Method and apparatus for image generation, and device and storage medium

Abstract

According to the embodiments of the present disclosure, provided are a method and apparatus for image generation, and a device and a storage medium. The method comprises: in response to an element adjustment request for a first image, which has a first element, of a first virtual avatar, presenting an element adjustment interface, wherein the first virtual avatar comprises media data representing appearance features of a first object; via the element adjustment interface, receiving adjustment information for the first element; and on the basis of the received adjustment information, presenting a second image, which has an adjusted first element, of the first virtual avatar. Thus, on one hand, the flexibility and degree of freedom of content creation are increased, and on the other hand, the diversity and personalization of content styles are increased. In this way, the interestingness of content interaction can be improved.

Description

Method, apparatus, device and storage medium for image generation

[0001] This application claims priority to the Chinese invention patent application entitled “Method, apparatus, device and storage medium for image generation” filed on December 8, 2023, with application number 202311688888.8, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for image generation. Background Art

[0003] With the development of computer technology, more and more applications are designed to provide users with various services. For example, users can create, publish, browse, comment on, and forward various types of content in applications, including various media such as videos, images, image collections, and audio. The interactivity and fun of these applications are of great concern. Summary of the Invention

[0004] In a first aspect of the present disclosure, a method for image generation is provided. The method includes: presenting an element adjustment interface in response to an element adjustment request for a first image of a first virtual avatar having a first element, the first virtual avatar including media data representing an appearance feature of a first object; receiving adjustment information for the first element via the element adjustment interface; and presenting a second image of the first virtual avatar having the adjusted first element based on the received adjustment information.

[0005] In a second aspect of the present disclosure, a device for image generation is provided. The device includes: an interface presentation module configured to present an element adjustment interface in response to an element adjustment request for a first image of a first virtual avatar having a first element, the first virtual avatar including media data representing an appearance feature of a first object; an information receiving module configured to receive adjustment information for the first element via the element adjustment interface; and an image presentation module configured to present a second image of the first virtual avatar having the adjusted first element based on the received adjustment information.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0008] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0011] 2A to 2Z are schematic diagrams illustrating example interfaces for creating an avatar according to some embodiments of the present disclosure;

[0012] 3A to 3L are schematic diagrams illustrating example interfaces for stylized image generation according to some embodiments of the present disclosure;

[0013] 4A to 4E are schematic diagrams illustrating example interfaces for style adjustment according to some embodiments of the present disclosure;

[0014] 5A to 5J are schematic diagrams illustrating example interfaces for providing style adjustment information according to some embodiments of the present disclosure;

[0015] 6A to 6E are schematic diagrams illustrating example interfaces for customizing styles according to some embodiments of the present disclosure;

[0016] 7A to 7G are schematic diagrams illustrating example interfaces for providing customized information according to some embodiments of the present disclosure;

[0017] 8A to 8I illustrate schematic diagrams of example interfaces for reusing styles according to some embodiments of the present disclosure;

[0018] 9A to 9M illustrate schematic diagrams of example interfaces for managing stylized images according to some embodiments of the present disclosure;

[0019] 10A to 10F illustrate schematic diagrams of example interfaces for managing styles according to some embodiments of the present disclosure;

[0020] FIG11 shows a flowchart of a process for image generation according to some embodiments of the present disclosure;

[0021] FIG12 shows a flowchart of an apparatus for image generation according to some embodiments of the present disclosure; and

[0022] FIG13 illustrates a block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0023] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0024] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below.

[0025] Herein, unless explicitly stated otherwise, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0026] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0027] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0028] For example, in response to receiving a user's active request, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information, so that the user can independently choose whether to provide personal information to the electronic device, application, server or storage medium and other software or hardware that performs the operation of the technical solution of the present disclosure based on the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving a user's active request, a prompt message may be sent to the user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. Furthermore, the pop-up window may also include a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0030] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0031] As used herein, the term "element" or "image element" may refer to any suitable aspect or attribute of an image. For example, an element may include image style (also referred to simply as style), image background, or image foreground.

[0032] As used herein, the term "avatar" may include media data representing the appearance characteristics of an object. The appearance characteristics may include facial features. The media data may include data in any suitable form, such as image data, video data, three-dimensional model data, etc.

[0033] As briefly mentioned above, users can create media content such as images, image collections, and videos within the app. With the advancement of machine learning technology, digital tools based on machine learning models have begun to be used to create avatars for users. Users can also use avatars to generate images with desired elements, such as stylized images. This approach allows users to generate content that resembles themselves.

