Image generation method and related equipment

Abstract

This disclosure provides an image generation method and related equipment. The method includes displaying a text editing area and an image effect setting control on an image display interface; determining a target prompt based on text content in response to editing text content in the text editing area; determining at least one target parameter in response to an operation on the image effect setting control; and displaying a generated target image in a first display area of ​​the image display interface based on the target prompt and the target parameter.

Description

Technical Field

[0001] (Cross - reference to related applications) This application claims the priority of a Chinese patent application titled "Image Generation Method and Related Devices", filed on August 18, 2023, with application number 202311049768.3, the entire content of which is incorporated herein by reference.

[0002] (Field of the Invention) This disclosure relates to the technical field of computers, and particularly to image generation methods and related devices.

Background Art

[0003] With the extensive application of artificial intelligence technology in the field of images, it has become possible to convert text descriptions into images for display, which has advantages such as high automation, high precision, high scalability, and customizability. However, in existing technologies, the image results generated based on text often need to jump from a text input interface to another interface for display. When the user needs to modify the text, they often have to return to the text input interface. As a result, the user has to jump back and forth between different interfaces, making the operation inconvenient and reducing the efficiency of image generation. In addition, the generated image results are only based on the input text, and the display effect of the image cannot be adjusted. Therefore, the flexibility of the settings for generating images based on text is not sufficient, and there is a problem that it cannot meet the needs of users who want to flexibly adjust the image generation effect.

Summary of the Invention

Problems to be Solved by the Invention

[0004] This disclosure proposes an image generation method, apparatus, device, storage medium, and program product to solve, to a certain extent, the technical problems that the settings of image generation lack flexibility, the operation is inconvenient, and the efficiency is reduced.

Means for Solving the Problems

[0005] A first aspect of the present disclosure provides an image generation method comprising: displaying a text editing area and an image effect setting control on an image display interface; determining a target prompt based on text content in response to editing text content in the text editing area; determining at least one target parameter in response to an operation on the image effect setting control; and displaying a generated target image in a first display area of ​​the image display interface based on the target prompt and the target parameter.

[0006] In a second aspect of the present disclosure, an image generating device is provided, comprising: a display module for displaying a text editing area and an image effect setting control in an image display interface; and a setting module for determining a target prompt based on text content in response to editing text content in the text editing area, and determining at least one target parameter in response to an operation on the image effect setting control, wherein the display module is further used to display a generated target image in a first display area of ​​the image display interface based on the target prompt and the target parameter.

[0007] A third aspect of the present disclosure provides an electronic device comprising one or more processors, memory, and one or more programs stored in the memory and executed by the one or more processors, wherein the processors include instructions for performing the method described in the first or second aspect.

[0008] A fourth aspect of the present disclosure provides a non-volatile computer-readable storage medium that, when executed by one or more processors, causes the processors to perform the method described in the first or second aspect.

[0009] A fifth aspect of this disclosure provides a computer program product that, when executed on a computer, includes computer program instructions causing a computer to perform the method described in the first aspect. [Brief explanation of the drawing]

[0010] To more clearly explain the technical concepts in this disclosure or related technologies, the following is a brief introduction to the accompanying drawings that may be used in the descriptions of the embodiments or related technologies. However, the accompanying drawings in the following descriptions are merely examples of the embodiments of this disclosure, and it is clear that a person of the ordinary skill in the art can obtain other drawings from these accompanying drawings without requiring any creative effort. [Figure 1] This is a schematic diagram of the image generation architecture of an embodiment of the present disclosure. [Figure 2] This is a schematic diagram illustrating the hardware configuration of an exemplary electronic device according to an embodiment of the present disclosure. [Figure 3] This is a schematic flowchart of the image generation method of the embodiment of this disclosure. [Figure 4] This is a schematic diagram of an image display interface in an embodiment of the present disclosure. [Figure 5] This is a schematic diagram of an image display interface in an embodiment of the present disclosure. [Figure 6] This is a schematic diagram of the image effect setting interface of an embodiment of the present disclosure. [Figure 7] This is a schematic diagram of an image display interface in an embodiment of the present disclosure. [Figure 8] This is a schematic diagram of the first display area of ​​an embodiment of the present disclosure. [Figure 9] This is a schematic diagram of the first display area of ​​an embodiment of the present disclosure. [Figure 10] This is a schematic diagram of an image display interface in an embodiment of the present disclosure. [Figure 11] This is a schematic diagram of a super-resolution image of an embodiment of the present disclosure. [Figure 12]It is a schematic diagram of a portfolio interface according to an embodiment of the present disclosure. [Figure 13] It is a schematic diagram of an image information interface according to an embodiment of the present disclosure. [Figure 14] It is a schematic diagram of a history image according to an embodiment of the present disclosure. [Figure 15] It is a schematic diagram of a display image according to an embodiment of the present disclosure. [Figure 16] It is a schematic diagram of a display image according to an embodiment of the present disclosure. [Figure 17] It is a schematic diagram of an image generation device according to an embodiment of the present disclosure.

Embodiments for Carrying Out the Invention

[0011] Hereinafter, in order to make the objectives, technical solutions, and advantages of the present disclosure clearer and easier to understand, the present disclosure will be described in more detail with reference to the accompanying drawings in connection with specific embodiments.

[0012] It should be noted that unless otherwise defined, technical terms or scientific terms used in the embodiments of the present disclosure have the ordinary meanings understood by those of ordinary skill in the field to which the present disclosure belongs. The "first", "second", and similar terms used in the embodiments of the present disclosure do not indicate order, number, or importance, and are only used to distinguish different components. Similar terms such as "including" or "having" are intended to cover the elements or objects that appear before the term, including the elements or objects listed after the term and their equivalents, but do not exclude other elements or objects. Similar terms such as "connected" or "coupled" are not limited to physical or mechanical connections, and may include electrical connections whether direct or indirect. "Above", "below", "left", "right", etc. are only used to indicate relative positional relationships, and if the absolute position of the described object changes, the corresponding relative positional relationships may also change accordingly.

[0013] Before using the technical solutions disclosed in each embodiment of this disclosure, it should be understood that, in accordance with relevant laws and regulations, appropriate means should be used to notify the user of the types, scope of use, usage scenarios, etc. of the personal information related to this disclosure and obtain the user's approval.

