An image searching and generating method, device, equipment and medium

Abstract

This application discloses an image search and generation method, apparatus, device, and medium, relating to the field of image search technology. The method includes: responding to a search request, performing an image search operation and an image generation operation in parallel based on image description information in the search request; upon receiving the search result of the image search operation, displaying a first image from the search results on a graphical user interface; and upon receiving the generation result of the image generation operation, displaying a second image from the generation result on a graphical user interface. This technical solution, by performing image search and generation operations in parallel and displaying the corresponding images upon receiving the results of the two operations respectively, allows users to view images close to their expectations obtained through the image generation operation, and also to browse searched images while waiting for image generation, greatly improving the user experience when searching for desired images.

Description

Technical Field

[0001] This invention relates to the field of image search technology, and in particular to a method, apparatus, device, and medium for searching and generating images. Background Technology

[0002] When searching for desired images, users can either search for them using keywords on image resource websites, or input prompts into AI (Artificial Intelligence) image generation software to generate images using AI.

[0003] Images found through image search may not match the user's expectations; AI-generated images are time-consuming, requiring users to wait a long time. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and medium for searching and generating images, which can perform image search and generation operations in parallel, and can quickly provide image search results and generate images as desired by the user.

[0005] According to one aspect of the present invention, an image search and generation method is provided, the method comprising: In response to an image search request, based on the image description information in the image search request, image search operations and image generation operations are performed in parallel. When the search result of the image search operation is received, the first image in the search result is displayed in the graphical user interface. When the generation result of the image generation operation is received, the second image in the generation result is displayed in the graphical user interface.

[0006] According to another aspect of the present invention, an image search and generation apparatus is provided, comprising: The image search and generation module is used to respond to an image search request and, based on the image description information in the image search request, perform image search operations and image generation operations in parallel. An image display module is configured to display a first image from the search results received from the image search operation on a graphical user interface, and to display a second image from the generation result received from the image generation operation on a graphical user interface.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the image search and generation method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the image search and generation method according to any embodiment of the present invention.

[0009] The technical solution of this application embodiment includes: responding to an image search request, performing an image search operation and an image generation operation in parallel based on the image description information in the image search request; upon receiving the search result of the image search operation, displaying a first image from the search result in a graphical user interface; and upon receiving the generation result of the image generation operation, displaying a second image from the generation result in a graphical user interface. This technical solution, by performing the image search and generation operations in parallel and displaying the corresponding images upon receiving the results of the two operations respectively, allows users to view images close to their expectations obtained through the image generation operation, and also to browse searched images while waiting for image generation, greatly improving the user experience when searching for desired images.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of an image search and generation method provided according to Embodiment 1 of this application; Figure 2 This is a flowchart of an image search and generation method provided according to Embodiment 2 of this application; Figure 3 This is a schematic diagram of an input box and a target control for image description information in a graphical user interface according to Embodiment 2 of this application; Figure 4This is a schematic diagram showing a first image and a second image according to Embodiment 2 of this application; Figure 5 This is a schematic diagram of a switching control corresponding to a workflow model provided in Embodiment 2 of this application; Figure 6 This is a schematic diagram of a switching control corresponding to a pre-trained image generation model provided in Embodiment 2 of this application; Figure 7 This is a schematic diagram of the structure of an image search and generation device according to Embodiment 3 of this application; Figure 8 This is a schematic diagram of the structure of an electronic device that implements an image search and generation method according to an embodiment of this application. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] Example 1 Figure 1 This document provides a flowchart of an image search and generation method according to Embodiment 1 of this application. This embodiment is applicable to image searching. The method can be executed by an image search and generation device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes: S110, in response to the image search request, based on the image description information in the image search request, perform the image search operation and the image generation operation in parallel.

[0016] In this embodiment, the image search request refers to the request to find the image required by the user. For an image search request, the image search operation and the image generation operation are performed in parallel, that is, the image required by the user is returned in two ways. The image search operation refers to the operation of searching for an image that matches the image description information in the image library (which includes, but is not limited to, images within the site, images from external websites, images uploaded by third parties or users, etc.). The image generation operation refers to the operation of generating an image that matches the image description information through algorithms, models (such as image generation models).

