Electronic device, method, and non-transitory computer-readable storage medium for obtaining prompt to be used for generating image

Abstract

This electronic device may comprise: a memory storing instructions; a display; and at least one processor. The instructions may instruct the electronic device to: receive a first user input indicating a first prompt for synthesizing an image; before synthesizing the image on the basis of the first user input, determine, by using the first prompt indicated by the first user input, whether to further obtain information to be used for synthesizing the image; on the basis of determining to further obtain the information to be used for synthesizing the image, display, through the display, a user interface (UI) for receiving a second user input for synthesizing the image; on the basis of the second user input received through the UI, generate a second prompt by using the first prompt and the information indicated by the second user input; and obtain an image corresponding to the first user input by using the second prompt.

Description

Electronic device, method, and non-transient computer-readable storage medium for acquiring a prompt to be used for generating an image

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

[0002] A service utilizing an artificial intelligence model is provided. The service may be configured to respond to user input based on natural language (e.g., one or more natural language sentence(s) referred to as a prompt) and to perform a function expressed by said user input (e.g., creation of media content such as images, videos, and / or audio). To execute the artificial intelligence model, a high-performance server may be deployed on a network. An electronic device owned by a user may communicate with the server to obtain the result of executing said function based on the artificial intelligence model.

[0003] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure.

[0004] No claim or determination is made as to whether any of the foregoing can be applied as prior art related to the present disclosure.

[0005] An electronic device is described. The electronic device may include a memory comprising one or more storage media for storing instructions. The electronic device may include a display. The electronic device may include at least one processor comprising a processing circuit. The instructions may cause the electronic device to receive a first user input corresponding to a first prompt for synthesizing an image when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to control the display (208) to display a user interface (UI) related to receiving a second user input corresponding to the synthesis of an image, based on determining to acquire additional information corresponding to the synthesis of the image based on the first prompt, before synthesizing the image when executed individually or collectively by the at least one processor. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to obtain a second prompt using the additional information according to the first prompt and the second user input received through the UI. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to obtain an image corresponding to the first user input based on the second prompt.

[0006] A method is provided. The method may be executed within an electronic device having a display. The method may include an operation of receiving a first user input corresponding to a first prompt for synthesizing an image. The method may include an operation of controlling the display to display a user interface (UI) related to receiving a second user input corresponding to the synthesis of an image, based on determining to acquire additional information corresponding to the synthesis of the image based on the first prompt before synthesizing the image. The method may include an operation of acquiring a second prompt using the additional information corresponding to the second user input received through the first prompt and the UI. The method may include an operation of acquiring an image corresponding to the first user input based on the second prompt.

[0007] 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 receive a first user input corresponding to a first prompt for synthesizing an image when executed by an electronic device having a display. The one or more programs may include instructions that cause the electronic device to control the display to display a user interface (UI) related to receiving a second user input corresponding to the synthesis of an image, based on determining to acquire additional information corresponding to the synthesis of the image based on the first prompt before synthesizing the image when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to acquire a second prompt using the additional information corresponding to the second user input received through the first prompt and the UI when executed by the electronic device. The above one or more programs may include instructions that cause the electronic device to acquire an image corresponding to the first user input based on the second prompt when executed by the electronic device.

[0008] Figure 1 illustrates an example of an electronic device that displays an image using a prompt.

[0009] Figure 2 is a simplified block diagram of an exemplary electronic device.

[0010] Figure 3 is a simplified block diagram of an exemplary external electronic device.

[0011] Figure 4 is a flowchart illustrating the operation of an electronic device that acquires an image based on displaying a user interface (UI).

[0012] FIG. 5a illustrates an exemplary operation of an electronic device that determines whether to acquire information.

[0013] FIG. 5b illustrates an exemplary operation of an electronic device that performs a function corresponding to user input using models.

[0014] FIG. 6 illustrates an exemplary operation of an electronic device displaying a UI related to information.

[0015] FIG. 7 illustrates an exemplary operation of an electronic device that generates a second prompt.

[0016] FIG. 8 illustrates an exemplary operation of an electronic device displaying an acquired image.

[0017] FIG. 9 illustrates examples of operations performed within an electronic device and an external electronic device.

[0018] FIG. 10 illustrates an exemplary operation of an external electronic device that synthesizes images.

[0019] FIG. 11 illustrates an exemplary electronic device and an exemplary external electronic device for acquiring an image according to various embodiments.

[0020] Figure 1 illustrates an example of an electronic device that displays an image using a prompt.

[0021] Referring to FIG. 1, the electronic device (100) may include a display (e.g., the display (208) of FIG. 2). For example, the electronic device (100) may be used to display an image. For example, the electronic device (100) may receive user input indicating a prompt used to generate the image. For example, the electronic device (100) may receive the user input through a microphone (e.g., the microphone (204) of FIG. 2). The electronic device (100) may receive user input through other means, such as a control device (e.g., a remote controller), as well as through the microphone. For example, the control device may transmit a signal indicating the audio signal to the electronic device (100) based on the audio signal obtained through the microphone included in the control device. For example, the electronic device (100) may include an IR (infra-red) circuit. For example, the electronic device (100) can receive a signal indicating the user input from a control device (e.g., a remote controller) through the IR circuit.

[0022] Although the operation of the electronic device (100) receiving a signal from the control device through the IR circuit has been described above, the embodiments of the present disclosure are not limited thereto. For example, the control device may transmit a signal to the electronic device (100) based on receiving an input from an input device (e.g., a button) included in the control device. For example, the electronic device (100) may receive the signal from the control device through the IR circuit.

[0023] For example, the electronic device (100) may acquire or generate the image using a trained model (e.g., the second model (730) of FIG. 7). For example, the electronic device (100) may acquire or generate the image by providing the trained model with a prompt corresponding to the user input. For example, the electronic device (100) may include the trained model. However, embodiments of the present disclosure are not limited thereto. For example, an external electronic device (e.g., the external electronic device (300) of FIG. 3) may include the trained model. For example, the electronic device (100) may transmit a signal indicating the prompt to the external electronic device through a communication circuit (e.g., the communication circuit (205) of FIG. 2). For example, the external electronic device may provide the prompt to the trained model based on receiving the signal. For example, the external electronic device may generate the image by providing the prompt to the trained model. For example, the external electronic device may transmit data representing the image to the electronic device (100) through a communication circuit (e.g., the communication circuit (305) of FIG. 3). For example, the electronic device (100) may display the image through the display using the received data.

[0024] For example, the electronic device (100) may use the microphone to receive user input indicating the prompt. For example, the user (120) may input or provide voice corresponding to the prompt to the microphone. For example, the user (120) may specifically describe the content (or composition) of the image to display the image desired (or specific) by the user (120) on the electronic device (100). For example, the electronic device (100) may be required to receive user input indicating a long prompt (or a prompt containing a lot of information) to display a specific image. For example, the more specific the prompt, the more specifically the image may be expressed. For example, the electronic device (100) may identify the prompt by performing voice recognition on the audio signal obtained through the microphone. For example, the longer the length of the audio signal, the lower the accuracy of the voice recognition may be. For example, if the accuracy of the voice recognition is low, the electronic device (100) may have difficulty accurately identifying a prompt corresponding to user input. For example, the electronic device (100) may be required to accurately identify a prompt that appears by the user input. For example, the electronic device (100) may display a user interface (UI) for augmenting, acquiring, or generating a short prompt based on user input that indicates a short prompt (or a prompt containing little information). For example, when the electronic device (100) displays the UI, it may add another prompt to the short prompt based on receiving other user input regarding the UI. For example, the electronic device (100) may acquire an augmented prompt using the short prompt and the other prompt.For example, the electronic device (100) can acquire an image by providing the augmented prompt to the trained model.

[0025] For example, the electronic device (100) may display a UI before generating an image to augment a prompt. For example, generating an image by providing a prompt to the trained model may take time. For example, the time required to display a UI to augment a prompt after displaying the image generated by providing a prompt to the trained model through the display may be longer than the time required to display a UI to augment a prompt before generating the image. For example, to reduce the time required to display an image using an augmented prompt, the electronic device (100) may be required to display a UI to augment a prompt through the display before generating an image using a prompt or displaying an image.

[0026] For example, the electronic device (100) may include hardware components used to perform or execute the above operations. The hardware components are described and illustrated with reference to FIG. 2.

[0027] For example, an external electronic device (e.g., the external electronic device (300) of FIG. 3) may include hardware components used to perform or execute the above operations. The hardware components are described and illustrated with reference to FIG. 3.

[0028] Figure 2 is a simplified block diagram of an exemplary electronic device.

[0029] Referring to FIG. 2, the electronic device (100) may include at least one processor (207), memory (206), communication circuit (205), microphone (204), and display (208).

[0030] At least one processor (207) may include a hardware component for processing data using instructions stored in memory (206). The hardware component for processing data may include a CPU (central processing unit) (e.g., including processing circuits). The hardware component for processing data may include a GPU (graphic processing unit) (e.g., including processing circuits). The hardware component for processing data may include a DPU (display processing unit) (e.g., including processing circuits). The hardware component for processing data may include a NPU (neural processing unit) (e.g., including processing circuits).

