG. 4.

[0048] Referring to FIG. 5, the unit images (501) can be classified into a first part (510) of the unit images (501), a second part (520) of the unit images (501), and a third part (530) of the unit images (501) according to the color of each unit image (501). For example, an electronic device (e.g., electronic device (301)) can identify the color of each unit image (501). For example, the electronic device (301) can identify the color values ​​(e.g., RGB (red-green-blue) values) of each pixel of the unit images (501). For example, the electronic device (301) can identify the color histogram of each unit image (501) for the color values ​​of each pixel of the unit images (501). For example, the color histogram can represent the distribution of color values ​​of the pixels of the unit image (e.g., one of the unit images (501)). For example, the 'calcHist' function of OpenCV (open source computer vision library) may be used to identify the color histogram of each of the unit images (501). The electronic device (301) may determine a first part (510) of the unit images (501), a second part (520) of the unit images (501), and a third part (530) of the unit images (501) according to the color values ​​of the pixels of each of the unit images (501). In FIG. 5, the unit images (501) are classified into three clusters (e.g., first part (510), second part (520), third part (530)), but the embodiment is not limited thereto. The number of clusters of the unit images (501) may be set by the user.

[0049] According to one embodiment, the electronic device (301) can identify the average value (or median value) of the color values ​​of each pixel of the unit images (501) using the color histogram of each of the unit images (501). For example, the electronic device (301) can determine a first part (510), a second part (520), and a third part (530) of the unit images (501) based on the similarity of the average value of the color values ​​of each pixel of the unit images (501). For example, a 'K-Means' algorithm may be used to classify the unit images (501) according to the similarity of the average value of the color values ​​of each pixel of the unit images (501). For example, the electronic device (301) can acquire or set data points according to the color histogram of each of the unit images (501). For example, the electronic device (301) can identify or acquire data points corresponding to unit images (501). For example, the electronic device (301) can generate or acquire a graph representing the distribution of data points corresponding to unit images (501). For example, the electronic device (301) can classify unit images (501) using the graph. For example, the electronic device (301) can perform clustering on adjacent data points in a graph representing the distribution of data points according to the number of clusters set by user input. For example, adjacent data points in the graph can be represented as having an average value of similar color values. For example, the electronic device (301) can determine a portion of the unit images (501) corresponding to the clustered data points as a single cluster.For example, the electronic device (301) can determine a first part (510) of the unit images (501), a second part (520) of the unit images (501), and / or a third part (530) of the unit images (501).

[0050] According to one embodiment, the electronic device (301) may place a first part (510) of the unit images (501), a second part (520) of the unit images (501), and a third part (530) of the unit images (501) on a blank image in order of increasing number of elements (e.g., unit images included in the part) contained therein. For example, the electronic device (301) may place the first part (510) of the unit images (501) on the blank image, and then place the second part (520) of the unit images (501) on the blank image. For example, the electronic device (301) may place the second part (520) of the unit images (501) on the blank image, and then place the third part (530) of the unit images (501) on the blank image.

[0051] According to one embodiment, the electronic device (301) can align elements within a portion of the unit images (501) according to the size of the elements (e.g., unit images included in a portion of the unit images (501)) included in a portion of the unit images (501) (e.g., a first portion (510), a second portion (520), a third portion (530)). For example, the electronic device (301) can align the elements in order starting from the largest size among the elements within the portion of the unit images (501) (e.g., a first portion (510), a second portion (520), a third portion (530)). For example, the electronic device (301) can place the elements on a blank image in the aligned order. For example, by placing the elements on the blank image in order starting from the largest size, the area of ​​the blank image can be utilized efficiently. For example, elements that are relatively small in size can be placed between elements that are relatively large in size.

[0052] FIG. 6 illustrates an example of a visual object (609) within a composite image (607) according to a unit image (601). The unit image (601) may be included in one or more first unit images of FIG. 4. For example, the unit image (601) may be included in the unit images (501) of FIG. 5.

