Image generation method and device, electronic equipment and storage medium

Abstract

The invention relates to an image generation method and device, electronic equipment and a storage medium. The method comprises the steps that a preset page comprising at least one kind of image reference information is displayed; in response to a reference image selection operation for first image reference information, determining at least one reference image corresponding to the first image reference information, the first image reference information being any one piece of image reference information in the at least one piece of image reference information; in response to the image generation operation, displaying at least one generated image, the at least one generated image being generated based on target reference information corresponding to each of a plurality of target reference images, the plurality of target reference images being reference images determined when the image generation operation is triggered, the plurality of target reference images correspond to one or more pieces of image reference information in the at least one piece of image reference information. According to the embodiment of the invention, a user can flexibly and conveniently select the image reference information and the corresponding reference image, so that the image generation effect is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to an image generation method, device, electronic device, and storage medium. Background Art

[0002] Image generation is an important research direction in the field of computer vision and artificial intelligence. It breaks through the limitations of traditional image creation and can generate customized visual content based on text, images or other modal inputs.

[0003] In related image generation technology, usually only a single reference image can be selected for image generation, which limits the diversity of image generation capabilities, resulting in poor image generation effects, and thus affecting the user experience. Summary of the Invention

[0004] The present disclosure provides an image generation method, device, electronic device, and storage medium to at least address the technical issues in related technologies such as the ability to select only a single reference image for image generation, which limits the diversity of image generation, resulting in poor image generation results and thus affecting the user experience. The technical solutions of the present disclosure are as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided an image generation method, comprising:

[0006] displaying a preset page including at least one image reference information;

[0007] In response to a reference image selection operation for first image reference information, determining at least one reference image corresponding to the first image reference information, where the first image reference information is any one of the at least one image reference information;

[0008] In response to an image generation operation, at least one generated image is displayed, where the at least one generated image is generated based on target reference information corresponding to each target reference image in a plurality of target reference images, where the plurality of target reference images are reference images determined when the image generation operation is triggered, and the plurality of target reference images correspond to one or more image reference information in the at least one image reference information, where the target reference information corresponding to each target reference image is image information in each target reference image that matches the image reference information corresponding to each target reference image.

[0009] In an optional embodiment, the multiple target reference images include: a second reference image, and the method further includes:

[0010] In response to an editing operation on a first reference image, the first reference image is updated to the second reference image, where the first reference image is any reference image among the at least one reference image, and the second reference image is obtained by image editing the first reference image.

[0011] In an optional embodiment, the method further includes:

[0012] In response to the reference image selection operation, displaying at least one reference image corresponding to the first image reference information on the preset page;

[0013] In response to a selection operation on the first reference image in the preset page, displaying an editing entry control corresponding to the first reference image;

[0014] In response to an editing area display operation triggered by the editing entry control, displaying a first editing area corresponding to the first reference image;

[0015] In response to the editing operation on the first reference image, updating the first reference image to the second reference image includes:

[0016] In response to the editing operation triggered based on the first editing area, the first reference image is updated to the second reference image in the preset page.

[0017] In an optional embodiment, the method further includes:

[0018] In response to a reference image confirmation operation on the at least one reference image, displaying a first editing area corresponding to the first reference image;

[0019] In response to the editing operation on the first reference image, updating the first reference image to the second reference image includes:

[0020] In response to the editing operation triggered based on the first editing area, the first reference image is updated to the second reference image.

[0021] In an optional embodiment, the at least one image reference information includes: multiple image reference information, and before displaying the preset page including the at least one image reference information, the method further includes:

[0022] Displaying initial image reference information on the preset page; the initial image reference information is any image reference information among the multiple image reference information;

[0023] The preset page displaying at least one image reference information includes:

[0024] In response to a reference information switching operation, the initial image reference information in the preset page is updated to image reference information corresponding to the reference information switching operation among the multiple image reference information.

[0025] In an optional embodiment, the preset page displaying at least one image reference information includes:

[0026] Displaying the preset page;

[0027] In response to a reference information adding operation triggered based on the preset page, the at least one image reference information is displayed in the preset page.

[0028] In an optional embodiment, the at least one image reference information includes: multiple image reference information, the multiple target reference images include: at least one reference image corresponding to the first image reference information and at least one reference image corresponding to second image reference information, the second image reference information being one of the multiple image reference information other than the first image reference information, and before displaying at least one generated image in response to the image generation operation, the method further includes:

[0029] In response to a reference image selection operation for the second image reference information, at least one reference image corresponding to the second image reference information is determined.

[0030] In an optional embodiment, the at least one reference image corresponding to the first image reference information includes: a plurality of reference images corresponding to the first image reference information, and the displaying of the at least one generated image in response to the image generation operation includes:

[0031] In response to the image generation operation being triggered based on the plurality of reference images, the at least one generated image is presented.

[0032] In an optional embodiment, before displaying at least one generated image in response to the image generation operation, the method further includes:

[0033] Displaying an image display area corresponding to each of at least one image reference information and a plurality of recommended reference image groups on the preset page, wherein the plurality of recommended reference images in each recommended reference image group corresponds to one or more image reference information in the at least one image reference information;

[0034] In response to the recommended image group selection operation, the target recommended image in the target recommended reference image group is displayed in the image display area corresponding to the target image reference information, the target recommended reference image group is any recommended reference image group among the multiple recommended reference image groups, the target recommended image is any recommended reference image among the multiple recommended reference images of the target recommended reference image group, and the target image reference information is the image reference information corresponding to the target recommended image in the at least one image reference information.

[0035] In an optional embodiment, the at least one image reference information includes: multiple image reference information, the preset page includes image display areas corresponding to the multiple image reference information respectively, and before displaying at least one generated image in response to the image generation operation, the method further includes:

[0036] In response to a reference image selection operation for the first image reference information, displaying at least one reference image corresponding to the first image reference information in an image display area corresponding to the first image reference information;

[0037] In response to an image move operation on a third reference image, the third reference image is canceled from the image display area corresponding to the first image reference information, and the third reference image is displayed in the image display area corresponding to the third image reference information, so as to update the image reference information corresponding to the third reference image from the first image reference information to the third image reference information, wherein the third reference image is any reference image among the at least one reference image, and the third image reference information is one of the multiple image reference information except the first image reference information.

[0038] In an optional embodiment, the method further includes:

[0039] If the first number of reference images determined when the image generation operation is triggered is less than the preset number, an image upload prompt message is displayed, and the image upload prompt message is used to prompt to continue uploading at least a second number of reference images corresponding to the fourth image reference information, where the fourth image reference information is one or more image reference information among the at least one image reference information, and the second number is the difference between the preset number and the first number.

[0040] According to a second aspect of an embodiment of the present disclosure, there is provided an image generating apparatus, including:

[0041] A preset page display module is configured to display a preset page including at least one image reference information;

[0042] a first reference image determination module configured to perform a reference image selection operation in response to first image reference information, and determine at least one reference image corresponding to the first image reference information, wherein the first image reference information is any one of the at least one image reference information;

[0043] A generated image display module is configured to execute, in response to an image generation operation, display at least one generated image, wherein the at least one generated image is generated based on target reference information corresponding to each target reference image in a plurality of target reference images, the plurality of target reference images being reference images determined when the image generation operation is triggered, and the plurality of target reference images corresponding to one or more image reference information in the at least one image reference information, and the target reference information corresponding to each target reference image being image information in each target reference image that matches the image reference information corresponding to each target reference image.

[0044] In an optional embodiment, the multiple target reference images include: a second reference image, and the apparatus further includes:

[0045] The image editing module is configured to execute an editing operation on a first reference image, updating the first reference image to the second reference image, wherein the first reference image is any reference image among the at least one reference image, and the second reference image is obtained by image editing the first reference image.

[0046] In an optional embodiment, the device further comprises:

[0047] a first image display module configured to display at least one reference image corresponding to the first image reference information on the preset page in response to the reference image selection operation;

[0048] an editing entry display module, configured to display an editing entry control corresponding to the first reference image in response to a selection operation on the first reference image in the preset page;

[0049] A first editing area display module is configured to execute an editing area display operation in response to being triggered based on the editing entry control, and to display a first editing area corresponding to the first reference image;

[0050] The image editing module includes:

[0051] The first image editing unit is configured to execute the editing operation triggered based on the first editing area, and update the first reference image to the second reference image in the preset page.