[0014] For example, in response to receiving an uncommitted request from a user, a prompt message is sent to the user explicitly prompting that the requested operation requires access to and use of the user's personal information. Thereby, based on the prompt message, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application, a server, or a storage medium that executes the operations of the technical solutions of this disclosure.

[0015] As a selectable and non-limiting implementation form, the form of sending a prompt message to the user in response to receiving an uncommitted request from the user may be, for example, by means of a pop-up window. In the pop-up window, the prompt message may be presented in text. Furthermore, the pop-up window may include a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0016] It should be understood that the above process of notification and obtaining user approval is merely exemplary and does not limit the implementation forms of this disclosure, and other methods that meet the relevant laws and regulations can also be applied to the implementation forms of this disclosure.

[0017] Figure 1 is a schematic diagram of an image generation architecture of an embodiment of the present disclosure. Referring to Figure 1, the image generation architecture 100 may include a server 110, a terminal 120, and a network 130 that provides a communication link. The server 110 and the terminal 120 may be connected to each other via the wired or wireless network 130. Here, the server 110 may be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, security services, and CDNs.

[0018] Terminal 120 may be a hardware implementation or a software implementation. For example, if terminal 120 is a hardware implementation, it may be a variety of electronic devices having a display and supporting page display, including but not limited to smartphones, tablet computers, e-readers, laptop computers, and desktop computers. If terminal 120 is a software implementation, it may be installed on the electronic devices listed above, and may be implemented as multiple software or software modules (e.g., software or software modules for providing distributed services), or as a single software or software module, and is not particularly limited herein.

[0019] It should be noted that the image generation method provided by the embodiments of this application may be performed by terminal 120 or by server 110. The number of terminals, networks, and servers in Figure 1 are merely illustrative and not intended to be limiting. Any number of terminals, networks, and servers may be used as required by the implementation.

[0020] Figure 2 shows a schematic diagram of the hardware configuration of an exemplary electronic device 200 provided by an embodiment of the present disclosure. As shown in Figure 2, the electronic device 200 may include a processor 202, memory 204, a network module 206, a peripheral interface 208, and a bus 210. The processor 202, memory 204, network module 206, and peripheral interface 208 enable communication connectivity within the electronic device 200 via the bus 210.

[0021] The processor 202 may be a central processing unit (CPU), an image generator, a neural network processor (NPU), a microcontroller (MCU), a programmable logic device, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or one or more integrated circuits. The processor 202 may be used to perform functions related to the technology described herein. In some embodiments, the processor 202 may have multiple processors integrated into a single logic component. For example, as shown in Figure 2, the processor 202 may have multiple processors 202a, 202b, and 202c.

[0022] Memory 204 may be configured to store data (e.g., instructions, computer code, etc.). As shown in Figure 2, the data stored in memory 204 may include program instructions (e.g., program instructions for implementing the image generation method of the embodiment of this disclosure) and data to be processed (e.g., the memory may store configuration files for other modules, etc.). The processor 202 may also access the program instructions and data stored in memory 204 and execute program instructions to perform operations on the data to be processed. Memory 204 may have volatile or non-volatile storage devices. In some embodiments, memory 204 may include random access memory (RAM), read-only memory (ROM), optical disks, magnetic disks, hard drives, solid-state drives (SSDs), flash memory, memory sticks, etc.

[0023] The network module 206 may be configured to provide the electronic device 200 with communication with other external devices via a network. This network may be any wired or wireless network capable of sending and receiving data. For example, this network may be a wired network, a local wireless network (e.g., Bluetooth®, WiFi, Near Field Communication (NFC), etc.), a cellular network, the Internet, or a combination thereof. It should be understood that the type of network is not limited to the specific examples given above. In some embodiments, the network module 306 may include any number of network interface controllers (NICs), RF modules, transceivers, modems, routers, gateways, adapters, cellular network chips, and any combination thereof.

[0024] The peripheral interface 208 may be configured to connect the electronic device 200 to one or more peripheral devices in order to enable information input and output. For example, the peripheral devices may include input devices such as a keyboard, mouse, touchpad, touchscreen, microphone, and various sensors, and output devices such as a display, speaker, vibrator, and indicator lamp.

[0025] Buses 210, such as an internal bus (e.g., a processor-memory bus) or an external bus (USB port, PCI-E bus), may be configured to transmit information between the various components of the electronic device 200 (e.g., a processor 202, memory 204, a network module 206, and peripheral interfaces 208).

[0026] While the above-described architecture of the electronic device 200 illustrates only the processor 202, memory 204, network module 206, peripheral interface 208, and bus 210, it should be noted that in a specific implementation process, the architecture of this electronic device 200 may also include other components necessary for its successful operation. In addition, it will be understood by those skilled in the art that the above-described architecture of the electronic device 200 may include only the components necessary to realize the solution of the embodiment of this disclosure, and does not need to include all of the components shown in the figure.

[0027] Currently, after generating image results based on text, displaying the generated image often requires jumping from one interface to another. If the user needs to make changes to the input text, they must return to the text input interface. This results in users having to jump back and forth between different interfaces, making operation inconvenient and reducing the efficiency of image generation. Furthermore, the generated image results are solely based on the input text, and the display effects of the image cannot be adjusted. This lack of flexibility in setting up text-generated images fails to meet the user's need for flexible adjustment of image results. Therefore, finding a rational layout for the text-generated image process, simplifying user operation, improving image generation efficiency, and flexibly adjusting the effects of the generated image are urgent technical challenges that need to be addressed.

[0028] In view of this, embodiments of the present disclosure provide an image generation method and related equipment. By displaying a text editing area, style selection controls, condition setting controls, and the generated target image on the same image generation interface, the target prompt, target style model, and target parameters of the generated target image can be directly adjusted while displaying the target image, without having to jump between different interfaces. This simplifies user operation and improves the efficiency of image generation. Furthermore, image effects can be flexibly set to meet the user's personal needs regarding image generation effects.

[0029] Refer to Figure 3, which shows a schematic flowchart of the image generation method according to an embodiment of the present disclosure. In Figure 3, the image generation method 300 may further include the following steps.

[0030] In step S310, a text editing area and image effect setting controls are displayed on the image display interface.