[0053] Referring to FIG. 6, an electronic device (e.g., electronic device (301)) can acquire or generate an array image (603) based on a unit image (601). For example, the electronic device (301) can generate or acquire an array image (603) based on copying the unit image (601). For example, the electronic device (301) can acquire or generate multiple copied images by copying the unit image (601). For example, the electronic device (301) can generate or acquire an array image (603) by arranging the unit image (601) and the multiple copied images. For example, to generate the array image (603), a specified number (e.g., 8) of copied images may be required according to the shape (e.g., square) of the unit image (601). For example, the electronic device (301) can generate or obtain an array image (603) by arranging the unit image (601) and eight copy images in a 3x3 matrix form.

[0054] According to one embodiment, the array image (603) may include a combination area (604). For example, an electronic device (301) may identify the combination area (604) in the array image (603). The combination area (604) may include a central area (605) and / or a peripheral area (606). The size of the combination area (604) may be larger than the size of the central area (605). The peripheral area (606) may surround the central area (605). For example, the peripheral area (606) may represent the margin of the central area (605). The central area (605) may correspond to a unit image (601). For example, the central area (605) may be visually identical to the unit image (601). For example, the central area (605) may represent the unit image (601).

[0055] According to one embodiment, an electronic device (301) can extract a combination area (604) from an array image (603). Extracting the combination area (604) from the array image (603) may include performing a crop of the combination area (604) from the array image (603) and / or performing a capture of the combination area (604) from the array image (603). For example, the electronic device (301) may obtain or generate a composite image (607) by placing the combination area (604) extracted from the array image (603) onto a blank image. For example, the composite image (607) may include a visual object (609). For example, the visual object (609) may be visually identical to the combination area (604). For another example, the visual object (609) may be obtained by reducing or enlarging the size of the combination area (604). For example, a visual object (609) can represent a combination area (604).

[0056] According to one embodiment, the visual object (609) may include a central area (611) and / or a peripheral area (613). The central area (611) may correspond to the central area (605). For example, the central area (611) may represent the central area (605). The central area (611) may correspond to the unit image (601). For example, the central area (611) may be visually identical or similar to the unit image (601). For example, the central area (611) may represent the unit image (601). The peripheral area (613) may correspond to the peripheral area (606). For example, the peripheral area (613) may represent the peripheral area (606). For example, the peripheral area (613) may represent the margin of the central area (611). For example, the peripheral area (613) may be used to protect the central area (611) from distortion (e.g., blur effect). For example, the electronic device (301) may obtain or generate an output image (e.g., the second composite image of FIG. 4) according to the composite image (607) by providing the composite image (607) to an image change model (e.g., image change model (200)). For example, the output image may include an output visual object corresponding to the visual object (609). For example, the output visual object may include a first area corresponding to the central area (611) and a second area corresponding to the peripheral area (613). For example, among the first area and the second area, the second area may include distortion. By the visual object (609) including the peripheral area (613), the first area corresponding to the central area (611) in the output image may be prevented from having distortion. For example, the first area within the output visual object may not have distortion.The electronic device (301) can obtain an output unit image according to the unit image (601) (e.g., included in one or more second unit images of FIG. 4) by performing a crop of a first region within an output visual object in the output image.

[0057] FIG. 7 illustrates examples of operations of an electronic device (e.g., electronic device (301)) that generates a composite image (709) to be provided to an image change model (e.g., image change model (200)).

[0058] Referring to FIG. 7, the electronic device (301) can acquire a blank image (701). The electronic device (301) can acquire intermediate images (703, 705, 707) and a composite image (709) by placing unit images (e.g., unit images (501)) on the blank image (701). For example, the electronic device (301) can acquire an intermediate image (703) by placing a first part of the unit images (501) (e.g., a first part (510) of the unit images (501)) on the blank image (701). The intermediate image (703) may include visual objects (710) corresponding to the first part (510) of the unit images (501). For example, the visual objects (710) may be visually identical or similar to the first part (510) of the unit images (501).