[0052] In an optional embodiment, the device further comprises:

[0053] a second editing area display module configured to display a first editing area corresponding to the first reference image in response to a reference image confirmation operation on the at least one reference image;

[0054] The image editing module includes:

[0055] The second image editing unit is configured to execute, in response to the editing operation triggered based on the first editing area, updating the first reference image to the second reference image.

[0056] In an optional embodiment, the at least one image reference information includes: multiple image reference information, and the apparatus further includes:

[0057] An initial image reference information display module is configured to display initial image reference information on the preset page; the initial image reference information is any image reference information among the multiple types of image reference information;

[0058] The preset page display module includes:

[0059] The reference information switching unit is configured to execute, in response to a reference information switching operation, updating the initial image reference information in the preset page to image reference information corresponding to the reference information switching operation among the multiple image reference information.

[0060] In an optional embodiment, the preset page display module includes:

[0061] A preset page display unit, configured to display the preset page;

[0062] The reference information adding unit is configured to execute a reference information adding operation in response to being triggered based on the preset page, and to display the at least one image reference information in the preset page.

[0063] In an optional embodiment, the at least one image reference information includes: multiple image reference information, the multiple target reference images include: at least one reference image corresponding to the first image reference information and at least one reference image corresponding to second image reference information, the second image reference information being one of the multiple image reference information other than the first image reference information, and the apparatus further includes:

[0064] The second reference image determination module is configured to perform a reference image selection operation in response to the second image reference information, and determine at least one reference image corresponding to the second image reference information.

[0065] In an optional embodiment, the at least one reference image corresponding to the first image reference information includes: multiple reference images corresponding to the first image reference information, and the image display generation module includes:

[0066] The generated image display unit is configured to perform the image generation operation triggered in response to the plurality of reference images and display the at least one generated image.

[0067] In an optional embodiment, the device further comprises:

[0068] a recommended reference image group display module configured to display, on the preset page, image display areas corresponding to at least one image reference information and a plurality of recommended reference image groups, wherein the plurality of recommended reference images in each recommended reference image group corresponds to one or more image reference information in the at least one image reference information;

[0069] The target recommended image display module is configured to execute a target recommended image in a target recommended reference image group in an image display area corresponding to the target image reference information in response to a recommended image group selection operation, wherein the target recommended reference image group is any recommended reference image group among the multiple recommended reference image groups, the target recommended image is any recommended reference image among the multiple recommended reference images of the target recommended reference image group, and the target image reference information is image reference information corresponding to the target recommended image in the at least one image reference information.

[0070] In an optional embodiment, the at least one image reference information includes: multiple image reference information, the preset page includes image display areas corresponding to the multiple image reference information respectively, and the device further includes:

[0071] a second image display module configured to perform a reference image selection operation in response to the first image reference information, and display at least one reference image corresponding to the first image reference information in an image display area corresponding to the first image reference information;

[0072] The third image display module is configured to execute, in response to an image movement operation on a third reference image, cancel the display of the third reference image in the image display area corresponding to the first image reference information, and display the third reference image in the image display area corresponding to the third image reference information, so as to update the image reference information corresponding to the third reference image from the first image reference information to the third image reference information, wherein the third reference image is any reference image among the at least one reference image, and the third image reference information is an image reference information among the multiple image reference information except the first image reference information.

[0073] In an optional embodiment, the device further comprises:

[0074] The prompt information display module is configured to display image upload prompt information if the first number of reference images determined when the image generation operation is triggered is less than a preset number, wherein the image upload prompt information is used to prompt to continue uploading at least a second number of reference images corresponding to fourth image reference information, the fourth image reference information being one or more image reference information among the at least one image reference information, and the second number being the difference between the preset number and the first number.

[0075] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a method as described in any one of the first aspects above.

[0076] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any one of the image generation methods of the embodiments of the present disclosure.

[0077] According to a fifth aspect of an embodiment of the present disclosure, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the method as described in any one of the above-mentioned first aspects.

[0078] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:

[0079] The present application can display a preset page including at least one image reference information in a picture-generated image scene. In response to a reference image selection operation for the first image reference information, at least one reference image corresponding to the first image reference information is determined. The first image reference information is any image reference information among the at least one image reference information. The user can flexibly and conveniently select the image reference information and its corresponding reference image. In response to an image generation operation, at least one generated image is displayed. The at least one generated image is generated based on target reference information corresponding to each target reference image among multiple target reference images. The multiple target reference images are reference images determined when the image generation operation is triggered. The multiple target reference images correspond to one or more image reference information among the at least one image reference information. The target reference information corresponding to each target reference image is image information in each target reference image that matches the image reference information corresponding to each target reference image. Image generation is performed based on the target reference information corresponding to the multiple target reference images selected by the user. This can accurately and efficiently control the image generation process, improve the customization and diversification of the picture-generated image, and thereby enhance the user experience and willingness to use.

[0080] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0082] Figure 1 is a schematic diagram of an application environment provided by an embodiment of the present application;

[0083] Figure 2 This is a flowchart of an image generation method provided by an embodiment of the present application;

[0084] Figure 3a This is a schematic diagram of a preset page provided by an embodiment of the present application showing reference images corresponding to multiple image reference information;

[0085] Figure 3b This is a schematic diagram of a preset page provided by an embodiment of the present application showing multiple reference images corresponding to single image reference information;

[0086] Figure 4a-4c is a schematic diagram of a reference image editing provided by an embodiment of the present application;

[0087] Figure 5a-5c is a schematic diagram of another reference image editing method provided by an embodiment of the present application;

[0088] Figure 6a-6c is a schematic diagram of switching image reference information provided by an embodiment of the present application;

[0089] Figure 6d-6f This is a schematic diagram of adding image reference information provided by an embodiment of the present application;

[0090] Figure 7a-7c This is a schematic diagram showing a recommended reference image group provided by an embodiment of the present application;

[0091] Figure 8 is a schematic diagram of a reference image movement provided by an embodiment of the present application;

[0092] Figure 9 This is a block diagram of an image generation device provided in an embodiment of the present application;

[0093] Figure 10 This is a block diagram of an electronic device for image generation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0094] In order to enable ordinary people in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0095] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish between similar and different contents, and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.

[0096] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0097] See also Figure 1 , Figure 1 FIG1 is a schematic diagram showing an application environment according to an exemplary embodiment. The application environment may include a terminal 100 and a server 200 .

[0098] In an optional embodiment, the terminal 100 can be used to provide image generation and other services to any user. Specifically, the terminal 100 may include, but is not limited to, electronic devices such as smartphones, desktop computers, tablet computers, laptop computers, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. It may also be software running on these electronic devices, such as applications. Optionally, the operating system running on the electronic device may include, but is not limited to, Android, iOS, Linux, Windows, etc.

[0099] In an optional embodiment, the server 200 may provide background services for the terminal 100. Specifically, the server 200 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0100] In addition, it should be noted that Figure 1 What is shown is only one application environment provided by the present disclosure. In actual applications, other application environments may also be included, for example, more terminals may be included.

[0101] In the embodiments of this specification, the terminal 100 and the server 200 may be directly or indirectly connected via wired or wireless communication, which is not limited in this disclosure.

[0102] Figure 2 is a flow chart of an image generation method according to an exemplary embodiment. Figure 2 As shown, the method may include the following steps:

[0103] In step S201, a preset page including at least one image reference information is displayed;

[0104] In step S202, in response to a reference image selection operation for first image reference information, at least one reference image corresponding to the first image reference information is determined, where the first image reference information is any one of the at least one image reference information;

[0105] In step S203, in response to the image generation operation, at least one generated image is displayed, and the at least one generated image is generated based on the target reference information corresponding to each target reference image in a plurality of target reference images, the plurality of target reference images are reference images determined when the image generation operation is triggered, and the plurality of target reference images correspond to one or more image reference information in at least one image reference information, and the target reference information corresponding to each target reference image is image information in each target reference image that matches the image reference information corresponding to each target reference image.

[0106] In a specific embodiment, the preset page may be a page for implementing an image generation function. Optionally, the preset page may be a page that provides the image generation function in a preset application or a preset network platform. Specifically, the preset page may display at least one type of image reference information, each type of image reference information being used to indicate a reference dimension for a corresponding reference image when controlling the image generation process. The at least one type of image reference information may be at least one type of preset image reference information provided by the image generation system where the preset page is located. Optionally, the at least one type of image reference information may be at least one type of preset image reference information displayed by the image generation system by default, or may be at least one type of preset image reference information customized by the user.