[0031] At least one processor (207) may include one or more cores. For example, at least one processor (207) may have the structure of a multi-core processor such as a dual core, a quad core, or a hexa core.

[0032] Memory (206) may include a hardware component for storing data and / or instructions that are input to and / or output from at least one processor (207). Memory (206) may include, for example, volatile memory such as random-access memory (RAM) and / or non-volatile memory such as read-only memory (ROM). Volatile memory may include, for example, at least one of dynamic RAM (DRAM), static RAM (SRAM), cache RAM, and pseudo SRAM (PSRAM). Non-volatile memory may include, for example, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), flash memory, hard disk, compact disk, and embedded multimedia card (EMMC).

[0033] The communication circuit (205) may include hardware components to support the transmission and / or reception of signals between the electronic device (100) and an external electronic device. The communication circuit (205) may include, for example, at least one of a modem, an antenna, and an O / E (optic / electronic) converter. The communication circuit (205) may support the transmission and / or reception of signals based on various types of protocols such as Ethernet, LAN (local area network), WAN (wide area network), Wi-Fi (wireless fidelity), Bluetooth, BLE (Bluetooth low energy), Zigbee, LTE (long term evolution), and 5G NR (new radio).

[0034] The display (208) can output visualized information. For example, the display (208) can output visualized information to a user under the control of at least one processor (207). The display (208) may include hardware components of an electronic device (100) used to display a screen. For example, the display (208) may include light-emitting elements and circuits (e.g., transistors) that control the light-emitting elements to emit light. For example, each of the light-emitting elements may include an organic light-emitting diode (OLED) or a micro LED. However, it is not limited thereto. For example, the display (208) may include a liquid crystal display (LCD).

[0035] A microphone (204) may be used to acquire an audio signal. For example, the audio signal may be an audio signal of the user's (120) voice. For example, the audio signal may represent a prompt to be used to generate an image.

[0036] At least one processor (207) may receive a first user input indicating a first prompt for synthesizing an image (e.g., the first prompt (500) of FIG. 5a). Before synthesizing the image based on the first user input, at least one processor (207) may determine whether to acquire more information to be used to synthesize the image by using the first prompt (e.g., the first prompt (500) of FIG. 5a) indicated by the first user input. For example, at least one processor (207) may display a UI (e.g., UI (612) of FIG. 6) for receiving a second user input for synthesizing the image through a display (208) based on a decision to acquire more information to be used to synthesize the image. For example, at least one processor (207) can generate a second prompt (e.g., the second prompt (720) of FIG. 7) based on the second user input received through the UI, using the information indicated by the first prompt and the second user input. For example, at least one processor (207) can obtain an image corresponding to the first user input using the second prompt. For example, a microphone (204) can be used to receive the first user input and / or the second user input.

[0037] Figure 3 is a simplified block diagram of an exemplary external electronic device.

[0038] Referring to FIG. 3, the external electronic device (300) may include at least one processor (307), memory (306), and communication circuit (305).

[0039] At least one processor (307) may include a hardware component for processing data using instructions stored in memory (306). The hardware component for processing data may include a central processing unit (e.g., including a processing circuit). The hardware component for processing data may include a neural processing unit (e.g., including a processing circuit).

[0040] At least one processor (307) may include one or more cores. For example, at least one processor (307) may have the structure of a multi-core processor such as a dual core, a quad core, or a hexa core.

[0041] Memory (306) may include a hardware component for storing data and / or instructions that are input to and / or output from at least one processor (307). Memory (306) may include, for example, volatile memory such as RAM (random-access memory) and / or non-volatile memory such as ROM (read-only memory). Volatile memory may include, for example, at least one of DRAM (dynamic RAM), SRAM (static RAM), cache RAM, and PSRAM (pseudo SRAM). Non-volatile memory may include, for example, at least one of PROM (programmable ROM), EPROM (erasable PROM), EEPROM (electrically erasable PROM), flash memory, hard disk, compact disk, and EMMC (embedded multimedia card).

[0042] The communication circuit (305) may include hardware components to support the transmission and / or reception of signals between the electronic device (100) and an external electronic device. The communication circuit (305) may include, for example, at least one of a modem, an antenna, and an O / E (optic / electronic) converter. The communication circuit (305) may support the transmission and / or reception of signals based on various types of protocols such as Ethernet, LAN (local area network), WAN (wide area network), Wi-Fi (wireless fidelity), Bluetooth, BLE (Bluetooth low energy), Zigbee, LTE (long term evolution), and 5G NR (new radio).

[0043] At least one processor (307) may generate data for displaying one or more visual objects based on receiving a signal indicating a first prompt (e.g., the first prompt (500) of FIG. 5a). For example, at least one processor (307) may receive said signal from an electronic device (100) via a communication circuit (305). For example, at least one processor (307) may receive another signal indicating at least one of the one or more visual objects corresponding to user input received by the electronic device (100) based on transmitting said data. At least one processor (307) may synthesize an image (e.g., image (740) of FIG. 7) using a second prompt (e.g., the second prompt (720) of FIG. 7) based on receiving said other signal. For example, at least one processor (307) can obtain a second prompt (e.g., the second prompt (720) of FIG. 7) by providing a first prompt (e.g., the first prompt (500) of FIG. 5a) and information (e.g., additional information (705) of FIG. 7) to a second model (e.g., the second model (730) of FIG. 7). For example, at least one processor (307) can transmit the image to an electronic device (100) through a communication circuit (305).

[0044] FIG. 4 is a flowchart illustrating the operation of an electronic device that acquires an image based on displaying a user interface (UI). This method may be executed by the electronic device (100) illustrated in FIG. 2 or by at least one processor (207) of the electronic device (100).

[0045] This method may be executed by the electronic device (100) illustrated in FIG. 2 or at least one processor (207) of the electronic device (100). In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0046] Referring to FIG. 4, in operation 410, the electronic device (100) may receive a first user input corresponding to a first prompt (e.g., the first prompt (500) of FIG. 5a) for synthesizing an image (e.g., the image (740) of FIG. 7). For example, the electronic device (100) may receive a first user input indicating a first prompt (e.g., the first prompt (500) of FIG. 5a) for synthesizing an image (e.g., the image (740) of FIG. 7). For example, the first user input may include voice input. For example, the electronic device (100) may receive a first user input for an audio signal indicating the first prompt through a microphone (204).

[0047] According to one embodiment, the electronic device (100) can perform speech recognition on an audio signal obtained through a microphone (204). For example, the electronic device (100) can transmit the audio signal to another electronic device (e.g., a server) to perform speech recognition. For example, the other electronic device may be used to perform speech-to-text (STT). For example, the other electronic device may be different from the external electronic device (300). For example, a first prompt (500) obtained by performing speech recognition on the audio signal may be transmitted to the electronic device (100). However, it is not limited thereto. For example, the other electronic device may be the same as the external electronic device (300).

[0048] Although the operation of an electronic device (100) transmitting an audio signal to another electronic device has been described above, embodiments of the present disclosure are not limited thereto. For example, the electronic device (100) may perform voice recognition on the audio signal within the electronic device (100). For example, by performing voice recognition on the audio signal, the electronic device (100) may identify a first prompt (500) corresponding to the audio signal.

[0049] Although the operation of performing voice recognition within the electronic device (100) or within another electronic device with respect to an audio signal obtained through the microphone (204) of the electronic device (100) has been described above, the embodiments of the present disclosure are not limited thereto. For example, the electronic device (100) may receive a signal representing another audio signal obtained through the microphone of a control device (e.g., a remote controller) via an IR circuit. For example, the control device may receive an analog voice signal through the microphone of the control device. For example, the control device may transmit the digitized other signal to the electronic device (100) by digitizing the analog voice signal. For example, the electronic device (100) may perform voice recognition on the other audio signal based on receiving the signal. However, it is not limited thereto. For example, the control device may perform voice recognition on the other audio signal. For example, the electronic device (100) can receive a signal obtained by performing voice recognition on the other audio signal from the control device through an IR circuit.

[0050] According to one embodiment, the first user input may include at least one of an input representing text, an input representing voice, an image, and a video. For example, an electronic device (100) may obtain a first prompt (e.g., the first prompt (500) of FIG. 5a) based on at least one of an input representing text, an input representing voice, an image, and a video. For example, the first prompt may include at least one of text, voice, an image, and / or a video.

[0051] In operation 420, the electronic device (100) may control the display (208) to display a UI (e.g., UI (612) of FIG. 6) related to receiving a second user input corresponding to the synthesis of the image, when it decides to acquire additional information (e.g., additional information (705) of FIG. 7) to be used to synthesize the image based on a first prompt (e.g., the first prompt (500) of FIG. 5a) before synthesizing (or generating) the image based on the first user input, the electronic device (100) may decide whether to acquire additional information (e.g., additional information (705) of FIG. 7) to be used to synthesize the image using the first prompt (e.g., the first prompt (500) of FIG. 5a) that appears by the first user input. For example, the operation of determining whether to acquire the information is described and illustrated in more detail with reference to FIG. 5a.