[0059] According to one embodiment, the electronic device (301) can obtain an intermediate image (705) by placing a second part of the unit images (501) (e.g., a second part (520) of the unit images (501)) on an intermediate image (703). The intermediate image (705) may include visual objects (720) corresponding to the second part (520) of the unit images (501). For example, the visual objects (720) may be visually identical or similar to the second part (520) of the unit images (501).

[0060] According to one embodiment, the electronic device (301) can obtain an intermediate image (707) by placing a third part of the unit images (501) (e.g., a third part (530) of the unit images (501)) on an intermediate image (705). The intermediate image (707) may include visual objects (730) corresponding to the third part (530) of the unit images (501). For example, the visual objects (730) may be visually identical or similar to the third part (530) of the unit images (501).

[0061] According to one embodiment, the electronic device (301) may acquire or generate a composite image (709) by changing the size of visual objects (710, 720, 730) within an intermediate image (707). The composite image (709) may be an example of the first composite image of FIG. 4. For example, each of the visual objects included in the composite image (709) may be an example of the visual object (609) of FIG. 6. For example, each of the visual objects included in the composite image (709) may be spaced apart from one another. Each of the visual objects included in the composite image (709) may include a central area (e.g., central area (611)) and a peripheral area (e.g., peripheral area (613)).

[0062] FIG. 8 illustrates examples of operations of an electronic device (e.g., electronic device (301)) for acquiring unit images (805) based on providing a first composite image (801) to an image change model (e.g., image change model (200)). For example, the first composite image (801) may be an example of or substantially identical to the composite image (709) of FIG. 7. For example, the first composite image (801) may be an example of the first composite image of FIG. 4.

[0063] Referring to FIG. 8, the electronic device (301) can obtain a second composite image (802) by providing a first composite image (801) to an image change model (200). The second composite image (802) may be an example of the second composite image of FIG. 4. First visual objects in the first composite image (801) may correspond to second visual objects in the second composite image (802). For example, each of the second visual objects may include a central area (e.g., the first area in FIG. 7) and / or a peripheral area (e.g., the second area in FIG. 7). For example, the peripheral area may be adjacent to the edges of each of the second visual objects. For example, the peripheral area may include distortion (e.g., a blur effect).

[0064] According to one embodiment, the electronic device (301) can obtain unit images (805) based on performing a crop for each of the second visual objects in the second composite image (802). For example, the electronic device (301) can obtain unit images (805) based on performing a crop for the center area of ​​each of the second visual objects. For example, the electronic device (301) can obtain unit images (805) by cropping the center area of ​​each of the second visual objects. For example, the electronic device (301) can obtain unit images (805) based on extracting each of the second visual objects from the second composite image (802). For example, the electronic device (301) can obtain unit images (805) based on extracting the center area of ​​each of the second visual objects. For example, unit images (805) can be obtained based on performing a capture for each of the second visual objects in the second composite image (802). For example, the electronic device (301) can obtain unit images (805) based on performing a capture for the central area of ​​each of the second visual objects.

[0065] According to one embodiment, the electronic device (301) can obtain second unit images (805) by changing the size of each of the second visual objects that have been cropped. For example, the electronic device (301) can obtain second unit images (805) by changing the size of each of the extracted second visual objects. For example, the electronic device (301) can obtain second unit images (805) by changing the size of each of the second visual objects that have been captured. For example, the similarity (or consistency) of style between the second unit images (805) may be relatively high. For example, the time used to obtain the second unit images (805) may be relatively short by the electronic device (301) obtaining the second unit images (805) by using the image change model (200) once.

[0066] In an embodiment according to the present disclosure, an electronic device (e.g., electronic device (301)) may acquire a first composite image based on placing one or more first unit images on a blank image. The electronic device (301) may acquire one or more second unit images based on providing the first composite image to an image change model (e.g., image change model (200)). For example, the number of uses of the image change model (200) when providing the first composite image to the image change model (200) may be less than the number of uses of the image change model (200) when providing each of the one or more first unit images to the image change model (200). The electronic device (301) may reduce the time required to acquire one or more second unit images. Additionally, the similarity (or consistency) of style between the one or more second unit images acquired by providing the first composite image to the image change model (200) may be relatively high. The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs from the description below.