[0107] In a specific embodiment, the multiple preset image reference information can be pre-set in combination with the image generation control requirements in actual applications. The multiple preset image reference information is used to indicate different image reference dimensions to control the image generation process from different image reference dimensions. Schematically, the multiple preset image reference information may include but is not limited to: subject reference information (indicating control of the image generation process from the subject dimension), scene reference information (indicating control of the image generation process from the scene dimension), style reference information (indicating control of the image generation process from the style dimension), shot reference information (indicating control of the image generation process from the shot dimension), lens angle reference information (indicating control of the image generation process from the lens angle dimension), visual composition reference information (indicating control of the image generation process from the visual composition dimension), color / light and shadow reference information (indicating control of the image generation process from the color / light and shadow dimension), posture reference information (indicating control of the image generation process from the posture dimension), sketch reference information (indicating control of the image generation process from the sketch dimension), etc.

[0108] In a specific embodiment, the reference image selection operation can be used to select a reference image corresponding to the first image reference information, wherein the first image reference information can be any image reference information from at least one image reference information. Specifically, a preset page displays an image display area corresponding to at least one reference image. Optionally, the user can implement a reference image selection operation for the first image reference information by moving at least one image (e.g., by dragging at least one image) to the image display area corresponding to the first image reference information, thereby determining the moved at least one image as the at least one reference image corresponding to the first image reference information. The user can also trigger an image library display operation by clicking or long pressing the image display area corresponding to the first image reference information, thereby displaying an image library including multiple candidate reference images to the user. The user can implement a reference image selection operation for the first image reference information by clicking, long pressing, or checking at least one candidate reference image in the image library, thereby determining the selected at least one candidate reference image as the at least one reference image corresponding to the first image reference information.

[0109] In an optional embodiment, at least one reference image includes at least one image from at least one original image and / or at least one image from at least one historically generated image. Specifically, the original image may be a non-AI generated image, and the historically generated image may be a historical image created by an image generation function of a user account that triggers a reference image selection operation. Schematically, the above-mentioned image library may include: an original image library and a historically generated image library. Accordingly, the user may determine at least one reference image from the original image library and / or the historically generated image library.

[0110] In an optional embodiment, taking into account the limited memory and computing power of the image generation system, in order to balance image generation efficiency and user experience, an upper limit threshold of the reference images determined when a single image generation operation is triggered can be pre-set. If the number of reference images determined based on the reference image selection operation reaches the upper limit threshold, other candidate reference images are controlled to be disabled, and the user is prompted that the number of reference images currently determined has reached the upper limit threshold.

[0111] In an optional embodiment, different reference image upper limit thresholds can be set for different image reference information in combination with the image generation control requirements in actual applications. Schematically, the reference image upper limit threshold of the subject reference information can be greater than or equal to 2. Image generation is controlled by multiple subject reference images (i.e., multiple reference images corresponding to the subject reference information) to generate a generated image including multiple subjects (i.e., subjects in multiple subject reference images) to meet the user's subject synthesis requirements for different images. The reference image upper limit threshold of the lens angle reference information can be set to 1 to avoid the image generation system controlling image generation according to multiple reference lens angles, resulting in perspective distortion of the generated image, poor image quality, and affecting the user's experience.

[0112] In an optional embodiment, in order to ensure the security and compliance of the reference image selected by the user, the image generation system may perform an image safety check on the at least one reference image after determining the at least one reference image corresponding to the first image reference information, and only display the reference image that passes the image safety check among the at least one reference image.

[0113] In a specific embodiment, the image generation operation is used to generate an image based on a reference image determined when the image generation operation is triggered. Optionally, the image generation operation can be any operation, including but not limited to touch operation, voice operation, operation through an input device such as a mouse, or gesture operation. Schematically, an image generation control is displayed in the preset page, and the image generation control is used to trigger the image generation operation. Accordingly, the user can trigger the image generation operation by clicking, long pressing the image generation control, and other operations.

[0114] In a specific embodiment, at least one generated image is generated based on the target reference information corresponding to each target reference image in a plurality of target reference images, where the target reference information corresponding to each target reference image is image information in each target reference image that matches the image reference information corresponding to each target reference image. It can be understood that each image reference information is used to indicate the reference dimension of the corresponding reference image when controlling the image generation process. Accordingly, the target reference information corresponding to each target reference image is also the image information corresponding to its own reference dimension in each target reference image. Schematically, the plurality of target reference images are target reference image 1 and target reference image 2, the image reference information corresponding to target reference image 1 is the subject reference information, and the image reference information corresponding to target reference image 2 is the scene reference information. Then, the target reference information corresponding to target reference image 1 is the image information corresponding to the subject dimension in target reference image 1 (i.e., subject information), and the target reference information corresponding to target reference image 2 is the image information corresponding to the scene dimension in target reference image 2 (i.e., scene information). Accordingly, image generation is controlled based on the subject information in target reference image 1 and the scene information in target reference image 2 to obtain at least one generated image.

[0115] In a specific embodiment, a pre-trained image generation model is deployed in the image generation system. Displaying at least one generated image in response to an image generation operation may include: inputting multiple target reference images determined when the image generation operation is triggered into the image generation model in response to the image generation operation, controlling image generation based on target reference information corresponding to each of the multiple target reference images, obtaining at least one generated image, and displaying the at least one generated image to a user. Specifically, the image generation model may be any artificial intelligence model in the prior art that can generate images based on multiple reference images. This application does not specifically limit the model architecture of the image generation model.

[0116] In an optional embodiment, the at least one generated image can be displayed directly on the preset page, or displayed on the upper layer of the preset page in the form of a pop-up window, or displayed on the image display page switched from the preset page. This application does not impose any special restrictions on this.

[0117] In a specific embodiment, the multiple target reference images are reference images determined when the image generation operation is triggered, and the multiple target reference images correspond to one or more image reference information in the at least one image reference information. Optionally, the multiple target reference images may be multiple reference images corresponding to a single image reference information in the at least one image reference information, or may be at least one reference image corresponding to each of multiple image reference information in the at least one image reference information. Schematically, the at least one image reference information may include: subject reference information, scene reference information, and style reference information. The multiple target reference images may be multiple subject reference images (i.e., reference images corresponding to the subject reference information), or multiple scene reference images (i.e., reference images corresponding to the scene reference information), or multiple style reference images (i.e., reference images corresponding to the style reference information); or may be an image combination of at least one subject reference image and at least one scene reference image, or an image combination of at least one subject reference image and at least one style reference image, or an image combination of at least one style reference image and at least one scene reference image, or an image combination of at least one subject reference image, at least one scene reference image, and at least one style reference image.

[0118] In the above embodiment, a preset page including at least one image reference information can be displayed in the image generation scene. In response to a reference image selection operation for the first image reference information, at least one reference image corresponding to the first image reference information is determined. The first image reference information is any image reference information from the at least one image reference information. The user can flexibly and conveniently select the image reference information and its corresponding reference image. In response to the image generation operation, at least one generated image is displayed. The at least one generated image is generated based on the target reference information corresponding to each target reference image in a plurality of target reference images. The plurality of target reference images are reference images determined when the image generation operation is triggered. The plurality of target reference images correspond to one or more image reference information from the at least one image reference information. The target reference information corresponding to each target reference image is image information in each target reference image that matches the image reference information corresponding to each target reference image. Image generation is performed based on the target reference information corresponding to the plurality of target reference images selected by the user. This allows for precise and efficient control of the image generation process, improved customization and diversification of the image generation, and thereby enhanced user experience and willingness to use.

[0119] In an optional embodiment, the at least one image reference information includes: multiple image reference information, the multiple target reference images include: at least one reference image corresponding to the first image reference information and at least one reference image corresponding to the second image reference information, the second image reference information being one of the multiple image reference information other than the first image reference information. Before displaying the at least one generated image in response to the image generation operation, the method further includes:

[0120] In response to a reference image selection operation for the second image reference information, at least one reference image corresponding to the second image reference information is determined.

[0121] Specifically, the reference images determined when the image generation operation is triggered include at least one reference image corresponding to the first image reference information and at least one reference image corresponding to the second image reference information. Accordingly, image generation can be performed based on the at least one reference image corresponding to the first image reference information and the at least one reference image corresponding to the second image reference information.

[0122] Specifically, the detailed content of "in response to the reference image selection operation for the second image reference information, determining at least one reference image corresponding to the second image reference information" here is similar to the detailed content of "in response to the reference image selection operation for the first image reference information, determining at least one reference image corresponding to the first image reference information" in the above step S202, and will not be repeated here.