[0034] However, this approach still has some drawbacks. For example, the elements available to users are very limited, typically only offering a few styles. Furthermore, users cannot modify or customize elements to their own preferences, which limits their creative flexibility. Furthermore, this can reduce users' willingness to continue using the app.

[0035] To this end, according to an embodiment of the present disclosure, an improved image generation scheme is proposed. According to the scheme of the embodiment of the present disclosure, in response to an element adjustment request for a first image of a first virtual avatar having a first element, an element adjustment interface is presented. The first virtual avatar includes media data representing the appearance characteristics of a first object. Adjustment information for the first element is received via the element adjustment interface. Based on the received adjustment information, a second image of the first virtual avatar having the adjusted first element is presented.

[0036] According to the embodiments of the present disclosure, users can utilize existing elements to generate images and adjust these elements to suit their preferences. This increases the flexibility and freedom of content creation while also increasing the diversity and personalization of image elements. This approach can enhance the fun of content interaction.

[0037] Example embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0038] Sample Environment

[0039] 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In environment 100, one or more users 110-1, 110-2, 110-3, ..., 110-N can publish and / or browse media data (also referred to as multimedia content, multimedia data, media content, etc.) in a target platform through their associated terminal devices 120-1, 120-2, 120-3, ..., 120-N.

[0040] For ease of discussion, users 110-1, 110-2, 110-3, ..., 110-N may be collectively or individually referred to as user 110, and terminal devices 120-1, 120-2, 120-3, ..., 120-N may be collectively or individually referred to as terminal device 120. In the context of publishing media data, user 110 may also be referred to as the publisher of the media data. In the context of browsing media data, user 110 may also be referred to as the viewer, browser, or viewer of the media data.

[0041] Terminal device 120 may be installed with a platform that supports media data publishing and / or media data playback. Such a platform may be, for example, an application or a website. User 110 may operate terminal device 120 to access the corresponding application or website. In some embodiments, the platform used to publish media data and the platform used to play media data may be the same or different platforms. For example, user 110-1 edits and publishes media data on a first platform, and the publishing operation indicates that the media data will be published on a second platform. User 110-2 may browse the media data on the second platform.

[0042] In some embodiments, the terminal device 120 may be installed with an application 125 that supports media data publishing (i.e., the terminal device 120-1 has application 125-1 installed, the terminal device 120-2 has application 125-2 installed, the terminal device 120-3 has application 125-3 installed, ..., the terminal device 120-N has application 125-N installed). It should be noted that the applications 125 installed in different terminal devices 120 may be exactly the same applications or different applications (e.g., different versions). The application 125 may be any appropriate application with a media data publishing function, such as a social application, a content sharing application, an office support application, and the like.

[0043] In the environment 100 of FIG. 1 , if application 125 is active, terminal device 120 may present the user interface of application 125. This user interface may include various interfaces provided by application 125, such as a user interface supporting message interaction, a user interface supporting content browsing, a message sending and receiving interface, and so on. Application 125 may provide different content to user 110 via different user interfaces. Application 125 may also provide user 110 with the ability to select and switch presentation methods for related content via appropriate means, such as by clicking or selecting any appropriate interface element in the user interface.

[0044] In some embodiments, different terminal devices 120 may also communicate with server 130 via network 132 to provide message interaction services. Server 130 may provide management, configuration, and maintenance functions for application 125.

[0045] The terminal device 120 can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a television receiver, a radio broadcast receiver, an e-book device, a gaming device or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 120 can also support any type of interface for the user (such as a "wearable" circuit, etc.). The server 130 can be various types of computing systems / servers that can provide computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, and the like.

[0046] It should be understood that the structure and function of each component in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. Various example implementations of the present disclosure will be described in detail below.

[0047] Sample interface

[0048] For ease of understanding, some example embodiments of the present disclosure will be described below in conjunction with the example interfaces of Figures 2A to 10F. Figures 2A to 10F show schematic diagrams of example interfaces according to some embodiments of the present disclosure. It should be understood that the interfaces shown in the accompanying drawings are merely examples, and various interface designs may actually exist. The various interface elements in the interface may have different arrangements and different visual representations, one or more of the interface elements may be omitted or replaced, and one or more other interface elements may also exist. The embodiments of the present disclosure are not limited in this respect.