[0067] The electronic devices according to the various embodiments disclosed in this document may be of various forms. The electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, electronic devices, or consumer electronics. The electronic devices according to the embodiments of this document are not limited to the devices described above.

[0068] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as “coupled” or “connected” to another (e.g., 2nd) component, with or without the terms “functionally” or “communicationly,” it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0069] The term “module” as used in the 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, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof 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).

[0070] Various embodiments of this document may be implemented as software comprising one or more instructions stored in a storage medium (e.g., memory (310)) readable by a machine (e.g., electronic device (101) of FIG. 1, electronic device (301) of FIG. 3). For example, a processor (e.g., at least one processor (300)) of the machine (e.g., electronic device (101), electronic device (301)) may call at least one of the one or more instructions stored from the storage medium and execute it. This enables the machine to be operated 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 that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0071] According to one embodiment, the method according to the various embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0072] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, 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. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by the module, program, or other components 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.

[0073] The technical problems to be solved in this disclosure are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this disclosure pertains.

[0074] An electronic device as described above may include a memory that stores instructions and includes one or more storage media. The electronic device may include at least one processor that includes processing circuitry. The instructions may cause the electronic device to acquire a first composite image including one or more first visual objects representing the one or more first unit images, based on placing each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images, when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to acquire a second composite image including one or more second visual objects, based on providing the first composite image to an image modification model, when executed individually or collectively by the at least one processor. The above instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to obtain one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects in the second composite image.

[0075] According to one embodiment, the instructions may cause the electronic device to identify a first portion of the one or more first unit images and a second portion of the one or more first unit images according to the color values ​​of the pixels of each of the one or more first unit images, when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to obtain the first composite image by placing the first portion on the blank image and then placing the second portion on the blank image, according to a determination that the number of unit images included in the first portion is greater than the number of unit images included in the second portion, when executed individually or collectively by the at least one processor.

[0076] According to one embodiment, the instructions may cause the electronic device to identify a color histogram representing the distribution of color values ​​of the pixels of each of the one or more first unit images when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to identify the average value of the color values ​​of the pixels of each of the one or more first unit images using the color histogram when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to identify the first part of the one or more first unit images and the second part of the one or more first unit images based on the similarity of the average value of the color values ​​of the pixels of each of the one or more first unit images when executed individually or collectively by the at least one processor.

[0077] According to one embodiment, each of the one or more first visual objects within the first composite image may be spaced apart from each other.

[0078] According to one embodiment, the instructions may cause the electronic device to acquire eight copies of each of the one or more first unit images by copying each of the one or more first unit images when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to acquire an array image of each of the one or more first unit images by arranging each of the one or more first unit images and the eight copies of the images in a 3x3 matrix form when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to identify a combination region in the array image of each of the one or more first unit images, including a central region representing the corresponding first unit image and a peripheral region surrounding the central region, when executed individually or collectively by the at least one processor. The above instructions may cause the electronic device to crop the combination region in the array image of each of the one or more first unit images when executed individually or collectively by the at least one processor. The above instructions may cause the electronic device to obtain the first composite image by placing the cropped combination region on the blank image when executed individually or collectively by the at least one processor.

[0079] According to one embodiment, each of the one or more second visual objects may include a central region and a peripheral region surrounding the central region. When the instructions are executed individually or collectively by the at least one processor, the electronic device may cause the one or more second unit images to be obtained by cropping the central region of each of the one or more second visual objects in the second composite image.

[0080] According to one embodiment, the color of the blank image may be set according to the color values ​​of the pixels of each of the one or more first unit images.

[0081] According to one embodiment, the instructions may cause the electronic device to generate a prompt for outputting the second composite image including the one or more second visual objects according to the first composite image including the one or more first visual objects, when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to acquire the second composite image by providing the prompt and the first composite image to the image change model, when executed individually or collectively by the at least one processor.