[0123] Figure 3a This is a schematic diagram of a preset page provided by an embodiment of the present application showing reference images corresponding to multiple image reference information, see Figure 3a , the preset page displays subject reference information 301 and scene reference information 302, and a subject reference image (i.e., a reference image corresponding to the subject reference image) 304 is displayed in the image display area 303 corresponding to the subject reference information 301, and a scene reference image (i.e., a reference image corresponding to the scene reference image) 306 is displayed in the image display area 305 corresponding to the scene reference information 302. The user can trigger an image generation operation based on the subject reference image 304 and the scene reference image 306.

[0124] In the above embodiment, the image generation operation is triggered based on the reference image corresponding to the multiple image reference information. The image generation process can be controlled through multi-dimensional reference information, further improving the accuracy and diversity of the image generation, thereby improving the user experience and willingness to use.

[0125] In an optional embodiment, the at least one reference image corresponding to the first image reference information includes: a plurality of reference images corresponding to the first image reference information, and the displaying of the at least one generated image in response to the image generation operation includes:

[0126] At least one generated image is presented in response to an image generation operation triggered based on the plurality of reference images.

[0127] Specifically, the reference images determined when the image generation operation is triggered include multiple reference images corresponding to the first image reference information. Accordingly, image generation can be performed based on multiple reference images of a single image reference information.

[0128] Figure 3b This is a schematic diagram of a preset page showing multiple reference images corresponding to a single image reference information provided by an embodiment of the present application, see Figure 3b The preset page displays subject reference information 301, and the image display area 303 corresponding to the subject reference information 301 displays a subject reference image (i.e., a reference image corresponding to the subject reference image) 304 and a subject reference image 307. The user can trigger an image generation operation based on the subject reference images 304 and 307.

[0129] In the above embodiment, image generation is controlled by multiple reference images in a single reference dimension, thereby improving the control accuracy of the image generation process in a single image dimension, further improving the accuracy of image generation, and thus improving user experience and willingness to use.

[0130] In an optional embodiment, the multiple target reference images include a second reference image, and the method may further include:

[0131] In response to an editing operation on a first reference image, the first reference image is updated to a second reference image, where the first reference image is any reference image of at least one reference image, and the second reference image is obtained by image editing the first reference image.

[0132] In a specific embodiment, the editing operation can be used to perform image editing processing on the first reference image. Optionally, the editing function types of the editing operation can include but are not limited to: picture framing operation, size adjustment operation, element elimination operation, color adjustment operation, image quality restoration operation, etc. In an optional embodiment, the operation type of the editing operation can be determined based on the image reference information (reference dimension) corresponding to the first reference image. For example, if the first reference image is a reference image corresponding to the subject reference information, the editing operation can be a subject framing operation. If the first reference image is a reference image corresponding to the color / light and shadow reference information, the editing operation can be a color adjustment operation.

[0133] In the above embodiment, multi-reference image selection is combined with single reference image editing. Different editing operations can be performed on reference images corresponding to different image reference information. By improving the single reference image for editing processing, the reference quality of the single reference image is improved. Subsequently, the image generation process can be accurately and efficiently controlled to improve the image quality, thereby improving the user experience.

[0134] In an optional embodiment, the above method further includes:

[0135] In response to the reference image selection operation, displaying at least one reference image corresponding to the first image reference information on a preset page;

[0136] In response to a selection operation on a first reference image in a preset page, displaying an editing entry control corresponding to the first reference image;

[0137] In response to an editing area display operation triggered by an editing entry control, displaying a first editing area corresponding to the first reference image;

[0138] In response to the editing operation on the first reference image, updating the first reference image to the second reference image includes:

[0139] In response to an editing operation triggered based on the first editing area, the first reference image is updated to a second reference image in the preset page.

[0140] In a specific embodiment, a selection operation on a first reference image can be used to trigger the display of an edit entry control corresponding to the first reference image. The selection operation can be configured based on the actual application; optionally, the selection operation can be any operation, including but not limited to touch operation, voice operation, operation via an input device such as a mouse, or gesture operation. Optionally, the edit entry control corresponding to the first reference image can be displayed above the area where the first reference image is located, or can be displayed around the area where the first reference image is located.

[0141] In a specific embodiment, the editing entry control is used to trigger the editing area display operation to display the first editing area corresponding to the first reference image. Optionally, the first editing area can be displayed directly in the preset page, or displayed in the upper layer of the preset page in the form of a pop-up window, etc., or displayed in the image editing page switched from the preset page. This application does not impose any special limitations on this.

[0142] In a specific embodiment, a first reference image and editing function controls of at least one editing function type are displayed in the first editing area. In response to an editing operation triggered by any editing function control in the first editing area, the first reference image is edited to obtain a second reference image, and the first reference image is updated to the second reference image in the preset page.

[0143] In an optional embodiment, an image replacement control is also displayed in the first editing area. Accordingly, in response to the image replacement operation triggered based on the image replacement control, the replacement reference image is determined, and the first reference image is updated to the replacement reference image. The detailed content of "determining the replacement reference image" here is similar to the detailed content of "determining at least one reference image corresponding to the first image reference information" in the above step S202, and will not be repeated here.

[0144] In an optional embodiment, an image deletion control is further displayed in the first editing area. Accordingly, in response to an image deletion operation triggered by the image deletion control, the first reference image is cancelled from the preset page.

[0145] In an optional embodiment, the at least one reference image corresponding to the first image reference information includes multiple reference images. In response to an editing area display operation triggered by an editing entry control, the identification information of the first editing area corresponding to the first reference image and at least one other reference image are displayed. The at least one other reference image is a reference image other than the first reference image among the multiple reference images. In response to a selection operation for the identification information of a fourth reference image, the first editing area corresponding to the first reference image is updated to the second editing area corresponding to the fourth reference image, so that the fourth reference image can be directly edited. The fourth reference image can be any other reference image among the at least one other reference image. Specifically, the identification information corresponding to each other reference image is used to identify the corresponding other reference image. Optionally, the identification information here may include but is not limited to: image number, image name, thumbnail, etc.

[0146] Figure 4a-4c This is a schematic diagram of a reference image editing provided by an embodiment of the present application, see Figure 4a In response to a reference image selection operation for the subject reference information 301, subject reference images 304 and 307 corresponding to the subject reference information 301 are displayed on a preset page. In response to a selection operation for the subject reference image 304 on the preset page, an edit entry control 401 corresponding to the subject reference image 304 is displayed; see Figure 4b In response to the editing area display operation triggered by the editing entry control 401, the first editing area 402 corresponding to the subject reference image 304, the thumbnail 403 of the subject reference image 304, and the thumbnail 404 of the subject reference image 307 are displayed; see Figure 4c In response to the editing operation (subject selection operation) triggered based on the first editing area 402, the subject reference image 304 is updated to the subject reference image 405 in the preset page. The subject reference image 405 is the subject reference image obtained by subject selection of the subject reference image 304.

[0147] In the above embodiment, in response to the reference image selection operation, at least one reference image corresponding to the first image reference information is displayed on the preset page, that is, after selecting the reference image, the preset page is returned to display the reference image. If the user has an editing requirement for any of the currently displayed reference images, the reference image is selected to display the editing entry control, and the image editing area corresponding to the reference image is displayed based on the editing entry control. This can effectively improve the speed of triggering the editing function of a single reference image, thereby improving the efficiency and convenience of image editing processing.

[0148] In an optional embodiment, the above method further includes:

[0149] In response to a reference image confirmation operation for at least one reference image, displaying a first editing area corresponding to a first reference image;

[0150] In response to the editing operation on the first reference image, updating the first reference image to the second reference image includes:

[0151] In response to an editing operation triggered based on the first editing area, the first reference image is updated to a second reference image.

[0152] Specifically, after step S202 "In response to a reference image selection operation for the first image reference information, determining at least one reference image corresponding to the first image reference information", the first editing area corresponding to the first reference image can be directly displayed to the user in response to a reference image confirmation operation for at least one reference image.