[0049] The example interfaces shown in Figures 2A to 10F can be presented at the terminal device 120. For ease of discussion, the example interfaces / example pages shown in Figures 2A to 10F will be described with reference to the environment 100 of Figure 1. It should be noted that, in this article, the operations performed by the terminal device 120 can be specifically performed with the help of locally installed related applications. In some embodiments, certain operations may need to be completed with the support of a server (such as server 130) or other devices. For ease of understanding, the following exemplary description is given by taking the terminal device 120 performing the operation itself as an example.

[0050] In some embodiments, terminal device 120 can obtain a virtual avatar corresponding to an object based on an image input by user 110 that includes the object's appearance. The virtual avatar can include media data representing the object's appearance characteristics, such as image data, video data, 3D model data, etc. In some embodiments, the appearance characteristics can include facial features. This allows virtual objects corresponding to different objects to be distinguishable.

[0051] User 110 can create an avatar associated with them. This object can include any appropriate object, such as a person, an animal, or a cartoon character, and this disclosure does not limit the specific object. In particular, in some embodiments, the object can be user 110 themselves. It will be understood that the avatar, image, etc., can be generated locally on terminal device 120 or in the cloud with the help of server 130. For ease of description, the following example uses the example of user 110 inputting an image containing a human face.

[0052] In some embodiments, based on an operation by user 110, terminal device 120 may obtain an image of the created avatar having specific elements, also referred to as an element-specific image. In some embodiments, the element may be a style. Terminal device 120 may obtain an image of the created avatar having a certain style, also referred to as a stylized image. In other words, a stylized image may be generated and presented to user 110. In embodiments of the present disclosure, a style or image style may include any type of style, such as, but not limited to, cartoon, watercolor, crayon, sketch, comic, and the like.

[0053] In some embodiments, the creation of the virtual image and the generation of the element-specific image can be achieved by the terminal device 120 and / or the server 130 with the help of a machine learning model. The machine learning model here can be any appropriate model, and this disclosure is not limited to this. Exemplarily, in the case of generating an image, the terminal device 120 can generate a prompt word based on the configuration information of the element to be used, and provide the prompt word to the model used to generate the image (i.e., the target model). The terminal device 120 can obtain the output of the target model and obtain an image based on the output.

[0054] As mentioned above, elements may include, but are not limited to, various aspects such as style, foreground, and background. Below, some exemplary embodiments of the present disclosure are described using style as an example of an element. However, it should be understood that the embodiments described with reference to style may be applied to other types of elements.

[0055] Example interface for creating an avatar

[0056] The following describes an example interaction for creating an avatar. In some embodiments, the terminal device 120 may provide an entry associated with the avatar in the user information interface of the user 110. If the user 110 has not created an avatar, the entry may be an entry for creating the avatar. Figures 2A to 2C show schematic diagrams of examples 200A to 200C of user information interfaces according to some embodiments of the present disclosure. As shown in Figure 2A, the terminal device 120 may provide a user information interface as shown in example 200A. If the user 110 (e.g., "user 123" in the figure) has not created an avatar, the terminal device 120 may provide an entry 201 for creating the avatar in example 200A. In response to detecting a trigger operation for creating entry 201, the terminal device 120 may present example 200B as shown in Figure 2B. Trigger operations include, but are not limited to, any appropriate operation, such as a click operation, a double-click operation, a long press operation, a slide operation, and a drag operation. This disclosure does not limit specific trigger operations.

[0057] In example 200B, the terminal device 120 may present a prompt panel 210 for prompting the creation of an avatar. The prompt panel 210 may present prompt information on how to create an avatar (for example, the text "Upload 5 pictures to create a digital version of yourself! With an avatar, you can quickly create pictures in various digital styles"). The prompt panel 210 may also present, for example, example effects of avatars or different image styles (for example, exemplary avatar images may be presented). The prompt panel 210 may also include a create control 212 and a cancel control 211. The terminal device 120 may determine to cancel the creation of the avatar in response to receiving a trigger operation on the cancel control 211, and return to presenting example 200A. Alternatively or additionally, in some embodiments, the terminal device 120 may determine to cancel the creation of the avatar in response to receiving a trigger operation on an area outside the prompt panel 210 in example 200B, and return to presenting example 200A.

[0058] It should be noted that regarding the prompt logic of the prompt panel 210 for prompting the user to create an avatar, in some embodiments, the terminal device 120 will, by default, present the prompt panel 210 each time it detects a trigger operation for creating the portal 201. In some embodiments, the terminal device 120 may also present the prompt panel 210 only when the trigger operation for creating the portal 201 is detected for the first time or after the first few (predetermined) times of detecting the trigger operation for creating the portal 201.