[0052] FIG. 5a illustrates an exemplary operation of an electronic device that determines whether to acquire information.

[0053] Referring to FIG. 5a, the electronic device (100) may receive a first user input representing a first prompt (500). For example, the first prompt (500) may include a set of information. For example, the set of information may be described as information used to generate an image by being provided to a model trained to generate an image (e.g., the second model (730) in FIG. 7). For example, the set of information may be described as information required to acquire an image (e.g., the image (740) in FIG. 7). For example, the information in the set may be described as information describing an image (e.g., the image (740) in FIG. 7). For example, the information in the set may represent words (e.g., beach, sand).

[0054] For example, the first prompt (500) may include first information (505-1), second information (505-2), to N information (505-N) (N is a natural number greater than or equal to 1). For example, the electronic device (100) may determine whether to acquire additional information (e.g., additional information (705) of FIG. 7) to be used to acquire an image (e.g., image (740) of FIG. 7) by providing the first prompt (500) that appears by the first user input to the first model (510). For example, the electronic device (100) may identify the information contained in the first prompt (500) by analyzing the first prompt (500). For example, the electronic device (100) may determine whether to acquire additional information to be used to generate an image (e.g., image (740) of FIG. 7) from among the set of information included in the first prompt (500). For example, the electronic device (100) may determine whether to acquire more information to be used to generate the image by providing the first prompt (500) to the first model (510). For example, the electronic device (100) may determine whether to acquire more information not included in the set of information included in the first prompt (500). For example, the electronic device (100) may determine whether to acquire more information to be used to synthesize the image (e.g., the image (740) of FIG. 7) by providing the first prompt (500) to the first model (510) for identifying information represented by text based on natural language, based on receiving the first user input.

[0055] For example, the first model (510) may be included within an electronic device (100). For example, the first model (510) may be described as a model trained to identify information not included in the text using text based on natural language. For example, the first model (510) may be described as a model trained by machine learning techniques (or deep learning techniques). For example, the first model (510) may be a language model. For example, the first model (510) may have a first complexity. For example, the language model (710) (e.g., the language model (710) of FIG. 7) may have a second complexity higher than the first complexity.

[0056] According to one embodiment, the electronic device (100) may acquire an image, acquire a video, or acquire music using a prompt acquired based on an input voice (e.g., input voice (522) of FIG. 5b). For example, the acquisition of at least one of an image, a video, and music is described and illustrated in more detail with reference to FIG. 5b.

[0057] FIG. 5b illustrates an exemplary operation of an electronic device that performs a function corresponding to user input using models.

[0058] Referring to FIG. 5b, the electronic device (100) may include at least one of a voice recognition unit (526), ​​a control unit (532), a conversation content analysis unit (530), and a first model (510). The electronic device (100) may include at least one of a language model (534), an image model (536), a video model (538), and a music model (540). However, it is not limited thereto. For example, an external electronic device (300) may include at least one of a language model (534), an image model (536), a video model (538), and a music model (540). For example, the electronic device (100) may receive data obtained from at least one of a language model (534), an image model (536), a video model (538), and a music model (540) from an external electronic device (300) through a communication circuit (205).

[0059] The electronic device (100) can acquire an input voice (522) through a microphone included in the electronic device (100) (or through a microphone included in the control device). The voice recognition unit (526) can acquire text (528) corresponding to the input voice (522) by performing voice recognition on the input voice (522).

[0060] The electronic device (100) can obtain input text (524) through an input mechanism (e.g., a keyboard or a control device). For example, each of the input text (524) and text (528) may be an example of a first prompt (500).

[0061] The control unit (532) may use a plurality of models (e.g., language model (534), image model (536), video model (538), music model (540)) to obtain at least one of an image, a video, and music based on at least one of text (528) and input text (524). For example, the control unit (532) may provide a prompt to the plurality of models or to the conversation content analysis unit (530).

[0062] The control unit (532) can determine whether to obtain additional information (e.g., additional information (705) of FIG. 7) using the first model (510). For example, the control unit (532) may include at least one processor (207) of FIG. 2. For example, the control unit (532) may control the display (208) to display a UI (e.g., UI (612) of FIG. 6) for obtaining the additional information based on the first model (510).

[0063] The conversation content analysis unit (530) can augment, generate, or obtain a prompt using a language model (534) by analyzing at least one of the text (528) and the input text (524). For example, the language model (534) may be an example of a language model (e.g., the language model (710) of FIG. 7). For example, the language model (534) can obtain a second prompt (e.g., the second prompt (720) of FIG. 7) using a first prompt (500) based on at least one of the text (528) and the input text (524).

[0064] The image model (536) may be used to generate an image corresponding to the first user input based on the second prompt. The video model (538) may be used to generate a video corresponding to the second prompt based on the second prompt, according to user input for generating a video. The music model (540) may be used to generate music corresponding to the second prompt based on the second prompt, according to user input for generating music.

[0065] Referring again to FIG. 4, the electronic device (100) may, in operation 420, display a UI (e.g., UI of FIG. 6 (612)) for receiving a second user input for synthesizing an image (e.g., image of FIG. 7 (740)) through a display (208), based on a decision to further acquire information (e.g., additional information of FIG. 7 (705)) to be used for synthesizing an image (e.g., image of FIG. 7 (740)). The display of the UI is described and illustrated in more detail with reference to FIG. 6.

[0066] FIG. 6 illustrates an exemplary operation of an electronic device displaying a UI related to information.

[0067] Referring to FIG. 6, the state (610) can be described as a state in which the UI (612) is displayed. For example, the electronic device (100) may decide to obtain information about a model to be used to generate an image (e.g., image (740) of FIG. 7) by using the first prompt (500). For example, the electronic device (100) may display the UI (612) through the display (208) to obtain information about a model to be used to generate an image (e.g., second model (730) of FIG. 7) among the plurality of trained models. For example, the electronic device (100) may display the UI (612) to obtain information indicating a trained model to be selected from among the plurality of trained models that can be used to synthesize an image (e.g., image (740) of FIG. 7), and to which a second prompt (e.g., second prompt (720) of FIG. 7) is provided.

[0068] For example, the UI (612) may include one or more visual objects (e.g., visual object (615-1) to visual object (615-4)). For example, visual object (615-1) may correspond to a first model (e.g., Mid Journey) among a plurality of trained models that may be used to generate an image. For example, visual object (615-2) may correspond to a second model among a plurality of trained models that may be used to generate an image. For example, visual object (615-3) may correspond to a third model among a plurality of trained models that may be used to generate an image. For example, visual object (615-4) may correspond to a fourth model among a plurality of trained models that may be used to generate an image. For example, the electronic device (100) may display an exemplary result image (617) of the first model along with a visual object (615-1) through the display (208). For example, the electronic device (100) may display exemplary result images of each of the plurality of trained models along with one or more visual objects through the display (208).

[0069] According to one embodiment, the electronic device (100) can display text (or visual objects) indicating the cost of using the plurality of trained models together with the one or more visual objects through the display (208).

[0070] According to one embodiment, the electronic device (100) may display text (or visual objects) indicating a user's (e.g., user (120)) preference (e.g., 75%) for each of the plurality of trained models, along with the one or more visual objects, through a display (208). For example, the electronic device (100) may store data indicating a preference for each of the plurality of trained models in memory (206). For example, the electronic device (100) may update the data based on receiving a second user input for selecting one of the plurality of trained models when displaying the UI (612).

[0071] For example, when the electronic device (100) displays the UI (612), it may receive other user input for selecting at least one of one or more visual objects. For example, based on receiving the other user input, the electronic device (100) may use the at least one to acquire or generate an image (e.g., image (740) of FIG. 7). For example, when the electronic device (100) displays the UI (612), based on receiving the other user input, it may switch the state of the electronic device (100) from state (610) to state (620). However, it is not limited thereto.

[0072] A state (620) can be described as a state in which a UI (622) for obtaining information about the style of an image (e.g., image (740) of FIG. 7) is displayed through a display (208). For example, the electronic device (100) may decide to obtain more information about the style of the image using a first prompt (500). For example, the electronic device (100) may display a UI (622) (or UI object) for obtaining information about the style through a display (208) based on the decision to obtain more information about the style of the image. For example, the electronic device (100) may display a UI (622) to obtain information indicating the style of an image (e.g., image (740) of FIG. 7).

[0073] For example, the UI (622) may include one or more visual objects representing the style of the image. For example, a visual object (625-1) may correspond to a first style (e.g., digital art). For example, a visual object (625-2) may correspond to a second style (e.g., animation). For example, a visual object (622-3) may correspond to a third style (e.g., photography).