[0153] In an optional embodiment, at least one reference image corresponding to the first image reference information includes multiple reference images. Accordingly, in response to the reference image confirmation operation for the multiple reference images, the first editing area corresponding to the first reference image and the identification information of at least one other reference image are displayed. The at least one other reference image is a reference image other than the first reference image among the multiple reference images. Since the user did not select the reference image currently to be edited from the multiple reference images before entering the first editing area, the first reference image determined in this reference image selection operation can be used as the first reference image, or the last reference image determined in this reference image selection operation can be used as the first reference image. The user can switch the image to be edited by selecting the identification information of any other reference image, and update the first editing area corresponding to the first reference image to the editing area corresponding to the selected other reference image. If the user has no image editing requirements at this time, the closing operation can also be directly triggered based on the closing control corresponding to the first editing area, the first editing area can be canceled, and the preset page can be returned.

[0154] Exemplarily, in response to the first reference image selection operation for the first image reference information, reference image 1 and reference image 2 are determined to be the reference images corresponding to the first image reference information. At this time, the user can also trigger a second reference image selection operation for the first image reference information, determine reference image 3 and reference image 4 as the reference images corresponding to the first image reference information, and trigger a reference image confirmation operation for reference image 3 and reference image 4, displaying the first editing area corresponding to the first reference image. At this time, the first reference image is any one of reference image 3 and reference image 4.

[0155] Specifically, the other detailed contents for the "first editing area" in the step "updating the first reference image to the second reference image in response to the editing operation triggered based on the first editing area" are similar to the detailed contents for the "first editing area" in the above step "updating the first reference image to the second reference image in the preset page in response to the editing operation triggered based on the first editing area", and will not be repeated here.

[0156] Figure 5a-5c This is a schematic diagram of another reference image editing provided by an embodiment of the present application, see Figure 5a In response to the reference image selection operation for the subject reference information 301, an image library 501 including a plurality of candidate reference images and a reference image confirmation control 502 are displayed, see Figure 5b In response to the reference image confirmation operation for the two selected subject reference images triggered by the reference image confirmation control 502, a first editing area 503 corresponding to the subject reference image 1, a thumbnail 504 of the subject reference image 1, and a thumbnail 505 of the subject reference image 2 are displayed; see Figure 5c In response to the selection operation on the thumbnail 505, the image to be edited is switched, and the first editing area 503 corresponding to the main reference image 1 is updated to the editing area 506 corresponding to the main reference image 2 to perform editing processing on the main reference image 2.

[0157] In the above embodiment, in response to the reference image confirmation operation for at least one reference image, the first editing area corresponding to the first reference image is displayed, that is, after the reference image is selected, the image editing area of ​​the reference image is directly displayed, further shortening the triggering path of the image editing area, which can effectively improve the speed of triggering the reference image editing function, thereby improving the efficiency and convenience of image editing processing.

[0158] In an optional embodiment, the at least one image reference information includes: a plurality of image reference information, and before displaying the preset page including the at least one image reference information, the method further includes:

[0159] Displaying initial image reference information on a preset page; the initial image reference information is any image reference information among a plurality of image reference information;

[0160] The preset page including at least one image reference information is displayed including:

[0161] In response to the reference information switching operation, the initial image reference information in the preset page is updated to the image reference information corresponding to the reference information switching operation among the plurality of image reference information.

[0162] Specifically, the reference information switching operation can be used to switch the image reference information displayed in the preset page. Optionally, the reference information switching operation can be any operation, including but not limited to touch operation, voice operation, operation through an input device such as a mouse, or gesture operation. In a specific embodiment, the initial image reference information includes a reference information switching control. Accordingly, the user can trigger the reference information switching operation by clicking, long pressing the reference information switching control, etc. Optionally, the above-mentioned response to the reference information switching operation to update the initial image reference information in the preset page to the image reference information corresponding to the reference information switching operation among the multiple image reference information may include: in response to the reference information switching operation triggered based on the reference information switching control, displaying first candidate information including multiple image reference information, and in response to the first selection operation triggered by any image reference information among the multiple image reference information displayed based on the first candidate information, updating the initial image reference information in the preset page to the image reference information determined by the first selection operation.

[0163] In an optional embodiment, displaying the first candidate information including multiple image reference information may include: displaying the first candidate information in the form of a pop-up window (for example, a drop-down menu) on a preset page; in another optional embodiment, displaying the first candidate information including multiple image reference information may also include: switching the preset page to a page containing the first candidate information.

[0164] Figure 6a-6c This is a schematic diagram of switching image reference information provided by an embodiment of the present application, see Figure 6a , the preset page displays scene reference information 601 and reference information switching control 602, such as Figure 6b As shown, in response to the reference information switching operation triggered by the reference information switching control 602, the first candidate information 603 is displayed in the form of a drop-down menu, wherein the first candidate information 603 displays 6 types of image reference information. Since the subject reference information and style reference information are already displayed in the preset page, in order to avoid repeated selection, the options corresponding to the subject reference information and the options 604 corresponding to the style reference information in the first candidate information 603 are in a gray state (indicating that selection is prohibited), as shown in FIG. Figure 6cAs shown, in response to the first selection operation triggered by option 605 corresponding to the gesture reference information, the scene reference information 601 is updated to gesture reference information 606 in the preset page.

[0165] In the above embodiment, the initial image reference information is displayed on a preset page, and the initial image reference information is any image reference information among a plurality of image reference information. In response to a reference information switching operation, the initial image reference information in the preset page is updated to the image reference information among the plurality of image reference information corresponding to the reference information switching operation. Through the reference information switching operation, the user can change the desired image reference information (image reference dimension) during the use of the image generation function, thereby improving the flexibility of image reference information selection, and thereby improving the customization and diversification of image generation.

[0166] In an optional embodiment, the preset page displaying at least one image reference information includes:

[0167] Display the preset page;

[0168] In response to a reference information adding operation triggered based on a preset page, at least one image reference information is displayed in the preset page.

[0169] Specifically, the reference information adding operation can be used to add image reference information in a preset page. Optionally, the reference information adding operation can be any operation, including but not limited to touch operation, voice operation, operation through an input device such as a mouse, or gesture operation. In a specific embodiment, the preset page includes a reference information adding control. Accordingly, the user can trigger the reference information adding operation by clicking, long pressing the reference information adding control, and other operations.

[0170] In an optional embodiment, the above-mentioned response to the reference information adding operation triggered based on the preset page, displaying at least one image reference information in the preset page may include: in response to the reference information adding operation triggered based on the reference information adding control, displaying second candidate information including multiple image reference information, and in response to the second selection operation triggered by at least one image reference information among the multiple image reference information displayed based on the second candidate information, displaying at least one image reference information corresponding to the second selection operation in the preset page. Exemplarily, the second candidate information displays check boxes corresponding to each of the multiple image reference information, and the user implements the second selection operation by checking the check box corresponding to at least one image reference information. In another optional embodiment, the above-mentioned reference information adding operation may include: at least one adding operation, and the above-mentioned display of at least one image reference information in the preset page in response to the reference information adding operation triggered based on the preset page may include: displaying the reference information to be configured in the preset page in response to the reference information adding operation triggered based on the current adding operation in at least one adding operation, and updating the reference information to be configured in the preset page to the image reference information corresponding to the reference information switching operation in response to the reference information switching operation triggered based on the reference information to be configured; when the at least one adding operation is completed, the image reference information switched by the reference information to be configured added by each of the at least one adding operation is used as the at least one image reference information displayed in the preset page. Schematically, the reference information to be configured may be an initialized image reference information column to be configured.

[0171] Figure 6d-6f This is a schematic diagram of adding image reference information provided by an embodiment of the present application, see Figure 6d , the preset page displays a reference information adding control 607, such as Figure 6e As shown, in response to the reference information adding operation triggered by the reference information adding control 607, the second candidate information 608 is displayed in the form of a pop-up window, wherein the second candidate information 608 displays 6 types of image reference information. Since the main body reference information has been displayed in the preset page, in order to avoid repeated addition, the option 609 corresponding to the main body reference information in the second candidate information 608 is in a gray state (indicating that it is prohibited to be selected), as shown in FIG. Figure 6f As shown, in response to the second selection operation triggered by option 610 corresponding to the style reference information and option 611 corresponding to the posture reference information, style reference information 612 and posture reference information 613 are displayed in the preset page.

[0172] In the above embodiment, in response to the reference information adding operation triggered based on the preset page, at least one image reference information is displayed in the preset page. Through the reference information adding operation, the user can add the desired image reference information (image reference dimension) during the use of the image generation function, thereby improving the flexibility and richness of the image reference information configuration, thereby improving the customization and diversification of image generation, and improving the quality of the generated image.