[0059] In response to detecting a trigger operation on the creation control 211, the terminal device 120 may determine that a request to create a virtual image has been received and present an image acquisition interface. The image acquisition interface may include an image capture interface and / or an image selection interface. The terminal device 120 may use a camera to capture an image in the image capture interface. The terminal device 120 may select an image stored locally on the terminal device 120 in the image selection interface. The locally stored images here include images previously captured by the terminal device 120 through the camera and images obtained by the terminal device 120 from the cloud, from other devices, etc.

[0060] In some embodiments, if a request to create an avatar is detected, the terminal device 120 may provide a tab sheet including at least a first option corresponding to an image capture interface and a second option corresponding to an image selection interface. In response to detecting a selection of the first option, the terminal device 120 may determine that access rights to the image capture interface have been obtained, and present the image capture interface. Furthermore, in response to detecting a selection of the second option, the terminal device 120 may determine that access rights to the image selection interface have been obtained, and present the image selection interface. The selection operation herein may include, for example, any appropriate operation, such as a click, double-click, long-press, slide, or drag.

[0061] For example, as shown in FIG2B and FIG2C , the terminal device 120 may present example 200C in response to detecting a trigger operation on the create control 211. Example 200C includes a tab sheet 220. The terminal device 220 may present option 221 corresponding to the image capture interface and option 222 corresponding to the image selection interface in the tab sheet 220. In response to detecting a selection operation for option 221, the terminal device 120 may present the image capture interface, and in response to detecting a selection operation for option 222, the terminal device 220 may present the image selection interface. For example, the terminal device 220 may also present option 223 in the tab sheet 220. For example, the terminal device 110 may determine to cancel the presentation of the image capture interface or the image selection interface in response to detecting a selection operation for option 223, and return to presenting example 200B.

[0062] In some embodiments, the terminal device 120 may also predetermine a default interface. In response to detecting a request to create a virtual image, the terminal device 120 presents the predetermined default interface. In response to detecting a trigger operation on any appropriate interface element in the default interface, the terminal device 120 may present another interface. For example, the default interface may be an image selection interface, and the terminal device 120 may switch to presenting an image capture interface in response to detecting a trigger operation on any appropriate interface element (e.g., an interface switching control) in the image selection interface.

[0063] In some embodiments, the terminal device 110 may present an image selection interface in response to detecting a selection operation for option 222 in example 200C. Alternatively or additionally, in some embodiments, the terminal device 120 may present a default image selection interface in response to detecting a request to create an avatar (e.g., a trigger operation for creating entry 201 in example 200A, a trigger operation for creating control 212 in example 200B, etc.). The terminal device 120 may present a prompt panel in the image selection interface for providing prompt information.

[0064] As shown in Figure 2D, the terminal device 120 can, for example, present example 200D including a prompt panel 230. Example 200D can, for example, be an image selection interface including a prompt panel. The prompt panel 230 can also, for example, present examples of appropriate target images (e.g., images that meet conditions related to facial regions) and examples of inappropriate target images (e.g., images that do not meet conditions related to facial regions). The prompt panel 230 also includes an operation control 231. The terminal device 120 can cancel the presentation of the prompt panel 230 in response to detecting a triggering operation on the operation control 231 or detecting a triggering operation on any area outside the prompt panel 230 in example 200D. After canceling the presentation of the prompt panel 230, the terminal device 120 can, for example, present example 200E as shown in Figure 2E. Example 200E can, for example, be an image selection interface that does not include a prompt panel. Example 200E can present multiple images with access rights.

[0065] Similarly, regarding the prompt panel 230, in some embodiments, each time the terminal device 120 presents the image selection interface, the image selection interface including the prompt panel 230 is presented by default. In some embodiments, the terminal device 120 may also present the image selection interface including the prompt panel 230 only when presenting the image selection interface for the first time (or the first few (which may be predetermined) times) the image selection interface is presented, and present the image selection interface without the prompt panel 230 when presenting the image selection interface again thereafter.

[0066] As shown in FIG2E , example 200E may further include an area 233 for presenting selected images. If the user has not selected an image, the terminal device 120 may not present any image in area 233. The terminal device 120 may determine that an image is selected in response to receiving a selection operation on any image presented in the image selection interface (e.g., a selection operation on an already captured image). In this case, the terminal device 120 may also present the selected image in area 233.