[0031] Here, the image display interface refers to an interface for displaying images, which may display images generated by the current user or images generated by other users, for example, by retrieving images posted by other users from the server side. The image display interface may also display a text editing area, in which the user can enter text and obtain a target prompt for generating a target image based on this text. For example, the text may be a keyword, in which case the keyword may be used directly as the target prompt, or the text may be a text description, in which case the target prompt may be extracted from this text description. The image display interface may also display an image effect setting control, which the user can use to set the style of the target image, for example, portrait, anime, general, etc. Predetermined condition parameters of the target image, for example, ratio conditions, degree of stylization conditions, detail conditions, etc., may be set by the image effect setting. Refer to Figure 4, which shows a schematic diagram of an image display interface according to an embodiment of the present disclosure. In Figure 4, the image display interface 400 includes a text editing area 410 and an image effect setting control 420.

[0032] In step S320a, in response to editing text content in the text editing area, a target prompt is determined based on the text content.

[0033] Here, the text editing area 410 may be a text input box, and the user can enter text content into the text editing area 410. This text content may be associated with an image that the user wants to generate, and may be, for example, at least one keyword and / or at least one descriptive paragraph. This text content may be in multiple languages.

[0034] Specifically, as shown in Figure 4, if the text editing area 410 does not display a prompt, that is, if the text editing area 410 is empty, prompt text indicating the function or effect of the text editing area 410 may be displayed in the text editing area 410 in a predetermined color (for example, gray, or a color that distinguishes it from the background color of the text editing area). The prompt text may be, for example, "Please enter a keyword," "Please enter a description of the effect to be generated," or "For example, high quality, long hair, girl." Alternatively, the user may perform a trigger operation O1 (for example, a click operation) on the text editing area 410, causing the cursor to blink in the text editing area 410, and then input text such as text content 1, text content 2, text content 3, ... as shown in Figure 5, which shows a schematic diagram of the image display interface according to an embodiment of the present disclosure. Furthermore, the text editing area 410 may also display the number of characters a of the prompt entered and the maximum number of characters b. For example, the format "number of characters entered / maximum number of characters entered" may be adopted, and the number of characters a may be updated in real time according to the number of characters actually displayed in the text editing area 410. If the text editing area 410 is empty, no prompt is entered, and 0 / b may be displayed as shown in Figure 4. If the user enters character a into the text editing area 410, a / b may be displayed as shown in Figure 5.

[0035] In step S320b, at least one target parameter is determined in response to an operation on the image effect setting control.

[0036] Here, the image effect setting control may be used to set the display effect of the target image, and includes setting one of the following predetermined conditions for the target image: style model condition, ratio condition, degree of stylization condition, and detail condition. The style model condition may refer to the style type of the target image, the ratio condition may refer to the aspect ratio of the target image, the degree of stylization condition may refer to the degree to which the target image is stylized, and the detail condition may refer to the resolution of the target image.

[0037] In some embodiments, determining at least one target parameter in response to an operation on the image effect setting control includes displaying an image effect setting interface in the relevant area of ​​the image effect setting control in response to a trigger operation on the image effect setting control, wherein the image effect setting interface includes at least one predetermined condition, and determining the selected condition parameter as the target parameter in response to a selection operation on the predetermined condition, wherein the image effect setting interface includes at least one of a style model condition, a ratio condition, a degree of stylization condition, and a detail condition.

[0038] Each of the given conditions includes multiple corresponding condition parameters, and the user may select multiple condition parameters for each given condition and set the selected condition parameters as the target parameters for the given condition.

[0039] In some embodiments, the style model condition includes at least one predetermined style model parameter, the target parameter includes a target style model, and determining the selected condition parameter as the target parameter in response to a selection operation on the predetermined condition includes determining the selected predetermined style model as the target style model in response to a selection operation on the predetermined style model.

[0040] Specifically, an image effect setting control 420 may be displayed on the image display interface 400 in Figure 4, and a setting identifier indicating the function of the image effect setting control 420 (for example, "Parameter Adjustment" or "Parameter Setting") may be displayed on the image effect setting control 420. The user may perform a trigger operation O2 (for example, a click operation) on this image effect setting control 420, and in response to this trigger operation O2, an image effect setting interface 421 may be displayed in the relevant area of ​​the image effect setting control 420 via a pop-up window, as shown in Figure 6, which shows a schematic diagram of the image effect setting interface according to an embodiment of the present disclosure.

[0041] In Figure 6, the image effect setting interface 421 displays style labels 422 for multiple style models. Each style label 422 may display a style name and a corresponding icon, and each style label corresponds to one style model. For example, if style label s1 contains the style name "General" and icon 422a, this style label s1 corresponds to the General style model; if style label s2 contains the style name "Anime" and icon 422b, this style label s2 corresponds to the Anime style model; and if style label s3 contains the style name "Portrait" and icon 422c, this style label s3 corresponds to the Portrait style model. Style models may be deployed on the server side, and the user may select a style label to determine the target style model. For example, a predetermined mark (e.g., a check mark) may be placed on the selected style label to indicate that this style label has been selected, and the style model corresponding to this style label is the target style model. In some embodiments, the default value of the target style model corresponds to the General style model. The style labels and their corresponding style models described above are merely illustrative and not intended to be limiting. You may set more or fewer different style labels and their corresponding style models as needed, and this specification does not limit them.

[0042] Furthermore, as shown in Figure 6, the image effect setting interface 421 also displays multiple ratio labels 423. In Figure 6, each ratio label includes a ratio parameter and a corresponding icon 423a, 423b, ..., where the size ratio of the icon may match the ratio parameter, for example, 1:1, 3:4, 16:9, 4:3, 9:16, 2:3, 3:2, ... The user can determine the target parameter of the ratio condition by selecting a ratio label 423, for example, the border of the selected ratio label is thickened to indicate that this ratio border has been selected, as in the 1:1 ratio label in Figure 7, and the ratio parameter displayed by this ratio label is determined as the target parameter of the ratio condition. In some embodiments, the default value of the ratio condition may be 1:1.