[0017] In an optional embodiment, in response to an image search request, an image search operation and an image generation operation are performed in parallel based on the image description information in the image search request, including: if a trigger operation of an image search control in a graphical user interface is detected, obtaining the image description information input by the user in the graphical user interface, and performing the image search operation and the image generation operation in parallel based on the image description information.

[0018] In another optional embodiment, in response to an image search request, an image search operation and an image generation operation are performed in parallel based on the image description information in the image search request, including: in response to a voice command for image search, determining the image description information based on the voice content, and performing the image search operation and the image generation operation in parallel based on the image description information.

[0019] Obviously, there are many ways to initiate an image search request. The methods mentioned above, such as clicking controls in the graphical user interface and issuing commands via voice, are just two specific examples. Other methods will not be elaborated on.

[0020] This solution responds to image search requests by performing image search and image generation operations in parallel. Compared to initiating image search and image generation requests separately on two platforms, this greatly reduces the number of steps users need to take between different platforms, such as clicking and jumping, thus improving the user experience.

[0021] S120: When the search result of the image search operation is received, the first image in the search result is displayed in the graphical user interface; when the generation result of the image generation operation is received, the second image in the generation result is displayed in the graphical user interface.

[0022] The first image may be at least one image from the search results; the second image may be at least one image from the generated results.

[0023] Specifically, when performing image search and image generation operations in parallel, the execution times of the two operations may differ. For example, the execution time of the image search operation may be shorter than that of the image generation operation. In this case, when the image search operation returns a search result, the first image from the search result can be displayed in the graphical user interface (GUI). Only after the image generation operation returns a generation result can the second image from the generation result be displayed in the GUI. Similarly, if the image generation operation returns a generation result first, the second image from the generation result is displayed in the GUI; until the image search operation returns a search result, the first image from the search result is displayed in the GUI. Furthermore, if the image generation operation returns a generation result and the image search operation returns a search result simultaneously, both the first and second images are displayed in the GUI.

[0024] In a specific example, when a user searches for a desired image, the image description information of the desired image can be obtained, and the image search and generation operations can be performed in parallel. Since the image search operation usually has a short execution time, the image search operation returns the search results before the image generation operation. The first image in the search results can be displayed in the graphical user interface until the image generation operation returns the generated result. The first image and the second image are then displayed in the graphical user interface. This setting allows the user to browse the first image in the search results while waiting for the image to be generated, avoiding the poor user experience caused by excessively long image generation time. In addition, since the second image, which is close to the user's expectation, is displayed after the first image in the search results, the problem of not being able to find the desired image when searching for images is solved. Furthermore, compared with the method of users searching for and generating images separately on different products, this technical solution also solves the problem of the cumbersome operation caused by users constantly switching platforms to perform corresponding operations, greatly improving the user experience when searching for desired images.

[0025] The technical solution of this application embodiment includes: responding to an image search request, performing an image search operation and an image generation operation in parallel based on the image description information in the image search request; upon receiving the search result of the image search operation, displaying a first image from the search result in a graphical user interface; and upon receiving the generation result of the image generation operation, displaying a second image from the generation result in a graphical user interface. This technical solution, by performing the image search and generation operations in parallel and displaying the corresponding images upon receiving the results of the two operations respectively, allows users to view images close to their expectations obtained through the image generation operation, and also to browse searched images while waiting for image generation, greatly improving the user experience when searching for desired images.

[0026] Example 2 Figure 2 This is a flowchart of an image search and generation method provided in Embodiment 2 of this application. This embodiment is an optimization based on the above embodiment.

[0027] like Figure 2 As shown, the method in this embodiment of the application specifically includes the following steps: S210, in response to the image search request, based on the image description information in the image search request, the image search operation and the image generation operation are performed in parallel.

[0028] In this embodiment of the application, optionally, in response to an image search request, an image search operation and an image generation operation are performed in parallel based on the image description information in the image search request, including: displaying an input box for inputting image search content in a graphical user interface to obtain the image description information input into the input box; and in response to an image search request for the image description information in the input box, performing an image search operation and an image generation operation in parallel based on the image description information.