[0067] In some embodiments, the terminal device 120 may also determine whether the selected image meets the conditions related to the facial region (e.g., whether it is an image including the face of the subject). The terminal device 120 may, for example, determine whether the selected image meets the conditions related to the facial region through a series of face detection models. For example, if the terminal device 120 determines that the selected image meets the conditions related to the facial region, the terminal device 120 may present the selected image in area 233. For example, if the terminal device 120 determines that the selected image does not meet the conditions related to the facial region, it may present prompt information indicating that the image does not meet the conditions related to the facial region and that the image cannot be selected.

[0068] In some embodiments, in order to ensure the effect of the created virtual image, the terminal device 120 may need to obtain multiple images. The number of these multiple images can be any appropriate number that meets the requirements for creating a virtual image. The number of images and / or the range of the number of images that meet the requirements for creating a virtual image can be preset. For example, if the user presets the number of images that meet the requirements for creating a virtual image to be 5, the user needs to select 5 images so that the terminal device 120 can obtain these 5 images. For another example, if the user presets the range of the number of images that meet the requirements for creating a virtual image to be 5-20, the user needs to select any number of images between 5 and 20 (for example, 10) so that the terminal device 120 can obtain these 5 images.

[0069] Region 233 may also include an operation control 234. In response to detecting a trigger operation on operation control 234, terminal device 120 may acquire a selected set of images. For example, terminal device 120 may present example 200F of the interface shown in FIG. 2F while acquiring the selected set of images. In example 200F, terminal device 120 may present an interface element 240 indicating that terminal device 120 is acquiring the selected set of images.

[0070] In some embodiments, the terminal device 120 may present a virtual image generation interface in response to obtaining a selected set of images. In some embodiments, in order to make a secondary determination of the selected set of images and whether to generate a virtual image, the terminal device 120 may also present example 200G as shown in Figure 2G in response to obtaining a selected set of images. In example 200G, the terminal device 120 may present a card 250 for prompting confirmation whether to generate a virtual image. Card 250 includes a return control and a generation control. In response to detecting a trigger operation on the return control in card 250, the terminal device 120 may cancel the presentation of card 250. In response to detecting a trigger operation on the generation control in card 250, the terminal device 120 may start generating a virtual image.

[0071] Referring back to FIG2E , the image selection interface shown in Example 200E may further include an operation control 232. The terminal device 120 may switch to presenting the image capture interface in response to detecting a trigger operation for the operation control 232. In some embodiments, the terminal device 120 may further determine that permission to access the camera has been obtained in response to detecting a selection operation for the selection 221 in Example 200C, and present the image capture interface. In some embodiments, the terminal device 120 may further present a default image capture interface in response to detecting a request to create an avatar (e.g., a trigger operation for the creation entry 201 in Example 200A, a trigger operation for the creation control 212 in Example 200B, etc.).

[0072] The terminal device 120 can, for example, present example 200H as shown in Figure 2H. Example 200H can, for example, be an example of an image capture interface. The terminal device 120 can present the image captured by the camera in area 202 of example 200H. In some embodiments, the terminal device 120 can also present a border 204 and an area 203 for presenting prompt information in area 202. The terminal device 120 can, for example, determine whether the captured image meets the conditions related to the facial area. The conditions related to the facial area can, for example, include at least the condition that the facial area of ​​the target object in the captured image is located within the border 204. As mentioned above, the terminal device 120 can, for example, use a series of face detection models to determine whether the captured image meets the conditions related to the facial area.

[0073] In some embodiments, if it is determined that the captured image in example 200H does not meet the conditions related to the facial region, the terminal device 120 may present a corresponding prompt message in area 203. This prompt message may be a pre-set fixed prompt message. For example, it may be a prompt message such as "Please adjust your face position." The prompt message may also be determined based on one or more of the at least one conditions not being met. For example, if it is determined that the captured image does not meet the condition that the facial region of the target subject in the captured image is within the bounding box 204, the terminal device 120 may present a prompt message such as "Place your face in the predetermined region" in area 203. As shown in FIG2H , in response to the facial region being located outside the bounding box 204 (including both the possibility of being completely or partially outside the bounding box 204), the terminal device 120 may present the prompt message "Place your face in the predetermined region" in area 203. Area 203 may be located at any appropriate location in example 200H, for example, it may be presented at the top of all layers. For example, area 203 may be presented superimposed on area 202.