[0074] According to one embodiment, the one or more visual objects may be based on the first prompt (500). For example, the electronic device (100) may use the first prompt (500) to determine the type (e.g., landscape, person, object, animal, and surreal, etc.) of an image (e.g., image (740) of FIG. 7) to be obtained using the first prompt (500). For example, the electronic device (100) may identify the type of the image by analyzing the first prompt (500). For example, the electronic device (100) may determine or identify the type of the image by providing the first prompt (500) to a language model (e.g., language model (710) of FIG. 7). For example, the electronic device (100) may determine one or more visual objects included in the UI (622) based on the determined type. For example, the one or more visual objects may be mapped to the determined type. For example, the above one or more visual objects may represent preferred styles according to the determined type.

[0075] According to one embodiment, the electronic device (100) may display one or more visual objects representing preferred styles according to the type of image (e.g., image (740) of FIG. 7) identified by the first prompt (500). For example, the electronic device (100) may store data representing the preferred style in memory (206). For example, the electronic device (100) may update the data based on a second user input received for the UI (622). For example, the preferred style may be based on the number of times it has been selected by the user (120).

[0076] According to one embodiment, the electronic device (100) may receive other user input for selecting at least one of one or more visual objects representing the style of an image. For example, based on receiving the other user input, the electronic device (100) may acquire or generate an image represented by the selected style (e.g., image (740) of FIG. 7). Based on receiving the other user input, the electronic device (100) may switch the state of the electronic device (100) from state (620) to state (630).

[0077] A state (630) can be described as a state that displays a UI (632) for selecting a visual element to be included in an image (e.g., image (740) of FIG. 7). For example, the electronic device (100) may decide to obtain more information about the visual element to be included in the image using a first prompt (500). For example, the electronic device (100) may display the UI (632) through a display (208) based on the decision. For example, the electronic device (100) may display the UI (632) to obtain information indicating at least one visual element to be included in the image (e.g., image (740) of FIG. 7).

[0078] For example, the electronic device (100) can determine the visual elements to be included in the image by using the first prompt (500). For example, the electronic device (100) can determine the visual elements related to the words included in the first prompt (500) by analyzing the first prompt (500). For example, based on the determination, the electronic device (100) can display a UI (632) containing one or more visual objects corresponding to each of the visual elements included in the image through the display (208). For example, if the first prompt (500) is "create a beautiful beach," the visual object (635-1) may correspond to a visual element (e.g., a boat). For example, the visual object (635-2) may correspond to a visual element (e.g., a sunbed). For example, the visual object (635-3) may correspond to a visual element (e.g., sand). However, it is not limited thereto. For example, the electronic device (100) may display, through the display (208), a visual object corresponding to a visual element that is less relevant to the words included in the first prompt (500). For example, the visual object (635-4) may correspond to a visual element (e.g., a dragon). For example, the electronic device (100) may display a visual object corresponding to a word that is highly relevant to the words included in the first prompt (500) among the words included in the database. For example, the electronic device (100) may identify the relevantness by calculating the similarities between the embedding vectors of each word included in the database and the embedding vectors of each word included in the first prompt (500).For example, the electronic device (100) may determine one or more visual objects (e.g., visual object (615-1) to visual object (615-4)) to be included in a UI (e.g., UI (612)) based on similarities between embedding vectors appearing by the first prompt (500) and other embedding vectors included in a language model (e.g., language model (710) of FIG. 7). For example, the electronic device (100) may display, through the display (208), one or more visual objects each containing one or more second words, determined using embedding vectors corresponding to first words included in the first prompt (500), among embedding vectors corresponding to each word. For example, the electronic device (100) may identify embedding vectors corresponding to words appearing by the first prompt (500). However, it is not limited thereto. For example, the electronic device (100) can display a visual object corresponding to a visual element (e.g., dragon) for at least one of the words in a different database for a type different from the type of image (e.g., image (740) of FIG. 7) to be generated by the first prompt (500) through the display (208).

[0079] According to one embodiment, a state in which the state (610), state (620), and state (630) are sequentially switched has been described, but the embodiments of the present disclosure are not limited thereto. For example, state (630) may be a state prior to state (610) or state (620).

[0080] According to one embodiment, the electronic device (100) can determine information (e.g., additional information (705) of FIG. 7) without displaying a UI. For example, the electronic device (100) can obtain information related to an image (e.g., image (740) of FIG. 7) by using a first prompt (500). For example, the electronic device (100) can obtain the information mapped to said words by identifying the words that appear by the first prompt (500). For example, the electronic device (100) can determine a first model mapped to said word among a plurality of trained models that appear by the state (610) by identifying a word (e.g., beach) that appears by the first prompt (500). For example, as the electronic device (100) identifies a word (e.g., beach) appearing by the first prompt (500), it can determine a first style (e.g., digital-art) mapped to the word among a plurality of styles appearing by the state (620). For example, as the electronic device (100) identifies a word (e.g., beach) appearing by the first prompt (500), it can determine a first visual element (e.g., boat) mapped to the word among a plurality of visual elements appearing by the state (630).

[0081] According to one embodiment, when the electronic device (100) displays the UI (632), the electronic device (100) may receive user input for selecting at least one of a plurality of visual objects (635-1, 635-2, 635-3, 635-4). For example, the electronic device (100) may obtain a second prompt (e.g., a second prompt (720) of FIG. 7) for obtaining an image (e.g., an image (740) of FIG. 7) by using additional information (e.g., additional information (705) of FIG. 7) indicating the at least one. However, it is not limited thereto. For example, when the electronic device (100) displays the UI (632), it may refrain from, bypass, or block receiving user input for selecting at least one of the plurality of visual objects. For example, the electronic device (100) can acquire an image (e.g., the image (740) of FIG. 7) without the additional information representing at least one of the plurality of visual objects.

[0082] Referring again to FIG. 4, in operation 430, the electronic device (100) can generate or obtain a second prompt (e.g., the second prompt (720) of FIG. 7) by using the first prompt (500) and information (e.g., additional information (705) of FIG. 7) that appears by the second user input received through the UI (612). For example, the electronic device (100) can generate the second prompt (e.g., the second prompt (720) of FIG. 7) by combining the first prompt (500) and the information.

[0083] In operation 440, the electronic device (100) can use the second prompt to obtain an image corresponding to the first user input (e.g., the image (740) of FIG. 7). For example, the generation of the second prompt and the acquisition of the image are described and illustrated in more detail with reference to FIG. 7.

[0084] FIG. 7 illustrates an exemplary operation of an electronic device that generates a second prompt.

[0085] Referring to FIG. 7, the electronic device (100) can determine whether to acquire additional information to be used to generate an image (740) by using the first prompt (500). For example, the electronic device (100) can acquire additional information (705) through a UI displayed based on the above determination. For example, the electronic device (100) can acquire, augment, or generate a second prompt (720) by using the additional information (705) and the first prompt (500). For example, the electronic device (100) can acquire the second prompt (720) by providing the first prompt (500) and additional information (705) to the language model (710). For example, the electronic device (100) can acquire the second prompt (720) by combining or adding additional information (705) to the first prompt (500).

[0086] According to one embodiment, additional information (705) may include information regarding the aspect ratio of the display (208) of the electronic device (100). For example, the electronic device (100) may use the information regarding the aspect ratio of the display (208) to obtain an image (740) having the same aspect ratio as the display (208). For example, the electronic device (100) may display a UI to obtain information indicating the aspect ratio of the image (740). However, it is not limited thereto. For example, the electronic device (100) may identify the information within memory (206).

[0087] According to one embodiment, additional information (705) may include information about the point of view (POV) (or camera angle) of the image (740). For example, an electronic device (100) may acquire the image (740) of the POV by using information about the POV of the image (740).

[0088] For example, the electronic device (100) can generate an image (740) using a second prompt (720). For example, the electronic device (100) can generate an image (740) by providing the second prompt (720) to a second model (730). For example, the second prompt (720) can be described as a prompt augmented from the first prompt (500). For example, the second prompt (720) can be described as a prompt obtained (or augmented) by combining the first prompt (500) and additional information (705) obtained through the UI.

[0089] The second model (730) may be described as a model for generating an image representing the prompt based on the prompt. For example, the second model (730) may be referred to as an image model or an image generation model. For example, the second model (730) may be used to generate an image in which words appearing by the prompt are represented.

[0090] According to one embodiment, at least one of the first model (510), the language model (710), and the second model (730) may be a model trained through machine learning techniques. For example, the artificial intelligence system may be described as a computer system for implementing human-level intelligence, and as a system in which the machine learns, makes judgments, and improves its recognition rate as it is used. For example, the artificial intelligence technology may be composed of machine learning (or deep learning) techniques that use algorithms to classify (or learn) the features of input data on their own, and elemental technologies that use machine learning algorithms to describe functions such as cognition and judgment of the human brain. For example, the elemental technologies may include at least one of linguistic understanding technology for recognizing human language and / or characters, visual understanding technology for recognizing objects like human vision, reasoning and prediction technology for logically inferring and predicting by judging information, knowledge representation technology for processing human experience information into knowledge data, and motion control technology for controlling the movement of a robot. For example, linguistic understanding technology may be described as a technology for applying or processing based on recognizing human language and characters. For example, linguistic understanding technology may include natural language processing, machine translation, dialogue systems, question answering, and speech recognition (or speech synthesis). For example, visual understanding technology may be described as technology that processes objects by perceiving them like human vision. For example, visual understanding technology may include object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image enhancement. For example, inference and prediction technology may be described as technology that logically reason and predict by judging information. For example, inference and prediction technology may include knowledge or probability-based inference, optimization prediction, preference-based prediction, and recommendations.