[0173] In an optional embodiment, a reference information deletion control is also displayed in the preset page. In response to a reference information deletion operation triggered based on the reference information deletion control, the image reference information corresponding to the reference information deletion operation in at least one image reference information is canceled from the preset page.

[0174] In an optional embodiment, before displaying at least one generated image in response to the image generation operation, the method further includes:

[0175] Displaying an image display area corresponding to each of at least one image reference information and a plurality of recommended reference image groups on a preset page, wherein the plurality of recommended reference images in each recommended reference image group corresponds to one or more image reference information in the at least one image reference information;

[0176] In response to the recommended image group selection operation, the target recommended image in the target recommended reference image group is displayed in the image display area corresponding to the target image reference information. The target recommended reference image group is any recommended reference image group among multiple recommended reference image groups. The target recommended image is any recommended reference image among multiple recommended reference images in the target recommended reference image group. The target image reference information is image reference information corresponding to the target recommended image in at least one image reference information.

[0177] Specifically, the multiple recommended reference image groups can be multiple reference image groups automatically recommended by the image generation system based on at least one image reference information displayed on a preset page, and the multiple recommended reference images in each recommended reference image group correspond to one or more image reference information in at least one image reference information; the recommended image group selection operation can be used to select a target recommended reference image group from the multiple recommended reference image groups. Optionally, the recommended image group selection operation can be any operation, including but not limited to touch operation, voice operation, operation through an input device such as a mouse, or gesture operation.

[0178] Schematically, if at least one image reference information in the preset page is subject reference information and scene reference information, then the multiple recommended reference images in each recommended reference image group can be multiple subject reference images or multiple scene reference images, or can be an image combination of at least one subject reference image and at least one scene reference image. If the preset page displays two recommended reference image groups (recommended reference image group 1 and recommended reference image group 2) at this time, recommended reference image group 1 is two subject reference images, and recommended reference image group 2 is one subject reference image and one scene reference image. If the user selects recommended reference image group 1, then the two subject reference images are displayed in the image display area corresponding to the subject reference information in the preset page; if the user selects recommended reference image group 2, then the corresponding subject reference image is displayed in the image display area corresponding to the subject reference information in the preset page, and the corresponding scene reference image is displayed in the image display area corresponding to the scene reference information.

[0179] In an optional embodiment, in response to the recommended image group update operation, the display of multiple recommended reference image groups may be canceled in the preset page, and the updated multiple recommended reference image groups may be displayed.

[0180] In an optional embodiment, in response to the recommended image group selection operation, after the target recommended image in the target recommended reference image group is displayed in the image display area corresponding to the target image reference information, the user can directly trigger the image generation operation for the target recommended reference image group, perform image generation processing based on multiple recommended reference images in the target recommended reference image group, and obtain at least one generated image, thereby improving the simplicity of the image customization generation process.

[0181] Figure 7a-7c This is a schematic diagram showing a recommended reference image group provided by an embodiment of the present application, see Figure 7a The preset page displays three image reference information, namely subject reference information, posture reference information and style reference information. The preset page also displays four recommended reference image groups corresponding to 701. Figure 7b In response to the selection operation based on the recommended reference image group corresponding to 702, the subject reference image 704 and the posture reference image 705 corresponding to 702 are displayed in the image group display area corresponding to 703, see Figure 7c In response to the determination operation based on the recommended reference image group corresponding to 702, the subject reference image 704 is displayed in the image display area 706 corresponding to the subject reference information, and the posture reference image 705 is displayed in the image display area 707 corresponding to the subject reference information.

[0182] In the above embodiment, a reference image group is recommended based on at least one image reference information displayed on a preset page, and after the target reference image group is selected, the target reference image group is displayed in the image display area of ​​the corresponding image reference information. On the basis of improving the targetedness of the reference image group recommendation, the intuitiveness of the display of the target recommended reference image in the target reference image group is improved.

[0183] In an optional embodiment, the at least one image reference information includes: multiple image reference information, the preset page includes image display areas corresponding to the multiple image reference information, and before displaying the at least one generated image in response to the image generation operation, the method further includes:

[0184] In response to a reference image selection operation for the first image reference information, displaying at least one reference image corresponding to the first image reference information in an image display area corresponding to the first image reference information;

[0185] In response to an image move operation on the third reference image, the third reference image is canceled from the image display area corresponding to the first image reference information, and the third reference image is displayed in the image display area corresponding to the third image reference information, so as to update the image reference information corresponding to the third reference image from the first image reference information to the third image reference information, where the third reference image is any reference image among the at least one reference image, and the third image reference information is an image reference information among the multiple image reference information except the first image reference information.

[0186] Specifically, the image movement operation can be used to move the third reference image from the image display area corresponding to the first image reference information to the image display area corresponding to the third image reference information. Optionally, the image movement operation can be any operation, including but not limited to touch operation, voice operation, operation through an input device such as a mouse, or gesture operation.

[0187] Indicatively, see Figure 3a , the reference image 306 is displayed in the image display area 305 of the scene reference information, indicating that the image reference information corresponding to the reference image 306 is the scene reference information, Figure 8 This is a schematic diagram of a reference image movement provided by an embodiment of the present application, see Figure 8 By moving the reference image 306 from the image display area 305 of the scene reference information to the image display area 801 of the style reference information, the image reference information corresponding to the reference image 306 is updated from the scene reference information to the style reference information.

[0188] In the above embodiment, after selecting a reference image, the reference image can be moved from the image display area of ​​a certain image reference information to the image display area of ​​another image reference information by moving the reference image to change the reference type corresponding to the reference image, shorten the operation path of changing the reference type corresponding to the reference image, and improve the speed of changing the reference type corresponding to the reference image.

[0189] In an optional embodiment, the above method further includes:

[0190] If the first number of reference images determined when the image generation operation is triggered is less than the preset number, an image upload prompt message is displayed. The image upload prompt message is used to prompt to continue uploading at least a second number of reference images corresponding to the fourth image reference information. The fourth image reference information is one or more image reference information in at least one image reference information, and the second number is the difference between the preset number and the first number.

[0191] Specifically, the preset number may be a lower threshold of reference images required to be determined when a single image generation operation is triggered, and the first number may be the number of reference images already determined when the image generation operation is triggered. To ensure the diversity and quality of the generated images, if the first number is less than the preset number, an image upload prompt is displayed to the user, prompting the user to continue uploading reference images to meet the lower threshold required for a single image generation operation. This application does not specifically limit the display format of the image upload prompt.

[0192] Illustratively, if at least one image reference information displayed on the preset page is subject reference information and scene reference information, and the second number is 1, the image upload prompt message may be "Please continue to upload at least one subject reference image / scene reference image."

[0193] In the above embodiment, if the first number is less than the preset number, an image upload prompt message is displayed to the user to prompt the user to continue uploading the reference image to reach the lower limit threshold required for a single image generation operation, thereby ensuring the diversity and quality of the generated images by improving the diversity and richness of the reference images.

[0194] In an optional embodiment, at least one generated image is generated based on the image description text and target reference information corresponding to each target reference image in the plurality of target reference images. Before displaying the at least one generated image in response to the image generation operation, the method further includes:

[0195] An image description text is determined, where the image description text is used to indicate the image content of the image to be generated. The text content of the image description text can match target reference information corresponding to multiple target reference images that have been determined when the image generation operation is triggered.

[0196] Optionally, the image description text can be a description text input by the user through an input device (such as a keyboard), or it can be an image description text obtained by a large language model deployed by the image generation system based on the target reference information corresponding to multiple target reference images to generate the image description.

[0197] As can be seen from the technical solutions provided by the embodiments of the present specification above, the present specification can display a preset page including at least one image reference information in an image generation scene. In response to a reference image selection operation for first image reference information, at least one reference image corresponding to the first image reference information is determined. The first image reference information is any image reference information from at least one image reference information. The user can flexibly and conveniently select the image reference information and its corresponding reference image. In response to an image generation operation, at least one generated image is displayed. The at least one generated image is generated based on target reference information corresponding to each target reference image in a plurality of target reference images. The plurality of target reference images are reference images determined when the image generation operation is triggered. The plurality of target reference images correspond to one or more image reference information from at least one image reference information. The target reference information corresponding to each target reference image is image information in each target reference image that matches the image reference information corresponding to each target reference image. Image generation is performed based on the target reference information corresponding to the plurality of target reference images selected by the user. This can accurately and efficiently control the image generation process, improve the customization and diversification of image generation, and thereby enhance the user experience and willingness to use. It can also reduce the waste of system resources caused by low-quality image generation and improve system performance.