[0082] According to one embodiment, the image modification model may include a generative artificial intelligence model.

[0083] According to one embodiment, each of the one or more first visual objects may include an image in which each of the one or more first unit images is enlarged or reduced.

[0084] A method performed in an electronic device as described above may include an operation of acquiring a first composite image comprising one or more first visual objects representing the one or more first unit images, based on placing each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images. The method may include an operation of acquiring a second composite image comprising one or more second visual objects, based on providing the first composite image to an image modification model. The method may include an operation of acquiring one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects in the second composite image.

[0085] According to one embodiment, the method may include an operation of identifying a first portion of the one or more first unit images and a second portion of the one or more first unit images according to the color values ​​of the pixels of each of the one or more first unit images. The method may include an operation of obtaining the first composite image by placing the first portion on the blank image and then placing the second portion on the blank image, based on a determination that the number of unit images included in the first portion is greater than the number of unit images included in the second portion.

[0086] According to one embodiment, the method may include an operation of identifying a color histogram representing the distribution of color values ​​of the pixels of each of the one or more first unit images. The method may include an operation of identifying an average value of the color values ​​of the pixels of each of the one or more first unit images using the color histogram. The method may include an operation of identifying a first part of the one or more first unit images and a second part of the one or more first unit images based on the similarity of the average value of the color values ​​of the pixels of each of the one or more first unit images.

[0087] According to one embodiment, each of the one or more first visual objects within the first composite image may be spaced apart from each other.

[0088] According to one embodiment, the method may include the operation of obtaining eight copied images of each of the one or more first unit images by copying each of the one or more first unit images. The method may include the operation of obtaining an array image of each of the one or more first unit images based on arranging each of the one or more first unit images and the eight copied images in a 3x3 matrix form. The method may include the operation of identifying a combination area in the array image of each of the one or more first unit images, the combination area including a central area representing the corresponding first unit image and a surrounding area surrounding the central area. The method may include the operation of cropping the combination area in the array image of each of the one or more first unit images. The method may include the operation of obtaining the first composite image by placing the cropped combination area on the blank image.

[0089] According to one embodiment, each of the one or more second visual objects may include a central region and a surrounding region that encloses the central region. The method may include the operation of obtaining the one or more second unit images by performing a crop of the central region of each of the one or more second visual objects in the second composite image.

[0090] According to one embodiment, the color of the blank image may be set according to the color values ​​of the pixels of each of the one or more first unit images.

[0091] According to one embodiment, the method may include an operation of generating a prompt for outputting the second composite image including the one or more second visual objects according to the first composite image including the one or more first visual objects. The method may include an operation of obtaining the second composite image by providing the prompt and the first composite image to the image change model.

[0092] According to one embodiment, the image modification model may include a generative artificial intelligence model.

[0093] According to one embodiment, each of the one or more first visual objects may include an image in which each of the one or more first unit images is enlarged or reduced.

[0094] In a computer-readable storage medium in which one or more programs as described above are stored, the one or more programs may include instructions that cause the electronic device to obtain a first composite image comprising one or more first visual objects representing the one or more first unit images, based on placing each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to obtain a second composite image comprising one or more second visual objects, based on providing the first composite image to an image modification model when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to obtain one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects in the second composite image when executed by the electronic device.

[0095] According to one embodiment, the one or more programs may include instructions that cause the electronic device to identify a first portion of the one or more first unit images and a second portion of the one or more first unit images according to the color values ​​of the pixels of each of the one or more first unit images when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to obtain a first composite image by placing the first portion on the blank image and then placing the second portion on the blank image, according to a determination that the number of unit images included in the first portion is greater than the number of unit images included in the second portion when executed by the electronic device.