[0091] According to one embodiment, when the electronic device (100) acquires a second prompt (720), it may add a hidden prompt (e.g., 4K, masterpieces, best quality). For example, the hidden prompt may be described as a prompt to improve the quality of the image (740) according to style (e.g., digital-art), type (e.g., landscape), and visual element (e.g., sand). For example, the electronic device (100) may refrain from displaying, bypass, or block the hidden prompt through the display (208). For example, when the electronic device (100) acquires the second prompt (720), it may add a hidden prompt mapped to at least one of the type of the image (740), the visual element contained in the image (740), and additional information (705) obtained by analyzing the first prompt (500). However, it is not limited thereto. For example, the hidden prompt may be obtained by a language model (710).

[0092] According to one embodiment, the electronic device (100) may add magic keywords when it obtains a second prompt (720). For example, the magic keywords may be described as keywords for loading a fine-tuned LoRA (Low-Rank Adaptation) model. For example, when the electronic device (100) obtains the second prompt (720), it may add magic keywords mapped to the style of the visual element and / or image (740) that appears by the first prompt (500). For example, the electronic device (100) may add magic keywords mapped to additional information (705) obtained through the UI. However, it is not limited thereto. For example, the magic keywords may be obtained by a language model (710).

[0093] According to one embodiment, the electronic device (100) may add a negative prompt when it obtains a second prompt (720). For example, the negative prompt may be described as a prompt that causes a model not to include visual elements in the image (740). For example, when the electronic device (100) obtains the second prompt (720), it may add a negative prompt mapped to at least one of the first prompt (500), additional information (705), and the style of the image (740). However, it is not limited thereto. For example, the negative prompt may be obtained by a language model (710).

[0094] According to one embodiment, an electronic device (100) may obtain a random prompt using a first prompt (500) and additional information (705). For example, the electronic device (100) may display an image obtained using the random prompt through a display (208). For example, a mode for displaying an image using the random prompt may be referred to as a serendipity mode. For example, the electronic device (100) may obtain the random prompt by randomly combining one of a plurality of trained models indicated by the state (610) of FIG. 6, one of a plurality of styles indicated by the state (620), the first prompt (500), and additional information (705). For example, the electronic device (100) may display an image based on the serendipity mode based on receiving user input indicating a specified word (or sentence) (e.g., "Generate any image" or "Generate a random image"). For example, the electronic device (100) can control the display (208) to display an image based on the serendipity mode based on not receiving user input for a specified period of time.

[0095] For example, the electronic device (100) can augment the first prompt (500) using additional information (705) identified through the UI (e.g., UI (612)). For example, the electronic device (100) can obtain the second prompt (720) by augmenting the first prompt (500) without generating an intermediate image using the first prompt (500). For example, the electronic device (100) can obtain the second prompt (720) using the first prompt (500) without generating an intermediate image by providing the first prompt (500) to the second model (730). For example, since the electronic device (100) does not generate the intermediate image, it can obtain the result image (e.g., image (740)) faster than when generating the intermediate image. For example, the operation of generating an image using a trained model (e.g., second model (730)) may take a considerable amount of time. For example, the first time required to augment a prompt based on the generated intermediate image after generating an intermediate image may be longer than the second time required to augment a second prompt (720) using the first prompt (500) without generating an intermediate image. For example, since the electronic device (100) displays a UI without generating an intermediate image, a result image (e.g., image (740)) can be obtained faster than when an intermediate image is generated.

[0096] For example, the electronic device (100) can display the acquired image (740) through the display (208) by providing the second prompt (720) to the second model (730). For example, the electronic device (100) can acquire a plurality of images including the image (740) by using the second prompt (720). For example, the display of the image is described and illustrated in more detail with reference to FIG. 8.

[0097] FIG. 8 illustrates an exemplary operation of an electronic device displaying an acquired image.

[0098] Referring to FIG. 8, the state (810) may be described as a state for displaying an image. For example, the electronic device (100) may display the image (740) through the display (208) based on acquiring the image (740). For example, the electronic device (100) may display the image (812), image (814), and image (816) through the display (208). For example, one of the image (812), image (814), and / or image (816) may be the image (740). However, it is not limited thereto. For example, the electronic device (100) may acquire a plurality of images including the image (740) by providing a second prompt (720) to the second model (730). For example, the electronic device (100) can display images (812), images (814), and images (816) through a display (208) based on acquiring the images.

[0099] For example, when the electronic device (100) displays images (812), images (814), and images (816), it may display executable objects (820) and executable objects (822). For example, the executable object (820) may be described as an object for displaying other images by providing a second prompt (720) to a second model (730). For example, the executable object (822) may be described as an object for receiving user input that indicates a prompt different from the first prompt (500).

[0100] For example, when displaying images (812), images (814), and images (816), the electronic device (100) may receive user input for selecting one of images (812), images (814), and images (816). For example, the electronic device (100) may perform feedback (or reinforcement learning) on ​​a second prompt (720) and / or images (740) based on receiving the user input for selecting said one. For example, the electronic device (100) may change or determine a prompt to be added when generating a prompt different from the second prompt (720) used to generate said one by analyzing visual elements included in said selected one. For example, the electronic device (100) may change or determine a prompt to be added when generating a prompt different from the second prompt (720) by analyzing an image that was not selected among images (812), images (814), and images (816). For example, the electronic device (100) can evaluate the image (740) by calculating the similarity between the text represented by the second prompt (720) and the image (740) obtained by the second prompt (720). For example, the electronic device (100) can change the weights of the second model (730) or train it to better represent the second prompt (720).

[0101] According to one embodiment, the electronic device (100) can acquire a video using a second prompt (720). For example, the electronic device (100) can acquire a prompt to be used to generate a video by providing the second prompt (720) to a language model (e.g., language model (710)). However, it is not limited thereto. For example, the electronic device (100) can acquire a prompt to be used to generate a video without the language model by converting the second prompt (720). For example, the electronic device (100) can acquire a video corresponding to the second prompt (720) by using the prompt to be used to generate the video. For example, the electronic device (100) can display the video through a display (208). However, it is not limited thereto. For example, the electronic device (100) can transmit the second prompt (720) to an external electronic device (300) through a communication circuit (205). For example, the external electronic device (300) can generate a prompt to be used to generate a video by providing a second prompt (720) to the language model. For example, the external electronic device (300) can obtain a video corresponding to the generated prompt by providing the generated prompt to a model trained to generate a video (e.g., a video model). For example, the external electronic device (300) can transmit the obtained video to the electronic device (100). For example, the electronic device (100) can receive the obtained video from the external electronic device (300) through a communication circuit (205).

[0102] According to one embodiment, the electronic device (100) can generate music (or audio) using the second prompt (720). For example, the electronic device (100) can generate music (or audio) corresponding to the second prompt (720) by providing the second prompt (720) to a music model. For example, the electronic device (100) can generate music (or audio) corresponding to the second prompt (720) by providing a prompt to be used to generate the video to a music model. However, it is not limited thereto. For example, the electronic device (100) can transmit the second prompt (720) to an external electronic device (300) through a communication circuit (205). For example, the external electronic device (300) can generate music corresponding to the second prompt (720) by providing the second prompt (720) to a music model. For example, the external electronic device (300) can transmit the generated music to the electronic device (100). For example, the electronic device (100) can receive the generated music from an external electronic device (300) through a communication circuit (205).

[0103] According to one embodiment, the electronic device (100) can retrieve music corresponding to the second prompt (720). For example, the electronic device (100) can obtain metadata describing music by using the second prompt (720). For example, the electronic device (100) can obtain metadata describing music by providing the second prompt (720) to a language model (710). For example, the electronic device (100) can identify metadata corresponding to the second prompt (720) among a set of metadata describing music by comparing the metadata with the prompt to be used to generate the video.

[0104] Operations within an electronic device (100) including a language model (710) and a second model (730) have been described above, but embodiments are not limited thereto. For example, the language model (710) and / or the second model (730) may be included in an external electronic device (300). For example, a first external electronic device including the language model (710) may differ from a second external electronic device including the second model (730). For example, the first external electronic device may obtain a second prompt (720) by providing additional information (705) and a first prompt (500) to the language model (710). For example, the first external electronic device may transmit a signal indicating the second prompt (720) to the second external electronic device. For example, the second external electronic device may receive a signal indicating the second prompt (720). For example, the second external electronic device may acquire an image (740) by providing a second prompt (720) to the second model (730). For example, the second external electronic device may transmit the image (740) to the electronic device (100). For example, the electronic device (100) may display the image (740) through the display (208) based on receiving the image (740). For example, the first external electronic device may be different from the second external electronic device. However, it is not limited thereto. For example, the first external electronic device may be the same as the second external electronic device.