[0198] Figure 9 FIG. 1 is a block diagram of an image generating device according to an exemplary embodiment. Figure 9 , the device comprises:

[0199] The preset page display module 910 is configured to display a preset page including at least one image reference information;

[0200] A first reference image determination module 920 is configured to perform a reference image selection operation in response to first image reference information, and determine at least one reference image corresponding to the first image reference information, where the first image reference information is any image reference information among the at least one image reference information;

[0201] The generated image display module 930 is configured to execute a display of at least one generated image in response to an image generation operation, where the at least one generated image is generated based on target reference information corresponding to each target reference image in a plurality of target reference images, where the plurality of target reference images are reference images determined when the image generation operation is triggered, and the plurality of target reference images correspond to one or more image reference information in at least one image reference information, and the target reference information corresponding to each target reference image is image information in each target reference image that matches the image reference information corresponding to each target reference image.

[0202] In an optional embodiment, the multiple target reference images include: a second reference image, and the apparatus further includes:

[0203] The image editing module is configured to execute an editing operation on the first reference image and update the first reference image to a second reference image, wherein the first reference image is any reference image of at least one reference image, and the second reference image is obtained by image editing the first reference image.

[0204] In an optional embodiment, the above device further includes:

[0205] A first image display module is configured to display at least one reference image corresponding to the first image reference information on a preset page in response to a reference image selection operation;

[0206] an editing entry display module configured to display an editing entry control corresponding to the first reference image in response to a selection operation on the first reference image in the preset page;

[0207] A first editing area display module is configured to execute an editing area display operation in response to being triggered based on an editing entry control, and to display a first editing area corresponding to a first reference image;

[0208] Image editing modules include:

[0209] The first image editing unit is configured to execute an editing operation in response to being triggered based on the first editing area, and update the first reference image to a second reference image in a preset page.

[0210] In an optional embodiment, the above device further includes:

[0211] a second editing region display module configured to display a first editing region corresponding to a first reference image in response to a reference image confirmation operation on at least one reference image;

[0212] Image editing modules include:

[0213] The second image editing unit is configured to execute an editing operation in response to being triggered based on the first editing area, and update the first reference image to a second reference image.

[0214] In an optional embodiment, the at least one image reference information includes: multiple image reference information, and the apparatus further includes:

[0215] The initial image reference information display module is configured to display the initial image reference information on a preset page; the initial image reference information is any image reference information among a plurality of image reference information;

[0216] The preset page display module 910 includes:

[0217] The reference information switching unit is configured to execute, in response to a reference information switching operation, updating the initial image reference information in the preset page to image reference information corresponding to the reference information switching operation among the plurality of image reference information.

[0218] In an optional embodiment, the preset page display module 910 includes:

[0219] A preset page display unit is configured to display a preset page;

[0220] The reference information adding unit is configured to execute a reference information adding operation in response to a trigger based on a preset page, and display at least one type of image reference information in the preset page.

[0221] In an optional embodiment, the at least one image reference information includes: multiple image reference information, the multiple target reference images include: at least one reference image corresponding to the first image reference information and at least one reference image corresponding to the second image reference information, the second image reference information being one of the multiple image reference information other than the first image reference information, and the apparatus further includes:

[0222] The second reference image determination module is configured to perform a reference image selection operation in response to the second image reference information, and determine at least one reference image corresponding to the second image reference information.

[0223] In an optional embodiment, the at least one reference image corresponding to the first image reference information includes: multiple reference images corresponding to the first image reference information, and the image display generating module 930 includes:

[0224] The generated image display unit is configured to perform an image generation operation in response to being triggered based on a plurality of reference images, and display at least one generated image.

[0225] In an optional embodiment, the above device further includes:

[0226] a recommended reference image group display module configured to display, on a preset page, an image display area corresponding to each of at least one image reference information and a plurality of recommended reference image groups, wherein the plurality of recommended reference images in each recommended reference image group corresponds to one or more image reference information in the at least one image reference information;

[0227] The target recommended image display module is configured to execute a target recommended image in a target recommended reference image group in an image display area corresponding to the target image reference information in response to a recommended image group selection operation, wherein the target recommended reference image group is any recommended reference image group among multiple recommended reference image groups, the target recommended image is any recommended reference image among multiple recommended reference images in the target recommended reference image group, and the target image reference information is image reference information corresponding to the target recommended image in at least one image reference information.

[0228] In an optional embodiment, the at least one image reference information includes: multiple image reference information, the preset page includes image display areas corresponding to the multiple image reference information, and the above-mentioned device further includes:

[0229] a second image display module configured to execute a reference image selection operation for the first image reference information and display at least one reference image corresponding to the first image reference information in an image display area corresponding to the first image reference information;

[0230] The third image display module is configured to execute, in response to an image movement operation on the third reference image, cancel the display of the third reference image in the image display area corresponding to the first image reference information, and display the third reference image in the image display area corresponding to the third image reference information, so as to update the image reference information corresponding to the third reference image from the first image reference information to the third image reference information, where the third reference image is any reference image among the at least one reference image, and the third image reference information is an image reference information among the multiple image reference information except the first image reference information.

[0231] In an optional embodiment, the above device further includes:

[0232] The prompt information display module is configured to display image upload prompt information if a first number of reference images determined when an image generation operation is triggered is less than a preset number. The image upload prompt information is used to prompt to continue uploading at least a second number of reference images corresponding to fourth image reference information, where the fourth image reference information is one or more image reference information among at least one image reference information, and the second number is the difference between the preset number and the first number.

[0233] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0234] Figure 10 is a block diagram of an electronic device for image generation according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 10 As shown. It may include RF (Radio Frequency) circuit 1010, memory 1020 including one or more computer-readable storage media, input unit 1030, display unit 1040, sensor 1050, audio circuit 1060, WiFi (wireless fidelity) module 1070, processor 1080 including one or more processing cores, and power supply 1090 and other components. Those skilled in the art will understand that Figure 10 The terminal structure shown in the figure does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0235] The RF circuit 1010 can be used to receive and transmit signals during information transmission or calls. Specifically, it receives downlink information from the base station and transmits it to one or more processors 1080 for processing. Furthermore, it transmits uplink data to the base station. Typically, the RF circuit 1010 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a subscriber identity module (SIM) card, a transceiver, a coupler, an LNA (low noise amplifier), a duplexer, and the like. Furthermore, the RF circuit 1010 can communicate with the network and other terminals via wireless communication. Wireless communication can utilize any communication standard or protocol, including but not limited to GSM (Global System of Mobile Communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), and the like.

[0236] The memory 1020 can be used to store software programs and modules. The processor 1080 executes various functional applications and data processing by running the software programs and modules stored in the memory 1020. The memory 1020 may mainly include a program storage area and a data storage area. The program storage area may store an operating system, application programs required for functions, etc.; the data storage area may store data created based on the use of the terminal, etc. In addition, the memory 1020 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 1020 may also include a memory controller to provide access to the memory 1020 by the processor 1080 and the input unit 1030.

[0237] The input unit 1030 can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control. Specifically, the input unit 1030 may include a touch-sensitive surface 1031 and other input devices 1032. The touch-sensitive surface 1031, also known as a touch display or touchpad, can detect user touch operations on or near it (for example, operations performed by a user using a finger, stylus, or any other suitable object or accessory on or near the touch-sensitive surface 1031) and drive corresponding connected devices according to a pre-set program. Optionally, the touch-sensitive surface 1031 may include a touch detection device and a touch controller. The touch detection device detects the user's touch direction and detects the signals generated by the touch operation, transmitting the signals to the touch controller. The touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 1080. It can also receive and execute commands from the processor 1080. In addition, the touch-sensitive surface 1031 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface 1031, the input unit 1030 can also include other input devices 1032. Specifically, the other input devices 1032 can include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, power keys, etc.), a trackball, a mouse, a joystick, and the like.

[0238] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the terminal. These graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof. The display unit 1040 may include a display panel 1041. Optionally, the display panel 1041 can be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like. Furthermore, the touch-sensitive surface 1031 can cover the display panel 1041. When the touch-sensitive surface 1031 detects a touch operation on or near it, it transmits the information to the processor 1080 to determine the type of touch event. The processor 1080 then provides a corresponding visual output on the display panel 1041 based on the type of touch event. The touch-sensitive surface 1031 and the display panel 1041 can be two independent components to implement input and output functions. However, in some embodiments, the touch-sensitive surface 1031 and the display panel 1041 can also be integrated to implement input and output functions.