[0043] The image effect setting interface 421 in Figure 6 further displays parameters for the degree of stylization, which may be presented in the form of a first slider 424a and / or a first input box 424b. The user may drag the first slider 424a to determine the target parameter for the degree of stylization, or may directly input the target parameter for the degree of stylization into the first input box 424b. Here, the first slider 424a may adjust the degree of stylization by a first predetermined number of steps (e.g., 30 steps), and the first input box 424b may accept a value of up to e (e.g., e=2) characters. Furthermore, when a parameter value c for the degree of stylization is entered using the first input box 424b, a character identifier "number of characters entered / maximum number of characters", for example d / e, may be further displayed in the associated area of ​​the first input box 424b, where d / e means that the entered parameter value c is d characters and the maximum number of characters that can be entered in the first input box 424b is e. The number of characters entered d may be updated along with the number of characters entered by the user. Correspondingly, the number of characters entered d may match the value of the first slider 424a, and when the number of characters entered d is updated, the value of the first slider 424a is also updated, and when the value of the first slider 424a is updated, the number of characters entered d is also updated accordingly. In some embodiments, the default value for the degree of stylization condition may be 30 steps. In some embodiments, when the number of characters entered d in the first input box 424b of the degree of stylization condition exceeds the maximum number of characters e, prompt text, for example "Please enter up to e characters", may be displayed. In some embodiments, in response to a trigger operation on the name identifier 424c of the stylization degree condition (for example, a hover operation on the name identifier 424c "Stylization Degree" in Figure 6), a function identifier indicating the function of the stylization degree condition may be displayed in the area associated with the name identifier 424c, for example, as a pop-up in the form of a text box.

[0044] Furthermore, the image effect setting interface 421 in Figure 6 also displays parameters for the detail level condition, which may be presented in the form of a second slider 425a and / or a second input box 425b. The user may adjust the target parameter for the detail level condition by dragging the second slider 425a, or they may directly input the target parameter for detail into the second input box 425b. Here, the second slider 425a may adjust the detail level by a second predetermined number of steps (e.g., 50 steps), and the second input box 425b may accept a value of up to h characters (e.g., h=2). Also, when inputting the detail level parameter value f using the second input box 425b, a character identifier "number of characters entered / maximum number of characters", for example g / h, may be displayed in the relevant area of ​​the second input box 425b, where g / h indicates that the entered parameter value f is g characters and the maximum number of characters that can be entered in the second input box 425b is h. Furthermore, the number of characters g entered may be updated along with the number of characters entered by the user. Correspondingly, the number of characters g entered matches the value of the second slider 425a, and when the number of characters g entered is updated, the value of the second slider 425a is also updated, and when the value of the second slider 425a is updated, the number of characters g entered is also updated accordingly. In some embodiments, the default value of the refinement condition may be 30 steps. In some embodiments, when the number of characters g entered in the second input box 425b of the refinement condition exceeds the maximum number of characters h, prompt text, for example, "Please enter up to h characters," may be displayed. In some embodiments, in response to a trigger operation on the name identifier 425c of the refinement condition (for example, a hover operation on the name identifier 425c "Refinement" in Figure 6), a function identifier indicating the function of the refinement condition may be displayed in the area associated with the name identifier 425c, for example, as a pop-up in the form of a text box. A typical resolution includes 768 pixels on the longest side, while a super-resolution may include a resolution n (for example, n=2) times that of the typical resolution.

[0045] Steps S320a and S320b may or may not have a sequential order, and this is not limited herein.

[0046] In step S330, the generated target image is displayed in the first display area of ​​the image display interface based on the target prompt and the target parameters.

[0047] Here, the first display area may refer to an area within the image display interface for displaying the target image. Based on the determined target prompt, the image content of the target image can be determined, and based on the target parameters, the image effects of the target image can be determined. This allows the user to not only set the content of the target image but also flexibly set the visual effects of the target image, making it easy to operate and improving both the efficiency and effectiveness of image generation.

[0048] In some embodiments, a generation control (e.g., generation control 430 in Figure 4) for triggering the generation and display of a target image may be further displayed on the image display interface. The user can trigger an operation O3 (e.g., a click) on this generation control 430 to trigger the generation of a target image. Specifically, in response to this trigger operation O3, a target image is generated based on the target prompt and target parameters, and one or more of these target images are displayed in the first display area. A single user trigger operation on the generation control 430 may function as a single input to the text editing area 410; that is, the text displayed in the text editing area 410 collectively functions as a single input each time a target image is generated. Furthermore, in some embodiments, the target prompt displayed in the text editing area 410 is retained in response to the user trigger operation on the generation control 430.

[0049] In some embodiments, the generation control 430 may be available or unavailable. In some embodiments, the generation control displays an available state in response to detection of a prompt in the text editing area. In this case, the generation control may be displayed in a first predetermined color. In some embodiments, the generation control displays an unavailable state in response to detection of no prompt in the text editing area. Specifically, if there is no prompt in the text editing area 410, the generation control 430 is unavailable, and the user cannot perform an operation on this generation control 430. In this case, to indicate the unavailable state of the generation control 430, it may be displayed in a second predetermined color (e.g., gray). Furthermore, in some embodiments, in response to detection of a trigger operation on the unavailable generation control 430, the prompt text "Please enter a keyword" is displayed in the relevant area of ​​the generation control 440, popping up, for example, in the form of a callout or dialog box around the generation control 430.

[0050] In some embodiments, Method 300 may further include displaying a random text control on the image display interface, inputting randomly generated random text into the text editing area in response to a trigger operation on the random text control, and determining a target style model for the target image based on the style corresponding to the random text.

[0051] Specifically, as shown in Figure 7, Figure 7 shows a schematic diagram of an image display interface according to an embodiment of the present disclosure. In Figure 7, a random text control 440 is used to randomly generate text content and display it in a text editing area 410. A user can perform a trigger operation O4 (e.g., a click operation) on the random text control 440, and in response to this trigger operation O4 on the random text control 440, at least one random text may be generated and this random text, for example, random text text1, text2, ... may be displayed in the text editing area 410. Furthermore, random prompts may have corresponding style models. Here, a prompt database may be set on the server side, and this prompt database contains at least one prompt text, each prompt text having a corresponding style. That is, in response to a trigger operation O4, when the prompt text word in this database is displayed in the text editing area 410, the style model condition in the image effect setting control 420 may be set to the style model corresponding to the prompt text word.

[0052] In some embodiments, Method 300 may further include displaying an extended text control on the image display interface and, in response to a trigger operation on the extended text control, supplementing the text editing area with new text content based on the text content of the text editing area.

[0053] Specifically, in Figure 7, the extended text control 450 is used to display an extended version of the text content within the text editing area 410. The user can perform a trigger operation O5 (e.g., a click) on the extended text control 450, and in response to this trigger operation O5 on the extended text control 450, it generates at least one extended text that has a similar or identical meaning to the actual text content, based on the text content currently displayed in the text editing area 410; that is, the semantic similarity between the text content and the extended text is greater than or equal to a similarity threshold. This extended text, for example, text_a, text_b, ..., may be displayed in the text editing area 410.