[0105] According to one embodiment, an electronic device (100) may cause another electronic device including a display to display at least one of UI (612), UI (622), UI (632), image (812), image (814), and image (816) using a communication circuit (205). For example, the electronic device (100) may transmit at least one of UI (612), UI (622), UI (632), image (812), image (814), and image (816) to the other electronic device through the communication circuit (205). For example, the other electronic device may control a display included in the other electronic device to display the at least one based on receiving the at least one. For example, the electronic device (100) may transmit a signal to the other electronic device through the communication circuit (205) to cause the other electronic device to display the at least one.

[0106] According to one embodiment, the electronic device (100) may include a wired interface (e.g., DisplayPort (DP) or High-Definition Multimedia Interface (HDMI)). For example, the electronic device (100) may be connected to another electronic device (e.g., a set-top box) that includes a display through the wired interface. For example, the electronic device (100) may transmit at least one of a UI (612), a UI (622), a UI (632), an image (812), an image (814), and an image (816) to the other electronic device through the wired interface. For example, the other electronic device may control a display included in the other electronic device to display the at least one based on receiving the at least one. For example, the electronic device (100) may transmit a signal to the other electronic device through the wired interface that causes the other electronic device to display the at least one.

[0107] The electronic device (100) can receive data regarding the UI (612) from the external electronic device (300) via the communication circuit (205) to acquire an image (740). For example, the external electronic device (300) can generate an image (740) using additional information (705) acquired via the UI (612). For example, the operations of the electronic device (100) and the external electronic device (300) are described and illustrated in more detail with reference to FIG. 9.

[0108] FIG. 9 illustrates examples of operations performed within an electronic device and an external electronic device.

[0109] Referring to FIG. 9, in operation 910, the electronic device (100) can receive a first user input corresponding to a first prompt (500). For example, the electronic device (100) can receive a first user input indicating the first prompt (500). For example, the electronic device (100) can receive an audio signal indicating the first prompt (500) through a microphone (204). For example, the operation 910 can correspond to operation 410 of FIG. 4.

[0110] In operation 920, the electronic device (100) may determine whether to acquire additional information (705) corresponding to the synthesis of the image (740). For example, the electronic device (100) may determine whether to acquire additional information (705) to be used to synthesize the image (740) by using the first prompt (500). For example, the electronic device (100) may determine whether to acquire additional information (705) by providing the first prompt (500) to the first model (510). For example, the operation 920 may correspond to a part of operation 420 of FIG. 4.

[0111] In operation 925, the electronic device (100) may transmit a signal requesting the transmission of data for the UI (612) to the external electronic device (300) via the communication circuit (205) based on the decision to acquire additional information (705). For example, the electronic device (100) may transmit data indicating a first prompt (500) to the external electronic device (300) along with the signal. For example, the electronic device (100) may transmit a signal causing the external electronic device (300) to transmit data for the UI corresponding to the determined additional information (705) to the external electronic device (300) via the communication circuit (205) along with data indicating the first prompt (500). For example, the external electronic device (300) may receive the signal and the data from the electronic device (100) via the communication circuit (305).

[0112] In operation 930, the external electronic device (300) may generate data for displaying one or more visual objects related to additional information (705) based on receiving data representing the request and / or the first prompt (500). For example, the external electronic device (300) may generate data for displaying one or more visual objects related to additional information (705) by providing the first prompt (500) to the language model (710). For example, the external electronic device (300) may identify one or more words that are highly similar to the words represented by the first prompt (500) by providing the first prompt (500) to the language model (710). For example, the external electronic device (300) may generate data representing the one or more words. For example, an external electronic device (300) can identify one or more words with high similarity in a type different from the type of the first prompt (500) (e.g., landscape) (e.g., surreal) by providing the first prompt (500) to the language model (710). For example, the external electronic device (300) can generate data representing said one or more words. For example, the external electronic device (300) can identify one or more words that are highly similar or related to the first prompt (500) according to the type identified by the first prompt (500). However, it is not limited thereto. For example, the external electronic device (300) can identify one or more other words that are low similarity or less related to the first prompt (500).

[0113] In operation 935, an external electronic device (300) can transmit data for displaying one or more visual objects to an electronic device (100) through a communication circuit (305). For example, the electronic device (100) can receive said data from the external electronic device (300) through a communication circuit (205).

[0114] In operation 940, the electronic device (100) may display a UI related to receiving a second user input through the display (208). For example, the electronic device (100) may display a UI for receiving the second user input through the display (208) based on a decision to acquire more information to be used to synthesize an image (740). For example, the UI may include one or more visual objects that appear by data received from an external electronic device (300). For example, operation 940 may correspond to part of operation 420 of FIG. 4.

[0115] In operation 950, the electronic device (100) may receive a second user input when displaying the UI. For example, the electronic device (100) may receive a second user input for selecting at least one of the one or more visual objects included in the UI.

[0116] In operation 960, the electronic device (100) may generate a second prompt (720) based on receiving the second user input, using additional information (705) and the first prompt (500) that appear through the second user input. For example, the electronic device (100) may obtain the second prompt (720) by combining the first prompt (500) and the additional information (705). For example, the electronic device (100) may obtain the second prompt (720) by providing the first prompt (500) and the additional information (705) to the language model (710). Although the operation of the electronic device (100) generating the second prompt (720) has been described, the embodiments are not limited thereto. For example, the electronic device (100) may transmit another signal indicating additional information (705) that appears by a second user input to an external electronic device (300) through a communication circuit (205). For example, the external electronic device (300) may generate a second prompt (720) by providing the first prompt (500) and additional information (705) to the language model (710) based on receiving the other signal.

[0117] According to one embodiment, when the electronic device (100) generates a second prompt (720), it may add at least one of a hidden prompt, magic keywords, and a negative prompt.

[0118] In operation 965, the electronic device (100) may transmit another signal indicating a second prompt (720) to an external electronic device (300) through a communication circuit (205). For example, the external electronic device (300) may receive the other signal from the electronic device (100) through a communication circuit (305).

[0119] In operation 970, the external electronic device (300) can synthesize or generate an image (740) using the second prompt (720). For example, the external electronic device (300) can synthesize or generate an image (740) represented by the second prompt (720) by providing the second prompt (720) to the second model (730).

[0120] In operation 975, the external electronic device (300) can transmit other data representing the image (740) to the electronic device (100) through the communication circuit (305). For example, the electronic device (100) can receive other data representing the image (740) from the external electronic device (300) through the communication circuit (205).

[0121] In operation 980, the electronic device (100) may display an image (740) through a display (208) based on receiving the second user input. For example, the electronic device (100) may display an image (740) based on receiving the other data.

[0122] According to one embodiment, the electronic device (100) may perform operations 930 and 970. For example, the electronic device (100) may include a language model (710) and a second model (730). For example, the electronic device (100) may display a UI (e.g., UI (612)) for obtaining additional information (705) based on a decision to obtain additional information to be used to synthesize an image. For example, the electronic device (100) may use the language model (710) to generate data for displaying one or more visual objects related to the additional information (705) that are included in the UI. For example, the electronic device (100) may generate an image (740) by providing a second prompt (720) obtained using the first prompt (500) and additional information (705) to the second model (730) within the electronic device (100).

[0123] According to one embodiment, a first external electronic device including a language model (710) may be different from a second external electronic device including a second model (730). For example, with reference to FIG. 9, the operation of generating data for displaying one or more visual objects using the language model (710) in operation 930 and the operation of synthesizing an image (740) using the second model (730) in operation 970 are shown to be performed within the external electronic device (300), but the embodiment is not limited thereto. For example, the first external electronic device on which operation 930 is performed may be different from the second external electronic device on which operation 970 is performed.

[0124] FIG. 10 illustrates an exemplary operation of an external electronic device for synthesizing images. This method may be executed by the external electronic device (300) illustrated in FIG. 3 or by at least one processor (307) of the external electronic device (300). In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0125] Referring to FIG. 10, in operation 1010, an external electronic device (300) may generate data for displaying one or more visual objects based on receiving a signal representing a first prompt (500). For example, the electronic device (100) may transmit a signal representing the first prompt (500) to the external electronic device (300) through a communication circuit (205). For example, the signal may include data representing the first prompt (500). For example, the external electronic device (300) may generate data for displaying one or more visual objects by providing the first prompt (500) to a language model (710) based on receiving the signal. For example, the external electronic device (300) may generate the data by identifying words represented by the first prompt (500). For example, an external electronic device (300) can obtain data on one or more visual objects corresponding to other words highly related to the words by providing the words to a language model (710). For example, operation 1010 can correspond to operation 925 of FIG. 9.