[0096] According to one embodiment, the one or more programs may include instructions that cause the electronic device to identify a color histogram representing the distribution of color values ​​of the pixels of each of the one or more first unit images when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to identify an average value of the color values ​​of the pixels of each of the one or more first unit images using the color histogram when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to identify a first part of the one or more first unit images and a second part of the one or more first unit images based on the similarity of the average value of the color values ​​of the pixels of each of the one or more first unit images when executed by the electronic device.

[0097] According to one embodiment, each of the one or more first visual objects within the first composite image may be spaced apart from each other.

[0098] According to one embodiment, the one or more programs may include instructions that cause the electronic device to obtain eight copied images of each of the one or more first unit images by copying each of the one or more first unit images when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to obtain an array image of each of the one or more first unit images based on arranging each of the one or more first unit images and the eight copied images in a 3x3 matrix form when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to identify a combination area including a central area representing the corresponding first unit image and a surrounding area surrounding the central area in the array image of each of the one or more first unit images when executed by the electronic device. The above one or more programs may include instructions that cause the electronic device to crop the combination area in the array image of each of the one or more first unit images when executed by the electronic device. The above one or more programs may include instructions that cause the electronic device to obtain the first composite image by placing the cropped combination area on the blank image when executed by the electronic device.

[0099] According to one embodiment, each of the one or more second visual objects may include a central region and a peripheral region surrounding the central region. The one or more programs may include instructions that cause the electronic device to obtain the one or more second unit images by performing a crop of the central region of each of the one or more second visual objects in the second composite image when executed by the electronic device.

[0100] According to one embodiment, the color of the blank image may be set according to the color values ​​of the pixels of each of the one or more first unit images.

[0101] According to one embodiment, the one or more programs may include instructions that cause the electronic device to generate a prompt for outputting the second composite image including the one or more second visual objects according to the first composite image including the one or more first visual objects when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to obtain the second composite image by providing the prompt and the first composite image to the image change model when executed by the electronic device.

[0102] According to one embodiment, the image modification model may include a generative artificial intelligence model.

[0103] According to one embodiment, each of the one or more first visual objects may include an image in which each of the one or more first unit images is enlarged or reduced.

[0104] The device described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the device and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0105] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be embodied in any type of machine, component, physical device, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0106] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. In this case, the medium may continuously store a computer-executable program, or temporarily store it for execution or download. Additionally, the medium may be various recording or storage means in the form of a single or several combined hardware, and may not be limited to a medium directly connected to a computer system but may exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software.

[0107] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0108] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

1. In an electronic device, Memory comprising one or more storage media for storing instructions; and It includes at least one processor comprising a processing circuit, and When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Based on placing each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images, a first composite image is obtained that includes one or more first visual objects representing the one or more first unit images. Based on providing the first composite image to an image change model, a second composite image including one or more second visual objects is obtained, and Causing to obtain one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects in the second composite image. Electronic device.

2. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Identifying a first portion of the one or more first unit images and a second portion of the one or more first unit images according to the color values ​​of the pixels of each of the one or more first unit images, and Causing to obtain the first composite image by placing the first part on the blank image and then placing the second part on the blank image, in accordance with the determination that the number of unit images included in the first part is greater than the number of unit images included in the second part. Electronic device.

3. In Claim 2, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Identify a color histogram representing the distribution of color values ​​of the pixels of each of the one or more first unit images, and Using the above color histogram, the average value of the color values ​​of the pixels of each of the one or more first unit images is identified, and Causing to identify the first part of the one or more first unit images and the second part of the one or more first unit images based on the similarity of the average value of the color values ​​of the pixels of each of the one or more first unit images. Electronic device.

4. In Claim 1, Each of the one or more first visual objects within the first composite image is spaced apart from one another. Electronic device.

5. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: By copying each of the one or more first unit images, eight copied images of each of the one or more first unit images are obtained, and Based on arranging each of the one or more first unit images and the eight copy images in a 3x3 matrix form, an array image of each of the one or more first unit images is obtained, and Identifying a combination region including a central region representing the first unit image and a surrounding region surrounding the central region in each of the array images of the one or more first unit images, and Cropping the combination region in the array image of each of the one or more first unit images, and By placing the cropped combination area above on the blank image, causing the first composite image to be obtained, Electronic device.