[0054] In some embodiments, the image display interface 400 may further display an update control 460 for updating the text content displayed in the text editing area. Specifically, as shown in Figure 4, the user may perform a trigger operation O6 on the update control 460, which in response to this trigger operation O6 generates new text content and replaces the text content currently displayed in the prompt area.

[0055] In some embodiments, displaying a generated target image in a first display area of ​​the image display interface based on the target prompt and the target parameters includes displaying an initial image in the first display area, generating a target image based on the target prompt and the target parameters, and displaying the target image in the area of ​​the initial image.

[0056] Specifically, the user can perform a trigger operation O3 on the generation control 430, and in response to this trigger operation O3, initial images 471 to 474 are displayed in the first display area, as shown in Figure 8, which shows a schematic diagram of the first display area according to an embodiment of the present disclosure. Simultaneously with displaying the initial images 471 to 474, the server may generate target images based on the target prompt and target parameters. Since generating target images takes a certain amount of time, the initial images displayed in the first display area may be positioned at the location of the target images. Once the target images 471' to 474' are generated, the target images 471' to 474' may be displayed in the area of ​​the initial images 471 to 474, as shown in Figure 9, which shows a schematic diagram of the first display area according to an embodiment of the present disclosure; that is, the initial images 471 to 474 are replaced with the target images 471' to 474'.

[0057] In some embodiments, displaying the target image in the area of ​​the initial image includes displaying an animation in the first display area in which the initial image changes into the target image.

[0058] To avoid a decline in user experience due to waiting times, the process of changing from initial images 471-474 to target images 471'-474' can be displayed as an animation, enhancing the interest of the image generation process and improving the user experience. For example, the animation may be based on changes in optical flow information between the initial image and the target image. Another example is the change from a blurry (low-resolution) initial image to a sharp (high-resolution) target image. Yet another example is that the initial image may be a noisy image, and the animation may be the process of the noisy image generating the target image based on a diffusion model.

[0059] In some embodiments, displaying an initial image in the first display area includes generating the initial image based on the semantic information of the target prompt, or searching an image database based on the target prompt to obtain a predetermined number of initial images that match the meaning or style of the target prompt, and determining the predetermined number of areas in the first display area in order to display the initial image.

[0060] Here, the initial image may be an image that has a similar or identical meaning / style to the target image obtained by quick generation or quick search based on the semantic information of the target prompt. This not only visually enriches the target image generation process but also allows the position of the target image to be laid out in the first display area, facilitating display at this position after the target image has been generated, and further improving the efficiency of image generation and display. In some embodiments, the predetermined number may be 4, as shown in Figure 8. It should be understood that the predetermined number may be other values ​​and is not limited herein.

[0061] In some embodiments, Method 300 may further include displaying at least one of the trigger time for generating the target image, the text content, the target parameters, a re-edit control, or a re-generate control in association with the target image in the first display area.

[0062] Specifically, as shown in Figures 7 to 8, at least one of the following may be displayed in the first display area in association with the initial images 471 to 474 or the target images 471' to 474': the trigger time 481 of the target image, the text content 482, the re-edit control 491, or the re-generate control 492.

[0063] In some embodiments, Method 300 may further include displaying the text content in the text editing area and setting the image effect setting control to the target parameter in response to a trigger operation on the re-edit control.

[0064] Specifically, as shown in Figure 8, the user can perform a trigger operation O9_1 on the editing control 491 again. In response to this trigger operation O9_1, the text content "Text content 1, Text content 2, Text content 3, ..." may be displayed in the text editing area, and the image effect setting control 420 may be set as the target parameter. In this way, if the user wants to adjust some or all of the predetermined conditions of the current target images 471'~474', they can make adjustments on the current target images 471'~474' without resetting everything, further improving the efficiency and effect of image generation and making the operation more flexible.

[0065] In some embodiments, Method 300 may further include displaying a new target image generated based on the target prompt and the target parameters in the first display area in response to a trigger operation on the regenerate control, and displaying at least one of the trigger time, the text content, the target parameters, the re-edit control, or the regenerate control corresponding to the new target image in the first display area in association with the new target image.

[0066] Specifically, as shown in Figure 8, if the user is dissatisfied with the current target images 471'~474' and wants to regenerate the target images with the current text content and target parameters, they can perform a trigger operation O9_2 on the regenerate control 492. In response to this trigger operation O9_2, as shown in Figure 10, the server generates new target images 1010~1040 based on the target prompt and target parameters obtained from the current text content. These new target images 1010~1040 may be displayed in a first display area, for example, below or above the target images 471'~474'. At least one of the trigger time 1050, text content 1060, re-edit control 1070, or regenerate control 1080 of the new target images 1010~1040 may also be associated with the new target images 1010~1040 and displayed in the first display area. Please understand that the re-edit control 1070 or re-generate control 1080 functions similarly to the re-edit control 491 or re-generate control 492, and therefore the explanation here is not repeated.

[0067] In some embodiments, the method 300 may further include displaying a super-resolution image corresponding to the target image in the first display area in response to a trigger operation on the target image, and displaying at least one of the trigger time, the text content, the target parameters, the re-edit control, or the re-generate control corresponding to the super-resolution image in the first display area in association with the super-resolution image.

[0068] Specifically, the user may perform a trigger operation O11 on any one of the current target images 471' to 474', and in response to this trigger operation O11, a super-resolution image 1110 of the selected current target image may be displayed in the first display area, as shown in Figure 11, which shows a schematic diagram of a super-resolution image according to an embodiment of the present disclosure. For example, a trigger operation O11 (e.g., a click operation) may be performed on the current target image 471' in Figure 9, and in response to this trigger operation O11, a super-resolution image 1110 of the target image 471' may be displayed in the first display area. The resolution of the super-resolution image 1110 is m (where m is a positive integer greater than or equal to 2) times that of the target image 471'. At least one of the trigger time 1120, text content 1130, re-edit control 1140, or re-generate control 1150 corresponding to the super-resolution image may be displayed in the first display area in association with the super-resolution image 1110. Please understand that the re-edit control 1140 or re-generate control 1150 functions similarly to the re-edit control 491 or re-generate control 492, and therefore the description here is not repeated.