[0126] In operation 1020, the external electronic device (300) may receive another signal representing at least one of the one or more visual objects corresponding to a user input received by the electronic device (100), based on transmitting the data. For example, the electronic device (100) may receive a second user input selecting at least one of the one or more visual objects when displaying a UI including the one or more visual objects. For example, the electronic device (100) may transmit the other signal representing the at least one to the external electronic device (300) via a communication circuit (205), based on receiving the second user input. For example, the external electronic device (300) may receive the other signal from the electronic device (100) via a communication circuit (305). For example, operation 1020 may correspond to operation 965 of FIG. 9.

[0127] In operation 1030, the external electronic device (300) can synthesize an image (740) using a second prompt (720) based on receiving the other signal. For example, the external electronic device (300) can generate or obtain the second prompt (720) by providing at least one word and a first prompt (500) represented by the at least one, based on receiving the other signal, to a language model (710). For example, the external electronic device (300) can synthesize or generate an image (740) by providing the second prompt (720) to a second model (730). For example, operation 1030 may correspond to operation 970 of FIG. 9.

[0128] In operation 1040, the external electronic device (300) can transmit the image (740) to the electronic device (100) through the communication circuit (305). For example, operation 1040 can correspond to operation 975 of FIG. 9.

[0129] FIG. 11 illustrates an exemplary electronic device and an exemplary external electronic device for acquiring an image according to various embodiments.

[0130] Referring to FIG. 11, the state (1110) may be described as a state illustrating an exemplary electronic device. For example, the electronic device (100) may be described as an electronic device including a display (208). For example, the electronic device (100) may display an image (740) through the display (208) based on receiving a first user input. For example, the electronic device (100) may include a communication circuit (205). However, it is not limited thereto. For example, the communication circuit (205) may be an optional hardware component. For example, the electronic device (100) may include a television (1112). For example, the electronic device (100) may include a personal computer (PC) (1114). For example, the electronic device (100) may include a smartphone (1116). For example, the electronic device (100) may include a projector (1118).

[0131] The state (1120) may be described as a state illustrating an exemplary external electronic device. For example, the external electronic device (300) may include a server (1122). For example, the external electronic device (300) may be described as an electronic device for acquiring an image (740) using a first prompt (500) and additional information (705) received from the electronic device (100). For example, the electronic device (100) and the external electronic device (300) are depicted as distinct, but the embodiments are not limited thereto. For example, the electronic device (100) may be identical to the external electronic device (300).

[0132] 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.

[0133] An electronic device as described above (e.g., electronic device (100)) may include a memory (e.g., memory (206)) for storing instructions. The electronic device may include a display (e.g., display (208)). The electronic device may include at least one processor (e.g., at least one processor (207)). The instructions may cause the electronic device to receive a first user input corresponding to a first prompt (500) for synthesizing an image when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to control the display (208) to display a UI (612) (user interface) related to receiving a second user input corresponding to the synthesis of an image, based on determining to acquire additional information (705) corresponding to the synthesis of the image based on the first prompt (500) before synthesizing the image when executed individually or collectively by the at least one processor. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to obtain a second prompt (720) using the additional information (705) according to the first prompt (500) and the second user input received through the UI. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to obtain an image corresponding to the first user input based on the second prompt (720).

[0134] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to identify whether to further acquire additional information (705) corresponding to the synthesis of the image through an artificial intelligence model trained to identify additional information (705) corresponding to text based on natural language, based on the first prompt (500), upon receiving the first user input.

[0135] According to one embodiment, the UI (612) may include one or more visual objects related to the additional information (705), which are obtained through an artificial intelligence model based on the first prompt (500).

[0136] According to one embodiment, the additional information (705) may be information corresponding to an artificial intelligence model that provides an image corresponding to the first user input based on the second prompt (720), among a plurality of trained artificial intelligence models corresponding to the synthesis of images.

[0137] According to one embodiment, the additional information (705) may include at least one of the style of the image, at least one visual element to be included in the image, and the aspect ratio of the image.

[0138] According to one embodiment, the UI (612) may include one or more visual objects related to the additional information (705). The one or more visual objects may each include one or more second words obtained based on the embedding vectors corresponding to the first words included in the first prompt (500), among the embedding vectors corresponding to the words.

[0139] According to one embodiment, the electronic device may further include a communication circuit. The instructions may cause the electronic device to transmit a request for data corresponding to one or more visual objects included in the UI (612) and associated with the additional information (705), based on determining to further acquire the additional information (705) corresponding to the synthesis of the image when executed individually or collectively by the at least one processor, to transmit to a first external electronic device through the communication circuit. The instructions may cause the electronic device to control the display (208) to display the UI (612) including the one or more visual objects based on the data received from the first external electronic device through the communication circuit when executed individually or collectively by the at least one processor. When the above instructions are executed individually or collectively by the at least one processor, they may cause the electronic device to transmit data corresponding to the second prompt (720) based on the additional information (705) according to the second user input received through the UI to the second external electronic device through the communication circuit. When the above instructions are executed individually or collectively by the at least one processor, they may cause the electronic device to receive an image corresponding to the second prompt (720) from the second external electronic device through the communication circuit based on the data corresponding to the second prompt (720).

[0140] According to one embodiment, the electronic device may further include a microphone. The first user input may be received through the microphone.

[0141] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to acquire a third prompt corresponding to the second prompt through a first artificial intelligence model trained to generate a prompt corresponding to the acquisition of a video based on the second prompt. When the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to acquire a video corresponding to the third prompt through a second artificial intelligence model trained to generate a video corresponding to the prompt.

[0142] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to acquire audio corresponding to the second prompt through an artificial intelligence model trained to generate audio corresponding to the prompt.

[0143] According to one embodiment, the instructions may cause the electronic device to acquire a plurality of images corresponding to the first user input based on the second prompt when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to receive a third user input corresponding to the selection of one of the plurality of images based on displaying the plurality of images through the display when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to train an artificial intelligence model used to acquire the plurality of images based on the third user input when executed individually or collectively by the at least one processor.

[0144] A method performed by an electronic device (e.g., electronic device (100)) having a display (e.g., display (208)) as described above may include an operation of receiving a first user input corresponding to a first prompt (500) for synthesizing an image. The method may include an operation of controlling the display (208) to display a UI (612) (user interface) related to receiving a second user input corresponding to the synthesis of the image, based on determining to further acquire additional information (705) corresponding to the synthesis of the image based on the first prompt (500) before synthesizing the image. The method may include an operation of acquiring a second prompt (720) using the additional information (705) corresponding to the second user input received through the first prompt (500) and the UI. The method may include an operation of acquiring an image corresponding to the first user input based on the second prompt (720).

[0145] According to one embodiment, the method may include an operation of determining whether to further acquire additional information (705) corresponding to the synthesis of the image through an artificial intelligence model trained to identify additional information (705) corresponding to text based on natural language, based on the first prompt (500), upon receiving the first user input.

[0146] According to one embodiment, the UI (612) may include one or more visual objects related to the additional information (705), which are obtained through an artificial intelligence model based on the first prompt (500).

[0147] According to one embodiment, the additional information (705) may be information corresponding to an artificial intelligence model that provides an image corresponding to the first user input based on the second prompt (720), among a plurality of trained artificial intelligence models corresponding to the synthesis of images.

[0148] According to one embodiment, the additional information (705) may include at least one of the style of the image, at least one visual element to be included in the image, and the aspect ratio of the image.

[0149] According to one embodiment, the UI (612) may include one or more visual objects related to the additional information (705). The one or more visual objects may each include one or more second words obtained based on the embedding vectors corresponding to the first words included in the first prompt (500), among the embedding vectors corresponding to the words.

[0150] According to one embodiment, the electronic device may further include a communication circuit. The method may include an operation of transmitting a request for data corresponding to one or more visual objects included in the UI (612) and associated with the additional information (705), based on determining to further acquire the additional information (705) corresponding to the synthesis of the image, to a first external electronic device through the communication circuit. The method may include an operation of controlling the display (208) to display the UI (612) including the one or more visual objects based on the data when the data is received from the first external electronic device through the communication circuit. The method may include an operation of transmitting data corresponding to the second prompt (720) based on the additional information (705) according to the second user input received through the UI to a second external electronic device through the communication circuit. The above method may include the operation of receiving an image corresponding to the second prompt (720) from the second external electronic device through the communication circuit, based on data corresponding to the second prompt (720).

[0151] According to one embodiment, the electronic device may further include a microphone. The first user input may be received through the microphone.

[0152] According to one embodiment, the method may include an operation of displaying the image through the display based on acquiring the image.

[0153] According to one embodiment, the method may include an operation of acquiring a third prompt corresponding to the second prompt through a first artificial intelligence model trained to generate a prompt corresponding to the acquisition of a video based on the second prompt. The method may include an operation of acquiring a video corresponding to the third prompt through a second artificial intelligence model trained to generate a video corresponding to the prompt.

[0154] According to one embodiment, the method may include the operation of obtaining audio corresponding to the second prompt through an artificial intelligence model trained to generate audio corresponding to the prompt.