[0029] Specifically, an input box for image search can be displayed in the graphical user interface. This input box can display prompts such as "Please enter keywords / prompts" to allow the user to enter image description information. If the control for the image search request is triggered or the target key (Enter key) on the keyboard is triggered, the image search operation and the image generation operation are performed in parallel based on the image description information.

[0030] This solution allows users to initiate image search and image generation requests by entering image description information only once. Compared to the previous method where users had to enter image description information twice on different platforms to search for and generate images separately, this solution significantly reduces the user's operational costs.

[0031] Optionally, in this embodiment of the application, the method further includes: displaying a target control in a graphical user interface; the target control is a control that initiates an image search request; correspondingly, the step of responding to the image search request and performing image search operation and image generation operation in parallel based on the image description information in the image search request includes: responding to the triggering operation of the target control, determining image description information for image search, and performing image search operation and image generation operation in parallel based on the image description information.

[0032] For example, when displaying an input box for image description information in the graphical user interface, a target control can also be displayed. This target control is the control that initiates the image search request. For example, the target control can display words or symbols such as "Search," "Find," "Search and Generate," or "Search Symbol" to indicate that the target control is the control that initiates the image search request. Furthermore, if a trigger operation of the target control is detected, the image description information in the input box is obtained, and then, based on the image description information, the image search operation and the image generation operation are performed in parallel.

[0033] This solution is designed so that users only need to click on the target control once to initiate an image search request, without having to initiate separate image search and image generation requests, thus reducing the user's operational costs.

[0034] Figure 3 This is a schematic diagram of an input box and a target control for an image description information graphical user interface; the input box displays the words "Please enter keywords / prompt words"; the target control displays a search symbol.

[0035] In this embodiment of the application, optionally, performing an image generation operation based on the image description information includes: determining a target workflow model that matches the image description information from among pre-established workflow models; the workflow model is a model with a pre-configured image generation process; and processing the image description information based on the target workflow model to generate an image that matches the image description information.

[0036] For example, models used to perform image generation operations typically fall into two categories: workflow models and general-purpose models. Workflow models are pre-configured image generation processes; for instance, users can configure the steps in the image generation process to obtain a workflow model. Workflow models can be models developed for specific application scenarios (such as "anime," "traditional Chinese style," or "clothing embroidery"). General-purpose models are pre-trained image generation models. These pre-trained models are obtained by continuously adjusting the model parameters during training, and typically do not have limitations on their application scenarios.

[0037] Specifically, multiple workflow models can be developed in advance. When performing image generation operations based on the image description information, the image description information can be parsed and processed by a large language model (a model that can understand semantics) to determine the degree of matching between the image description information and the pre-developed workflow model. The workflow model that matches the pre-developed workflow model is determined as the target workflow model. Then, the image description information is processed based on the target workflow model to generate an image that matches the image description information.

[0038] This solution generates images by matching the target workflow model with the image description information, making the generated images more closely match the image description information and more in line with the user's expectations.

[0039] Optionally, in this embodiment of the application, the method further includes: if the pre-established workflow model does not meet the matching conditions with the image description information, then processing the image description information based on the pre-trained image generation model to generate an image that matches the image description information.

[0040] For example, if none of the pre-established workflow models meet the matching conditions with the image description information, the image description information can be processed by a pre-trained image generation model. By leveraging the wide applicability of the pre-trained image generation model, an image that matches the image description information can be generated.

[0041] In this embodiment of the application, optionally, the image generation operation based on the image description information includes: processing the image description information based on a pre-trained image generation model and the workflow model respectively, to generate an image that matches the image description information. This scheme allows for image generation operations using two different image generation models. When the user views the second image in the generated results in subsequent steps, they can view images generated by both models, thus expanding the user's options.

[0042] S220, when the search result of the image search operation is received, the first image in the search result is displayed in the first area of ​​the graphical user interface, and the execution status of the image generation operation is displayed in the second area of ​​the graphical user interface.