[0239] The terminal may also include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1041 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 1041 and / or the backlight when the terminal is moved to the ear. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the terminal posture (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured with the terminal, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be described here.

[0240] Audio circuit 1060, speaker 1061, and microphone 1062 provide an audio interface between the user and the terminal. Audio circuit 1060 converts received audio data into electrical signals and transmits them to speaker 1061, which then converts them into sound signals for output. Microphone 1062, on the other hand, converts collected sound signals into electrical signals, which are then received by audio circuit 1060 and converted into audio data. The audio data is then processed by processor 1080 and transmitted via RF circuit 1010 to, for example, another terminal. Alternatively, the audio data may be output to memory 1020 for further processing. Audio circuit 1060 may also include an earphone jack to allow external headphones to communicate with the terminal.

[0241] WiFi is a short-range wireless transmission technology. The terminal can help users send and receive emails, browse web pages and access streaming media through the WiFi module 1070. It provides users with wireless broadband Internet access. Figure 10 A WiFi module 1070 is shown, but it is understandable that it is not an essential component of the terminal and can be omitted as needed without changing the essence of the invention.

[0242] Processor 1080 is the terminal's control center, connecting all components of the terminal using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 1020 and accessing data stored in memory 1020, it performs various terminal functions and processes data, thereby providing overall terminal monitoring. Optionally, processor 1080 may include one or more processing cores; preferably, processor 1080 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 1080.

[0243] The terminal also includes a power supply 1090 (e.g., a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 1080 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 1090 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0244] Although not shown, the terminal may further include a camera, a Bluetooth module, etc., which will not be described in detail herein. Specifically, in this embodiment, the display unit of the terminal is a touch screen display, and the terminal further includes a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to execute instructions in the method embodiment of the present invention by one or more processors.

[0245] In an exemplary embodiment, an electronic device is further provided, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the image generation method in the embodiment of the present disclosure.

[0246] In an exemplary embodiment, a computer-readable storage medium is further provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the image generating method in the embodiment of the present disclosure.

[0247] In an exemplary embodiment, a computer program product including instructions is further provided. When the computer program product is run on a computer, the computer is caused to perform the image generation method in the embodiment of the present disclosure.

[0248] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, which can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0249] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0250] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An image generation method, characterized in that: The method comprises: displaying a preset page including at least one image reference information; In response to a reference image selection operation for first image reference information, determining at least one reference image corresponding to the first image reference information, where the first image reference information is any one of the at least one image reference information; In response to an image generation operation, at least one generated image is displayed, where the at least one generated image is generated based on target reference information corresponding to each target reference image in a plurality of target reference images, where the plurality of target reference images are reference images determined when the image generation operation is triggered, and the plurality of target reference images correspond to one or more image reference information in the at least one image reference information, where the target reference information corresponding to each target reference image is image information in each target reference image that matches the image reference information corresponding to each target reference image.

2. The image generation method according to claim 1, wherein: The plurality of target reference images include a second reference image, and the method further includes: In response to an editing operation on a first reference image, the first reference image is updated to the second reference image, where the first reference image is any reference image among the at least one reference image, and the second reference image is obtained by image editing the first reference image.

3. The image generation method according to claim 2, wherein: The method further comprises: In response to the reference image selection operation, displaying at least one reference image corresponding to the first image reference information on the preset page; In response to a selection operation on the first reference image in the preset page, displaying an editing entry control corresponding to the first reference image; In response to an editing area display operation triggered by the editing entry control, displaying a first editing area corresponding to the first reference image; In response to the editing operation on the first reference image, updating the first reference image to the second reference image includes: In response to the editing operation triggered based on the first editing area, the first reference image is updated to the second reference image in the preset page.

4. The image generation method according to claim 2, wherein: The method further comprises: In response to a reference image confirmation operation on the at least one reference image, displaying a first editing area corresponding to the first reference image; In response to the editing operation on the first reference image, updating the first reference image to the second reference image includes: In response to the editing operation triggered based on the first editing area, the first reference image is updated to the second reference image.

5. The image generation method according to claim 1, wherein: The at least one image reference information includes: a plurality of image reference information. Before displaying the preset page including the at least one image reference information, the method further includes: Displaying initial image reference information on the preset page; the initial image reference information is any image reference information among the multiple image reference information; The preset page displaying at least one image reference information includes: In response to a reference information switching operation, the initial image reference information in the preset page is updated to image reference information corresponding to the reference information switching operation among the multiple image reference information.

6. The image generation method according to claim 1, wherein: The preset page displaying at least one image reference information includes: Displaying the preset page; In response to a reference information adding operation triggered based on the preset page, the at least one image reference information is displayed in the preset page.

7. The image generation method according to any one of claims 1 to 6, characterized in that: The at least one image reference information includes: multiple image reference information, the multiple target reference images include: at least one reference image corresponding to the first image reference information and at least one reference image corresponding to a second image reference information, the second image reference information being one of the multiple image reference information other than the first image reference information. Before displaying at least one generated image in response to the image generation operation, the method further includes: In response to a reference image selection operation for the second image reference information, at least one reference image corresponding to the second image reference information is determined.

8. The image generation method according to any one of claims 1 to 6, characterized in that: The at least one reference image corresponding to the first image reference information includes: a plurality of reference images corresponding to the first image reference information, and the displaying of the at least one generated image in response to the image generation operation includes: In response to the image generation operation being triggered based on the plurality of reference images, the at least one generated image is presented.

9. The image generation method according to any one of claims 1 to 6, characterized in that: Before displaying at least one generated image in response to the image generation operation, the method further includes: Displaying an image display area corresponding to each of at least one image reference information and a plurality of recommended reference image groups on the preset page, wherein the plurality of recommended reference images in each recommended reference image group corresponds to one or more image reference information in the at least one image reference information; In response to the recommended image group selection operation, the target recommended image in the target recommended reference image group is displayed in the image display area corresponding to the target image reference information, the target recommended reference image group is any recommended reference image group among the multiple recommended reference image groups, the target recommended image is any recommended reference image among the multiple recommended reference images of the target recommended reference image group, and the target image reference information is the image reference information corresponding to the target recommended image in the at least one image reference information.

10. The image generation method according to any one of claims 1 to 6, characterized in that: The at least one image reference information includes: multiple image reference information, the preset page includes image display areas corresponding to the multiple image reference information respectively, and before displaying at least one generated image in response to the image generation operation, the method further includes: In response to a reference image selection operation for the first image reference information, displaying at least one reference image corresponding to the first image reference information in an image display area corresponding to the first image reference information; In response to an image move operation on a third reference image, the third reference image is canceled from the image display area corresponding to the first image reference information, and the third reference image is displayed in the image display area corresponding to the third image reference information, so as to update the image reference information corresponding to the third reference image from the first image reference information to the third image reference information, wherein the third reference image is any reference image among the at least one reference image, and the third image reference information is one of the multiple image reference information except the first image reference information.

11. The image generation method according to any one of claims 1 to 6, characterized in that: The method further comprises: If the first number of reference images determined when the image generation operation is triggered is less than the preset number, an image upload prompt message is displayed, and the image upload prompt message is used to prompt to continue uploading at least a second number of reference images corresponding to the fourth image reference information, where the fourth image reference information is one or more image reference information among the at least one image reference information, and the second number is the difference between the preset number and the first number.

12. An image generating device, characterized in that: include: A preset page display module is configured to display a preset page including at least one image reference information; a first reference image determination module configured to perform a reference image selection operation in response to first image reference information, and determine at least one reference image corresponding to the first image reference information, wherein the first image reference information is any one of the at least one image reference information; A generated image display module is configured to execute, in response to an image generation operation, display at least one generated image, wherein the at least one generated image is generated based on target reference information corresponding to each target reference image in a plurality of target reference images, the plurality of target reference images being reference images determined when the image generation operation is triggered, and the plurality of target reference images corresponding to one or more image reference information in the at least one image reference information, and the target reference information corresponding to each target reference image being image information in each target reference image that matches the image reference information corresponding to each target reference image.

13. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the image generation method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the image generating method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The computer program product includes a computer program stored in a readable storage medium. At least one processor of a computer device reads and executes the computer program from the readable storage medium, so that the device performs the image generation method according to any one of claims 1 to 11.

Images