[0155] According to one embodiment, the method may include an operation of acquiring a plurality of images corresponding to the first user input based on the second prompt. The method may include an operation of receiving a third user input corresponding to the selection of one of the plurality of images based on displaying the plurality of images through the display. The method may include an operation of training an artificial intelligence model used to acquire the plurality of images based on the third user input.

[0156] In a computer-readable storage medium in which one or more programs are stored as described above, the one or more programs may include instructions that cause the electronic device (e.g., electronic device (100)) having a display (e.g., display (208)) to receive a first user input corresponding to a first prompt (500) for synthesizing an image when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to control the display (208) to display a UI (612) (user interface) related to receiving a second user input corresponding to the synthesis of an image, based on determining to acquire additional information (705) corresponding to the synthesis of the image based on the first prompt (500) before synthesizing the image when executed by the electronic device. The above one or more programs may include instructions that cause the electronic device to obtain a second prompt (720) by using the additional information (705) according to the first prompt (500) and the second user input received through the UI when executed by the electronic device. The above one or more programs may include instructions that cause the electronic device to obtain an image corresponding to the first user input based on the second prompt (720) when executed by the electronic device.

[0157] According to one embodiment, the one or more programs may include instructions that cause the electronic device to identify whether to further acquire additional information (705) corresponding to the synthesis of the image through an artificial intelligence model trained to identify additional information (705) corresponding to text based on natural language, based on the first prompt (500), upon receiving the first user input when executed by the electronic device.

[0158] According to one embodiment, the UI (612) may include one or more visual objects related to the additional information (705), which are obtained through an artificial intelligence model based on the first prompt (500).

[0159] According to one embodiment, the additional information (705) may be information corresponding to an artificial intelligence model that provides an image corresponding to the first user input based on the second prompt (720), among a plurality of trained artificial intelligence models corresponding to the synthesis of images.

[0160] According to one embodiment, the additional information (705) may include at least one of the style of the image, at least one visual element to be included in the image, and the aspect ratio of the image.

[0161] According to one embodiment, the UI (612) may include one or more visual objects related to the additional information (705). The one or more visual objects may each include one or more second words obtained based on the embedding vectors corresponding to the first words included in the first prompt (500), among the embedding vectors corresponding to the words.

[0162] According to one embodiment, the electronic device may further include a communication circuit. The one or more programs may include instructions that cause the electronic device to transmit a request for data corresponding to one or more visual objects included in the UI (612) and associated with the additional information (705), based on determining to further acquire the additional information (705) corresponding to the synthesis of the image when executed by the electronic device, to a first external electronic device through the communication circuit. The one or more programs may include instructions that cause the electronic device to control the display (208) to display the UI (612) including the one or more visual objects based on the data received from the first external electronic device through the communication circuit when executed by the electronic device. The above one or more programs may include instructions that cause the electronic device to transmit data corresponding to the second prompt (720) based on the additional information (705) according to the second user input received through the UI, to the second external electronic device through the communication circuit when executed by the electronic device. The above one or more programs may include instructions that cause the electronic device to receive an image corresponding to the second prompt (720) from the second external electronic device through the communication circuit, based on the data corresponding to the second prompt (720), when executed by the electronic device.

[0163] According to one embodiment, the electronic device may further include a microphone. The first user input may be received through the microphone.

[0164] According to one embodiment, the one or more programs may include instructions that cause the electronic device to display the image through the display based on acquiring the image when executed by the electronic device.

[0165] According to one embodiment, the one or more programs may include instructions that cause the electronic device to obtain a third prompt corresponding to the second prompt through a first artificial intelligence model trained to generate a prompt corresponding to the acquisition of a video based on the second prompt when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to obtain a video corresponding to the third prompt through a second artificial intelligence model trained to generate a video corresponding to the prompt when executed by the electronic device.

[0166] According to one embodiment, the one or more programs may include instructions that cause the electronic device to obtain audio corresponding to the second prompt through an artificial intelligence model trained to generate audio corresponding to the prompt when executed by the electronic device.

[0167] According to one embodiment, the one or more programs may include instructions that cause the electronic device to acquire a plurality of images corresponding to the first user input based on the second prompt when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to receive a third user input corresponding to the selection of one of the plurality of images based on displaying the plurality of images through the display when executed by the electronic device. The one or more programs may include instructions that cause the electronic device to train an artificial intelligence model used to acquire the plurality of images based on the third user input when executed by the electronic device.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] Therefore, other implementations, other embodiments, and equivalents to the claims set forth below are also within the scope of the claims. According to one embodiment, the method according to the various embodiments disclosed herein may be provided as 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 in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0174] 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.

Claims

1. In an electronic device, display; Memory comprising one or more storage media for storing instructions; and It includes at least one processor comprising processing circuitry, and When the above instructions are executed individually or collectively by the at least one processor, Receiving a first user input corresponding to a first prompt for synthesizing an image, and Before synthesizing the above image, the display is controlled to display a UI (user interface) related to receiving a second user input corresponding to the synthesis of the image, based on determining to acquire additional information corresponding to the synthesis of the above image based on the first prompt, and Using the additional information based on the second user input received through the first prompt and the UI, a second prompt is obtained, and Based on the second prompt above, to obtain an image corresponding to the first user input, causing the above electronic device, Electronic device.

2. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, Upon receiving the first user input, based on the first prompt, to identify whether to further acquire additional information corresponding to the synthesis of the image through an artificial intelligence model trained to identify additional information corresponding to text based on natural language, causing the above electronic device, Electronic device.

3. In claim 1, the UI is, Based on the first prompt above, one or more visual objects obtained through an artificial intelligence model and related to the additional information, comprising Electronic device.

4. In Claim 1, the additional information is, Among a plurality of trained artificial intelligence models corresponding to image synthesis, information corresponding to an artificial intelligence model that provides an image corresponding to the first user input based on the second prompt, Electronic device.

5. In Claim 1, the additional information is, at least one of the style of the image, at least one visual element to be included in the image, and at least one of the aspect ratio of the image, Electronic device.

6. In claim 1, the UI is, Includes one or more visual objects related to the above additional information, and The above one or more visual objects are, Among the embedding vectors corresponding to each word, each comprising one or more second words obtained based on the embedding vectors corresponding to the first words included in the first prompt. Electronic device.

7. In claim 1, the electronic device is, It further includes a communication circuit, When the above instructions are executed individually or collectively by the at least one processor, Based on determining to further acquire the additional information corresponding to the synthesis of the above image, a request for data corresponding to one or more visual objects included in the UI, which is related to the additional information, is transmitted to a first external electronic device through the communication circuit, and When the above data is received from the first external electronic device through the communication circuit, the display is controlled to display the UI including the one or more visual objects based on the data, and Data corresponding to the second prompt based on the additional information according to the second user input received through the UI is transmitted to a second external electronic device through the communication circuit, and Based on data corresponding to the second prompt, to receive an image corresponding to the second prompt from the second external electronic device through the communication circuit. causing the above electronic device, Electronic device.

8. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, Based on the second prompt above, a third prompt corresponding to the second prompt is obtained through a first artificial intelligence model trained to generate a prompt corresponding to the acquisition of a video, and In order to obtain a video corresponding to the third prompt through a second artificial intelligence model trained to generate a video corresponding to the prompt, causing the above electronic device, Electronic device.

9. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, To obtain audio corresponding to the second prompt through an artificial intelligence model trained to generate audio corresponding to the prompt, causing the above electronic device, Electronic device.

10. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, Based on the second prompt above, a plurality of images corresponding to the first user input are obtained, and Based on displaying the plurality of images through the display, receiving a third user input corresponding to the selection of one of the plurality of images, and Based on the above third user input, to train an artificial intelligence model used to acquire the plurality of images, causing the above electronic device, Electronic device.

11. A method executed within an electronic device including a display, The operation of receiving a first user input corresponding to a first prompt for synthesizing an image, and Before synthesizing the above image, the operation of controlling the display to display a UI (user interface) related to receiving a second user input corresponding to the synthesis of the image, based on determining to acquire additional information corresponding to the synthesis of the above image based on the first prompt, and The operation of obtaining a second prompt using the additional information according to the second user input received through the first prompt and the UI, and Based on the second prompt above, the operation of acquiring an image corresponding to the first user input, method.

12. In Claim 11, A method comprising, upon receiving the first user input, identifying whether to further acquire additional information corresponding to the synthesis of the image through an artificial intelligence model trained to identify additional information corresponding to natural language-based text based on the first prompt, method.

13. In claim 11, the UI is, Based on the first prompt above, one or more visual objects obtained through an artificial intelligence model and related to the additional information, comprising method.

14. In claim 11, the additional information is, Among a plurality of trained artificial intelligence models corresponding to image synthesis, information corresponding to an artificial intelligence model that provides an image corresponding to the first user input based on the second prompt, method.

15. In claim 11, the additional information is, at least one of the style of the image, at least one visual element to be included in the image, and at least one of the aspect ratio of the image, method.

Images