[0043] The first and second regions can be preset; for example, the area of ​​the first region is larger than that of the second region, and the first region is located above the second region. This setting allows users to browse the first image in the first region from top to bottom. As the user browses, the image is being generated, and when the user browses to the second region, the second image may have already been generated, thus greatly improving the user's browsing experience.

[0044] For example, if the search results of the image search operation are received first, the first image in the search results is displayed in the first area of ​​the graphical user interface. At this time, the image generation operation is still in the process of generating the image. The execution status of the image generation operation can be displayed in the second area of ​​the graphical user interface. This setting allows users to browse the searched images first, which greatly improves the user's browsing experience compared to not displaying other content when generating images.

[0045] S230, until the generation result of the image generation operation is received, the second image in the generation result is displayed in the second area.

[0046] For example, after receiving the generation result of the image generation operation, the second image in the generation result is displayed in the second area. At this time, in the graphical user interface, the first image is displayed in the first area and the second image is displayed in the second area. The user can perform an image swiping operation in the first area to view more first images. The user can also perform an image swiping operation in the second area to view more second images. This solution greatly improves the user's image browsing experience.

[0047] Figure 4 This is a schematic diagram showing a first image and a second image; in Figure 4 In the image description, the character is described as wearing an ancient-style white dress; the generated second image is displayed on top of the first image found in the search.

[0048] In an embodiment of the present application, optionally, when displaying the second image in the generated result, the method further includes: displaying a switching control corresponding to the target image generation model; the target image generation model is an image generation model that is inconsistent with the current image generation model; the target image generation model is: a workflow model or a pre-trained image generation model; the workflow model is a model that pre-configures an image generation process; in response to a trigger operation of the switching control, displaying an image generated based on the target image generation model.

[0049] Exemplarily, if the currently displayed second image is an image generated by a workflow model, the switching control is a control corresponding to a pre-trained image generation model. If it is detected that the switching control has been triggered, the original second image is switched to a second image generated by the pre-trained image generation model. Similarly, if the currently displayed second image is an image generated by a pre-trained image generation model, the switching control is a control corresponding to the workflow model. If it is detected that the switching control has been triggered, the original second image is switched to a second image generated by the workflow model.

[0050] With this setting of the present solution, users can switch and view images generated by a workflow model and images generated by a pre-trained image generation model on the graphical user interface, and select pictures that are more in line with expectations.

[0051] Exemplarily, Figure 5 It is a schematic diagram of a switching control corresponding to a workflow model. There is a "work" character mark displayed inside the control to indicate that after triggering the control, a second image generated by the workflow model is displayed. Figure 6 It is a schematic diagram of a switching control corresponding to a pre-trained image generation model.

[0052] In a specific example, the method described in the embodiment of the present application can be applied to computer software. Users can click on the image description information input box at the top of the screen with the mouse to activate the input box cursor, and at the same time start entering the content of the desired picture, such as "a girl in ancient style with a white dress", "a blue sky scenery", "a second-generation cartoon anime character", etc. After entering, click the search button or press the Enter key on the keyboard to submit an image search and generation instruction.

[0053] In response to the image search and generation instruction, the search result is returned within seconds, and wait for the image generation result: At this time, the search result can be returned from the in-site picture library, external website resources or results uploaded by third parties / users. The search process can be to filter out more appropriate picture content according to keyword matching and display the pictures uniformly and sequentially in the graphical user interface. The speed of obtaining pictures through the image search operation is relatively fast, and users can immediately browse and slide to view the search results to find suitable images.

[0054] Because AI-generated images require processing using core algorithms such as large language models and image models to understand and semantically transform image descriptions before rendering, there can be loading times ranging from tens of seconds to several minutes. Therefore, the return of images is relatively slow; users can browse images from search results during this time.

[0055] The return of raw image results can be divided into the return of results from general models and the return of results from models based on customized workflows.