[0069] In some embodiments, Method 300 may further include displaying a portfolio control on the image display interface and displaying a portfolio interface on the first display area in response to a trigger operation on the portfolio control, wherein the portfolio interface includes a thumbnail corresponding to the super-resolution image, and the size ratio of the thumbnail matches that of the super-resolution image.

[0070] Specifically, refer to Figure 12, which shows a schematic diagram of a portfolio interface according to an embodiment of the present disclosure. In Figure 12, the portfolio control 1210 is used to display a collection of generated super-resolution images. The user can perform a trigger operation O12 (e.g., a click) on the portfolio control 1210, and in response to this trigger operation O12, the portfolio interface 1220 is displayed in the relevant area of ​​the portfolio control 1210. The thumbnails in the portfolio interface 1220 are sorted according to the trigger time of the corresponding super-resolution image. For example, the thumbnail of super-resolution image 1110 with the closest trigger time is sorted first, and the other thumbnails 1221-1223 are super-resolution images generated in the past and sorted in order of closest trigger time. The thumbnails have the same aspect ratio as the corresponding super-resolution image and can realistically reflect the image effect of the generated target image.

[0071] In some embodiments, Method 300 further includes popping up an image information interface on the image display interface in response to a trigger operation on the thumbnail, the image information interface may include at least one of the following: a super-resolution image corresponding to the thumbnail, text content corresponding to the super-resolution image, a target parameter corresponding to the super-resolution image, a matching production control, a posting control, or a close control.

[0072] Specifically, referring to Figures 12 and 13, the user can perform a trigger operation (e.g., a click operation) on the thumbnail 1221 in Figure 12, and in response to this trigger operation on the thumbnail 1221, the image information interface 1300 may be popped up in the image display interface 400, as shown in Figure 13, which shows a schematic diagram of the image information interface according to an embodiment of the present disclosure. The image information interface 1300 may display a super-resolution image 1310 corresponding to the thumbnail 1221, a user identifier 1320 corresponding to the super-resolution image, text content 1330 corresponding to the super-resolution image, target parameters 1340 corresponding to the super-resolution image, a matching creation control 1350, a posting control 1360, a close control 1370, and a download control 1380.

[0073] In some embodiments, Method 300 may further include, in response to a trigger operation on the matching production control, jumping to the image display interface, displaying text content corresponding to the super-resolution image in the text editing area, and setting the image effect setting control to the target parameter.

[0074] Specifically, the user can perform a trigger operation (for example, a click) on the matching production control 1350 in Figure 13. In response to this trigger operation, the system may jump to the image display interface 400 shown in Figure 12, display text content corresponding to the super-resolution image in the text editing area 410, and set the image effect setting control 420 to the target parameter corresponding to the super-resolution image.

[0075] In some embodiments, method 300 may further include posting the super-resolution image in response to a trigger operation on a posting control.

[0076] Specifically, a user can perform a trigger operation (e.g., a click) on the posting control 1360 in Figure 13, and in response to this operation, the super-resolution image 1310 may be posted. Furthermore, in response to the successful posting of the super-resolution image 1310, prompt text, such as "Posting successful," may be displayed on the image information interface 1300. In response to the unsuccessful posting of the super-resolution image 1310, prompt text, such as "Posting failed," may be displayed on the image information interface 1300.

[0077] In some embodiments, method 300 may further include closing the image information interface and positioning the thumbnail in the portfolio interface in response to a trigger operation for a close control.

[0078] Specifically, the user can perform a trigger operation (e.g., a click) on the close control 1370 in Figure 13, and in response to this trigger operation, the system may jump to the image display interface 400 shown in Figure 12 and position itself at the thumbnail 1221 in the portfolio interface 1220.

[0079] In some embodiments, method 300 may further include downloading the super-resolution image in response to a trigger operation on the download control.

[0080] Specifically, the user can perform a trigger operation (e.g., a click) on the download control 1380 in Figure 13, and in response to this operation, the super-resolution image 1310 is downloaded. Furthermore, in response to the successful download of the super-resolution image 1310, prompt text, such as "Download successful," may be displayed on the image information interface 1300. In response to the unsuccessful download of the super-resolution image 1310, prompt text, such as "Download failed," may be displayed on the image information interface 1300.

[0081] In some embodiments, the method 300 may further include displaying the historical images displayed in the first display area in the first display area, and displaying the historical images in chronological order in the first display area in response to a slide operation on the first display area.

[0082] Specifically, refer to Figure 14, which shows a schematic diagram of history images according to an embodiment of the present disclosure. In Figure 14, history images 471' to 474' and history image 1110 may be displayed in the first display area. The history images may be displayed in chronological order, and the user may perform a slide operation on the first display area to view the history images.

[0083] In some embodiments, Method 300 may further include displaying at least one type label in a second display area of ​​the image display interface, and, in response to the selection of the type label, displaying an exhibited image belonging to the image type corresponding to the selected type label in the second display area.

[0084] Specifically, referring to Figure 15, the second display area of ​​the image display interface 100 may display the exhibited images 1510 to 1560, and these exhibited images may be filtered from images posted by the current user and / or other users. All user-submitted images may be retrieved from the server side, and when a user selects one of the category labels 1501 to 1504, the server side may filter the user-submitted images belonging to this category label and send them to the image display interface 100, sort them according to predetermined rules, and present them to the user. The user can browse the exhibited images by sliding in the second display area and select and refer to exhibited images of interest from among them.

[0085] In some embodiments, displaying exhibited images belonging to the image type corresponding to the selected type label in the second display area includes scoring user-submitted images belonging to the selected image type based on image quality and user behavior data to obtain an overall score, determining user-submitted images whose overall score is equal to or greater than a score threshold as exhibited images, and sorting the exhibited images according to the overall score or submission time and displaying them in the second display area.

[0086] Here, image quality may refer to the sharpness, saturation, etc., of an image, and the image effect of a posted image can be evaluated from customer parameters. User behavior data refers to user actions such as liking, favorites, forwarding, and downloading of a posted image, indicating the degree of user interest in the posted image and reflecting the popularity of the posted image from the user's perspective. A weighted score can be obtained for the posted image based on image quality and user behavior data, and a higher overall score can be interpreted as a higher image effect for this posted image. Posted images with an overall score higher than the score threshold can be filtered and displayed to provide users with a good image data base, and users can refer to the displayed images to generate effective target images. Displayed images may be sorted in descending order of overall score, with higher overall scores ranking higher. Displayed images may also be sorted and displayed in descending order of posting time, with closer posting times ranking higher.