6. In Claim 1, Each of the above one or more second visual objects includes a central area and a surrounding area that encloses the central area, and When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Causing to obtain the one or more second unit images by cropping the central region of each of the one or more second visual objects in the second composite image. Electronic device.

7. In Claim 1, The color of the blank image is set according to the color values ​​of the pixels of each of the one or more first unit images. Electronic device.

8. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Generating a prompt for outputting the second composite image including the one or more second visual objects according to the first composite image including the one or more first visual objects, and By providing the above prompt and the above first composite image to the image change model, causing the second composite image to be obtained, Electronic device.

9. In Claim 1, The above image modification model includes a generative artificial intelligence model, Electronic device.

10. In Claim 1, Each of the above one or more first visual objects comprises an image in which each of the above one or more first unit images is enlarged or reduced. Electronic device.

11. In a method performed in an electronic device, The operation of obtaining a first composite image comprising one or more first visual objects representing the one or more first unit images, based on arranging each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images. Based on providing the first composite image to an image change model, the operation of acquiring a second composite image including one or more second visual objects, and The method includes the operation of obtaining one or more second unit images corresponding to the one or more second visual objects by cropping each of the one or more second visual objects in the second composite image. method.

12. In Claim 11, An operation of identifying a first portion of the one or more first unit images and a second portion of the one or more first unit images according to the color values ​​of the pixels of each of the one or more first unit images, and The operation of obtaining the first composite image by placing the first part on the blank image and then placing the second part on the blank image, in accordance with the determination that the number of unit images included in the first part is greater than the number of unit images included in the second part. method.

13. In Claim 12, The operation of identifying a color histogram representing the distribution of color values ​​of the pixels of each of the one or more first unit images, An operation of identifying the average value of the color values ​​of the pixels of each of the one or more first unit images using the above color histogram, and The operation of identifying the first part of the one or more first unit images and the second part of the one or more first unit images based on the similarity of the average value of the color values ​​of the pixels of each of the one or more first unit images, method.

14. In Claim 11, Each of the one or more first visual objects within the first composite image is spaced apart from one another. method.

15. In Claim 11, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: The operation of obtaining 8 copied images of each of the one or more first unit images by copying each of the one or more first unit images, The operation of obtaining an array image of each of the one or more first unit images based on arranging each of the one or more first unit images and the eight copy images in a 3x3 matrix form, An operation of identifying a combination region including a central region representing a corresponding first unit image and a surrounding region surrounding the central region in each of the array images of the above one or more first unit images, The operation of cropping the combination area in the array image of each of the one or more first unit images, and The operation of obtaining the first composite image by placing the cropped combination area on the blank image, method.

16. In Claim 11, Each of the above one or more second visual objects includes a central area and a surrounding area that encloses the central area, and The operation of acquiring the one or more second unit images by cropping the central region of each of the one or more second visual objects in the second composite image, method.

17. In Claim 11, The color of the blank image is set according to the color values ​​of the pixels of each of the one or more first unit images. method.

18. In Claim 11, An operation of generating a prompt for outputting a second composite image including one or more second visual objects according to a first composite image including one or more first visual objects, and The operation of obtaining the second composite image by providing the above prompt and the above first composite image to the image change model, method.

19. In Claim 11, The above image modification model includes a generative artificial intelligence model, method.

20. In a non-transient computer-readable storage medium storing one or more programs, When the above one or more programs are executed by an electronic device, Based on placing each of the one or more first unit images on a blank image according to the color values ​​of the pixels of each of the one or more first unit images, a first composite image is obtained that includes one or more first visual objects representing the one or more first unit images. Based on providing the first composite image to an image change model, a second composite image including one or more second visual objects is obtained, and The electronic device comprises instructions that cause one or more second unit images corresponding to the one or more second visual objects to be obtained by cropping each of the one or more second visual objects in the second composite image. Non-transient computer-readable storage media.

Images