[0056] A general-purpose model is an image generation model that encapsulates the algorithm into a core and has a wide recognition range. It can generate images for most instructions, making it quite versatile with few weaknesses. A customized workflow, on the other hand, is a model developed by algorithm developers specifically for a particular application scenario, such as models based on keywords like "anime," "traditional Chinese style," or "clothing and embroidery." Upon receiving image description information from the user, it automatically identifies which workflow model matches the description. Therefore, this type of model is highly targeted and generates more accurate images.

[0057] Therefore, by returning raw images from the two models, users can switch back and forth on the interface to view and perform further operations, thereby selecting the image that best meets their expectations.

[0058] This technical solution adds an image generation operation to the original image search path, meeting users' needs for precise image finding. This solution implements image search and image generation interaction within a single graphical user interface, eliminating the need for users to initiate image searches and image generation on multiple pages across multiple products, significantly reducing the time spent on clicking, switching, jumping, and waiting. This solution reduces the learning cost and learning curve for users of AI image generation: typically, users may not know where to find AI image generation software; therefore, embedding AI image generation into the search path greatly reduces the cost for users to learn how to perform image generation operations.

[0059] This technical solution can display a more suitable image obtained through image generation when the search image is inaccurate or the desired image cannot be found. This solution displays the search results before generating the image, avoiding the problem of users waiting too long for the image.

[0060] This technical solution uses a single input box to simultaneously trigger the image search and image generation operations, eliminating the need for separate image search and image generation operations; thus improving the efficiency of image retrieval for users.

[0061] This technical solution can generate images using a general model and a workflow model, which improves the accuracy of the generated images.

[0062] This technical solution allows users who are used to searching for images to view the generated image results, and users with experience in searching for raw images to quickly browse the search results, thus improving the image search experience for both types of users.

[0063] Example 3 Figure 7 This is a schematic diagram of an image search and generation apparatus provided in Embodiment 3 of this application. This apparatus can execute the image search and generation method provided in any embodiment of this invention, and possesses the corresponding functional modules and beneficial effects for executing the method. For example... Figure 7 As shown, the device includes: The image search and generation module 310 is used to respond to an image search request and, based on the image description information in the image search request, perform image search operations and image generation operations in parallel. The image display module 320 is configured to display a first image from the search results in a graphical user interface when the search results of the image search operation are received, and to display a second image from the generation results in a graphical user interface when the generation results of the image generation operation are received.

[0064] The technical solution of this application embodiment includes: an image search and generation module 310, used to respond to an image search request and, based on the image description information in the image search request, perform an image search operation and an image generation operation in parallel; and an image display module 320, used to display a first image in the search results on a graphical user interface when the search results of the image search operation are received, and to display a second image in the generation results on a graphical user interface when the generation results of the image generation operation are received. This technical solution, by performing image search and generation operations in parallel and displaying the corresponding images upon receiving the results of the two operations, allows users to view images close to their expectations obtained through the image generation operation, and also to browse searched images while waiting for image generation, greatly improving the user experience when searching for desired images.

[0065] Optionally, in this embodiment of the application, the image search and generation module 310 includes: An input box display unit is used to display an input box for inputting image search content in a graphical user interface, so as to obtain the image description information input into the input box; The image search and generation unit is configured to respond to an image search request for the image description information in the input box, and to perform image search and image generation operations in parallel based on the image description information.

[0066] Optionally, in this embodiment of the application, the device further includes: A target control display unit is used to display a target control in a graphical user interface; the target control is a control that initiates an image search request. Correspondingly, the image search and generation module 310 includes: The image search and generation subunit is used to respond to the triggering operation of the target control, determine the image description information for image search, and perform image search operation and image generation operation in parallel based on the image description information.

[0067] Optionally, in this embodiment of the application, the image display module 320 includes: The first image display unit is configured to, upon receiving the search result of the image search operation, display the first image in the search result in a first area of ​​the graphical user interface, and display the execution status of the image generation operation in a second area of ​​the graphical user interface. The second image display unit is used to display the second image in the second area after receiving the generation result of the image generation operation.