[0087] In some embodiments, Method 300 may further include displaying text content, matching production controls, or information controls corresponding to the display image in a relevant area of ​​the display image in response to a trigger operation on the display image, and displaying text content corresponding to the display image in the text editing area and setting the image effect setting controls to target parameters corresponding to the display image in response to a trigger operation on the matching production controls.

[0088] Specifically, refer to Figure 15, which shows a schematic diagram of an exhibit image according to an embodiment of the present disclosure. In Figure 15, a user can perform a trigger operation (e.g., a click operation) on the exhibit image 1530, and in response to this trigger operation, text content, matching production controls, or information controls corresponding to the exhibit image may be displayed in the form of a mask in the relevant area of ​​the exhibit image 1530. Here, the mask is transparent, and by displaying it in the form of a mask, the content of the exhibit image 1530 can be seen through the mask while displaying the text content "text content a, text content b, text content c, ...", matching production controls 1531, or information controls 1532. A user can perform a trigger operation on the matching production controls 1531, and in response to this trigger operation, text content "text content a, text content b, text content c, ..." corresponding to the exhibit image 1530 may be displayed in the text editing area 410, as shown in Figure 16, which shows a schematic diagram of an exhibit image according to an embodiment of the present disclosure.

[0089] In some embodiments, Method 300 further includes displaying an exhibit information interface in a relevant area of ​​the exhibit image in response to a trigger operation on the information control, the exhibit information interface may include at least one of the following: a user identifier for the exhibit image, text content corresponding to the exhibit image, a target parameter corresponding to the exhibit image, or a posting time.

[0090] Specifically, in response to a trigger operation on the information control 1532 in Figure 16, an information interface may pop up to display at least one of the following: the user identifier of the exhibited image 1530, the target parameters corresponding to the exhibited image, or the posting time.

[0091] In some embodiments, Method 300 further includes, in response to detecting the absence of a historical target image, displaying guide content on the image display interface regarding the display of the target image, wherein the guide content includes at least one of video data, picture data, GIF image data, or a text description.

[0092] Specifically, the system may detect whether a historical target image exists, determine whether the user is using the system for the first time, and if no historical target image exists, interpret this as the user potentially being a first-time user. In such cases, guide content may be displayed on the image display interface to guide the user in generating the target image. The guide content guides the user through one or more substeps, such as video data, picture data, GIF image data, or text descriptions, in various forms to help the user quickly generate the target image and further improve the efficiency of image generation. In some embodiments, the user may choose to skip this guide content.

[0093] It should be noted that the methods of the embodiments of this disclosure may be performed by a single device, such as a computer or server. Alternatively, the methods of these embodiments may be applied to a distributed scenario in which multiple devices cooperate to perform the process. In such a distributed scenario, one of these multiple devices may perform only one or more steps in the methods of the embodiments of this disclosure, while these multiple devices interact with each other to complete the described method.

[0094] Several embodiments of this disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, the operations or steps described in the claims may be performed in a different order than those described in the embodiments above, and the desired results may still be achieved. Furthermore, the processes depicted in the appended drawings do not necessarily require the specific order or sequence shown to achieve the desired results. In some embodiments, multitasking and parallel processing may be possible or advantageous.

[0095] Based on the same technical concept and corresponding to the method according to any of the above embodiments, the present disclosure further provides an image generating apparatus, referring to Figure 17, the image generating apparatus comprises a display module for displaying a text editing area and an image effect setting control on an image display interface, and a setting module for determining a target prompt based on the text content in response to editing text content in the text editing area, and for determining at least one target parameter in response to an operation on the image effect setting control, wherein the display module is further used to display a generated target image in a first display area of ​​the image display interface based on the target prompt and the target parameter.

[0096] For the sake of explanation, the above device was described by dividing it into various modules according to their function. Of course, when implementing this disclosure, it is possible to implement the functions of each module using the same or multiple software and / or hardware.

[0097] The apparatus of the above embodiment is used to implement the corresponding image generation method in any of the embodiments described above and has the beneficial effects of the corresponding method embodiment, but this description will not be repeated here.

[0098] Based on the same technical concept and corresponding to the method according to any of the above embodiments, the present disclosure further provides a non-temporary computer-readable storage medium which stores computer instructions and which is used to cause the computer to execute the image generation method described in any of the above embodiments.

[0099] The computer-readable media of this embodiment include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technique. The information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random-access memory (SRAM), dynamic random-access memory (DRAM), other types of random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROMs, digital versatile disks (DVDs) or other optical storage devices, magnetic cartridge tapes, magnetic tape magnetic disk storage devices or other magnetic storage devices, or any other non-transferable media that can be used to store information that can be accessed by a computer.

[0100] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the image generation method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiment, so the explanation will not be repeated here.

[0101] It should be understood by those ordinary in the art that any discussion of any of the above embodiments is merely illustrative and does not mean that the scope of the present disclosure (including the claims) is limited to these examples, that it is possible to combine the technical features in the above embodiments or different embodiments within the concept of the present disclosure, that the steps may be carried out in any order, and that, as stated above, there are many other variations in different aspects of the embodiments of the present disclosure, which are not provided in detail for the sake of brevity.

[0102] Furthermore, for the sake of simplifying the explanation and discussion, and to avoid complicating the understanding of the embodiments of this disclosure, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the accompanying drawings provided. In addition, to avoid complicating the understanding of the embodiments of this disclosure, devices may be shown in the form of block diagrams, taking into account the fact that details relating to embodiments of devices in these block diagrams are largely dependent on the platform on which the embodiments of this disclosure are implemented (i.e., these details should be within the understanding of those skilled in the art). Where certain details (e.g., circuits) are described to illustrate exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure may be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0103] This disclosure has been described in conjunction with specific embodiments thereof, and many substitutions, modifications, and variations of these embodiments will be obvious to an ordinary person of the art based on the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can be used with the embodiments discussed.

[0104] The embodiments of this disclosure are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this disclosure shall be covered within the scope of this disclosure.

Claims

1. Display a text editing area and image effect setting controls in the image display interface, In response to editing text content in the text editing area, a target prompt is determined based on the text content. In response to an operation on the aforementioned image effect setting control, at least one target parameter is determined, Based on the target prompt and the target parameters, the generated target image is displayed in the first display area of ​​the image display interface. An image generation method, including the following.

2. Determining at least one target parameter in response to an operation on the aforementioned image effect setting control is: In response to a trigger operation on the image effect setting control, an image effect setting interface is displayed in the relevant area of ​​the image effect setting control, wherein the image effect setting interface includes at least one predetermined condition. In response to a selection operation for the predetermined conditions, the selected condition parameter is determined as the target parameter, wherein the image effect setting interface includes at least one of the following: style model conditions, ratio conditions, degree of stylization conditions, or detail conditions. The method according to claim 1, including the method described in claim 1.

3. The style model condition includes at least one predetermined style model parameter, and the target parameter includes a target style model. In response to a selection operation for the predetermined conditions, determining the selected condition parameter as the target parameter is: The process includes determining the selected predetermined style model as the target style model in response to a selection operation for the predetermined style model. The method according to claim 2.

4. Displaying the generated target image in the first display area of ​​the image display interface based on the target prompt and the target parameters is: Displaying an initial image in the first display area, To generate a target image based on the target prompt and the target parameters, The target image is displayed in the area of ​​the initial image, The method according to claim 1, including the method described in claim 1.

5. Displaying an initial image in the first display area is, To generate the initial image based on the semantic information of the target prompt, or to search an image database based on the target prompt and obtain a predetermined number of initial images that match the meaning of the target prompt, In order to display the initial image, the predetermined number of regions in the first display region are determined, The method according to claim 4, including the method described in claim 4.

6. Displaying the target image in the region of the initial image means The process includes displaying an animation in the first display area in which the initial image changes to the target image. The method according to claim 4.

7. The further includes displaying in the first display area, in association with the target image, a trigger time for generating the target image, the text content, the target parameters, and at least one of a re-edit control or a re-generate control. The method according to claim 1.

8. In response to the trigger operation on the re-edit control, the text content is displayed in the text editing area, and the image effect setting control is set to the target parameter, or, In response to a trigger operation for the regenerate control, a new target image generated based on the target prompt and the target parameters is displayed in the first display area, and at least one of the trigger time, the text content, the target parameters, the re-edit control, or the regenerate control corresponding to the new target image is displayed in the first display area in association with the new target image. The method according to claim 7, further comprising:

9. In response to a trigger operation on the target image, a super-resolution image corresponding to the target image is displayed in the first display area, and at least one of the trigger time, text content, target parameters, re-edit control, or re-generate control corresponding to the super-resolution image is displayed in the first display area in association with the super-resolution image. The method according to claim 1.

10. Displaying portfolio control on the aforementioned image display interface, In response to a trigger operation on the portfolio control, a portfolio interface is displayed in the first display area, wherein the portfolio interface includes a thumbnail corresponding to the super-resolution image, and the size ratio of the thumbnail matches that of the super-resolution image. The method according to claim 9, further comprising:

11. The method further includes popping up an image information interface on the image display interface in response to a trigger operation on the thumbnail, The image information interface includes at least one of the following: a super-resolution image corresponding to the thumbnail, text content corresponding to the super-resolution image, a target parameter corresponding to the super-resolution image, a matching creation control, a posting control, or a close control. The method according to claim 10.

12. In response to a trigger operation on the aforementioned matching production control, the system jumps to the image display interface, displays text content corresponding to the super-resolution image in the text editing area, and sets the image effect setting control to the target parameter. Or, In response to a trigger operation on the posting control, the super-resolution image is posted. Or, In response to a trigger operation for the close control, the image information interface is closed and positioned in the portfolio interface where the thumbnail is located. The method according to claim 11, further comprising:

13. Displaying the history images displayed in the first display area in the first display area, In response to a slide operation on the first display area, the history images are displayed in the first display area in chronological order. The method according to claim 1, further comprising:

14. The image display interface will display a random text control, The method further includes: inputting randomly generated random text into the text editing area in response to a trigger operation on the random text control; and determining the target style model of the target image based on the style corresponding to the random text. Or, Displaying an extended text control on the aforementioned image display interface, Further including, in response to a trigger operation on the extended text control, supplementing the text editing area with new text content based on the text content within the text editing area, The method according to claim 1.

15. Display at least one type label in the second display area of ​​the image display interface, In response to the selection of the type label, the display image belonging to the image type corresponding to the selected type label is displayed in the second display area. The method according to claim 1, further comprising:

16. In response to a trigger operation on the aforementioned display image, text content, matching production controls, or information controls corresponding to the aforementioned display image are displayed in the relevant area of ​​the aforementioned display image. In response to a trigger operation on the aforementioned matching production control, text content corresponding to the display image is displayed in the text editing area, and the image effect setting control is set to the target parameter corresponding to the display image. Or, In response to a trigger operation on the information control, display an exhibition information interface in the relevant area of ​​the exhibition image, wherein the exhibition information interface includes at least one of the following: the user identifier of the exhibition image, the text content corresponding to the exhibition image, the target parameter corresponding to the exhibition image, or the posting time. The method according to claim 15, further comprising:

17. Displaying an exhibited image belonging to the image type corresponding to the selected type label in the second display area is: The user-submitted images belonging to the selected image type are scored based on image quality and user behavior data, and an overall score is obtained. The user-submitted images whose overall score is equal to or greater than the score threshold are selected as the display images. The exhibited images are sorted according to the overall score or posting time and displayed in the second display area. The method according to claim 14, including the method described in claim 14.

18. A display module for displaying a text editing area and image effect setting controls in the image display interface, The system includes a setting module for determining a target prompt based on text content in response to editing text content in the text editing area, and for determining at least one target parameter in response to an operation on the image effect setting control, The display module is further used to display the generated target image in a first display area of ​​the image display interface based on the target prompt and the target parameters. Image generation device.

19. The system comprises memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the method according to any one of claims 1 to 17. electronic equipment.

20. A computer instruction is stored which causes the computer to perform the method described in any one of claims 1 to 17. A non-temporary computer-readable storage medium.

21. A computer program product that is stored in a computer storage medium as a tangible object and includes computer executable instructions, When executed by a device, a computer executable instruction causes the device to perform the method described in any one of claims 1 to 17. Computer program products.

Images