[0068] Optionally, in this embodiment of the application, the image search and generation module 310 includes: The target workflow model determination unit is used to determine, among the pre-established workflow models, a target workflow model that matches the image description information; the workflow model is a model with a pre-configured image generation process. The first image generation unit is used to process the image description information based on the target workflow model to generate an image that matches the image description information.

[0069] Optionally, in this embodiment of the application, the image search and generation module 310 further includes: The second image generation unit is used to process the image description information based on the pre-trained image generation model to generate an image that matches the image description information if the pre-established workflow model does not meet the matching conditions with the image description information.

[0070] Optionally, in this embodiment of the application, the device further includes: A switching control display module is used to display a switching control corresponding to the target image generation model; the target image generation model is an image generation model that is inconsistent with the current image generation model; the target image generation model is a workflow model or a pre-trained image generation model; the workflow model is a model with a pre-configured image generation process. An image switching module is used to display an image generated based on the target image generation model in response to the triggering operation of the switching control.

[0071] The image search and generation apparatus provided in this application embodiment can execute the image search and generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0072] Example 4 Figure 8 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0073] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0074] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0075] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as image search and generation methods.

[0076] In some embodiments, the image search and generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the image search and generation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the image search and generation method by any other suitable means (e.g., by means of firmware).

[0077] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0078] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0079] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0080] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0081] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0082] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0083] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0084] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for searching and generating images, characterized in that, include: In response to an image search request, based on the image description information in the image search request, image search operations and image generation operations are performed in parallel. When the search result of the image search operation is received, the first image in the search result is displayed in the graphical user interface. When the generation result of the image generation operation is received, the second image in the generation result is displayed in the graphical user interface.

2. The method according to claim 1, characterized in that, In response to an image search request, based on the image description information in the image search request, image search operations and image generation operations are performed in parallel, including: A graphical user interface is displayed for inputting image search terms to obtain the image description information entered into the input box; In response to the image search request for the image description information in the input box, the image search operation and the image generation operation are performed in parallel based on the image description information.

3. The method according to claim 1, characterized in that, The method further includes: The target control is displayed in the graphical user interface; the target control is the control that initiates the image search request. In response to an image search request, based on the image description information in the image search request, the image search operation and image generation operation are performed in parallel, including: In response to the triggering operation of the target control, image description information for image search is determined, and based on the image description information, image search operation and image generation operation are performed in parallel.

4. The method according to claim 1, characterized in that, Upon receiving the search result of the image search operation, the first image from the search results is displayed in the graphical user interface; upon receiving the generation result of the image generation operation, the second image from the generation result is displayed in the graphical user interface, including: When the search result of the image search operation is received, the first image in the search result is displayed in the first area of ​​the graphical user interface, and the execution status of the image generation operation is displayed in the second area of ​​the graphical user interface. Until the generation result of the image generation operation is received, the second image in the generation result is displayed in the second area.

5. The method according to claim 1, characterized in that, The image generation operation is performed based on the image description information, including: Among the pre-established workflow models, a target workflow model that matches the image description information is determined; the workflow model is a model with a pre-configured image generation process. The image description information is processed based on the target workflow model to generate an image that matches the image description information.

6. The method according to claim 5, characterized in that, The method further includes: If the pre-established workflow model does not meet the matching conditions with the image description information, the image description information is processed based on the pre-trained image generation model to generate an image that matches the image description information.

7. The method according to claim 1, characterized in that, When displaying the second image in the generated result, the method further includes: Displays a switching control corresponding to the target image generation model; the target image generation model is an image generation model that is inconsistent with the current image generation model; the target image generation model is: a workflow model or a pre-trained image generation model; the workflow model is a model with a pre-configured image generation process; In response to the triggering operation of the switching control, the image generated based on the target image generation model is displayed.

8. An image search and generation apparatus, characterized in that, include: The image search and generation module is used to respond to an image search request and, based on the image description information in the image search request, perform image search operations and image generation operations in parallel. An image display module is configured to display a first image from the search results received from the image search operation on a graphical user interface, and to display a second image from the generation result received from the image generation operation on a graphical user interface.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the image search and generation method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the image search and generation method according to any one of claims 1-7.

Images