[0074] In some embodiments, if it is determined that the captured image meets the conditions associated with the facial region, the terminal device 120 may present a prompt in area 203 indicating that the image can be captured. As shown in FIG2I , if it is determined that the captured image meets the conditions associated with the facial region, the terminal device 120 may present a prompt message "No problem" in area 203 of example 200I to prompt the user that the current image meets the conditions associated with the facial region and can be captured. In response to detecting a trigger operation on the capture control 206 , the terminal device 120 may determine that an image capture operation has been received and capture the image currently presented in area 202 .

[0075] After the terminal device 120 acquires the captured image, it may present example 200J as shown in FIG2J . Example 200J may, for example, present the captured image and a mark 207 . Mark 207 is used to indicate that the currently captured image meets the conditions related to the facial region and that the image has been successfully acquired by the terminal device 120 .

[0076] As shown in Figures 2H to 2J, the image capture interface (e.g., example 200H, example 200I, example 200J) may also present an operation control 205. In response to receiving a trigger operation for the operation control 205, the terminal device 120 may switch to presenting the image selection interface. For example, the terminal device 120 may present example 200K shown in Figure 2K, which illustrates an example of an image selection interface. The terminal device 120 may present an image captured by the image capture interface in area 233 of example 200K.

[0077] It should be noted that terminal device 120 may acquire an avatar based solely on multiple images captured via the image capture interface, solely on multiple images selected via the image selection interface, or based on a combination of at least one image captured via the image capture interface and at least one image selected via the image selection interface. The specific images used to acquire the avatar may depend on the operation of user 110. Thus, user 110 can flexibly select previously captured images or capture new images.

[0078] In some embodiments, if the terminal device 120 acquires a virtual image only based on multiple images selected via the image selection interface, the terminal device 120 may determine the multiple images selected and acquire a virtual image based on the multiple images in response to receiving a trigger operation on the operation control 234 shown in Examples 200E to 200G.

[0079] In some embodiments, if terminal device 120 acquires an avatar based on a combination of at least one image captured via an image capture interface and at least one image selected via an image selection interface, terminal device 120 may acquire the selected multiple images in response to receiving a selection operation for multiple images in example 200K. Terminal device 120 may acquire an avatar based on the image captured via the image capture interface and the multiple selected images presented in area 233.

[0080] In some embodiments, if the terminal device 120 acquires an avatar based solely on multiple images captured via an image capture interface, the terminal device 120 may present examples 200L through 200O, as shown in Figures 2L through 2O. Examples 200L through 200O illustrate multiple examples of image capture interfaces. It is understood that to ensure the effectiveness of the avatar subsequently generated based solely on the multiple images captured via the image capture interface, the terminal device 120 may need to acquire images that include faces from different angles. Examples 200L through 200O may present area 208. Area 208 may present a prompt instructing the acquisition of multiple images that include faces from different angles (it is understood that while three images are shown, any number of images may be used). The terminal device 120 may also present prompt information in area 203 instructing the acquisition of faces from different angles. For example, in response to acquiring an image that includes the right side of a face, the terminal device 120 may present the prompt "Turn your face to the right" in area 203. The terminal device 120 may also present the acquired image at the corresponding location in area 208. The terminal device 120 may then acquire a virtual avatar based on the multiple images presented in the area 208 .

[0081] For example, in response to receiving a trigger operation on the operation control 234, the terminal device 120 may determine that an operation has been received to create an avatar and begin acquiring the avatar. The terminal device 120 may create the avatar using a machine learning model. Such a machine learning model may be deployed locally on the terminal device 120 or on the server 130. For example, multiple images specified by the user 110 may be provided to the machine learning model for generating the avatar.

[0082] As described above, in some embodiments of the present disclosure, the user 110 may not be required to distinguish the selected images, for example, it is not necessary to specify which of the images are front-facing images of the object. This helps the user to more conveniently specify images.

[0083] It should be noted that when the multiple images acquired all include the face of the same object (e.g., the first object) and only include the face of the object, the terminal device 120 can generate a virtual image corresponding to the object (e.g., the first virtual image) based on the multiple images acquired. When the multiple images acquired include the faces of multiple objects, the terminal device 120 can determine the priorities corresponding to these multiple objects. The terminal device 120 can, for example, determine the priority corresponding to each object based on the number of faces of each object. For example, if a total of 10 images are acquired, 6 of the 10 images include the face of the first object, 5 images include the face of the second object, and 3 images include the face of the third image (it can be understood that the same image can include the faces of multiple objects, and the first object, the second object, and the third object are three different objects), then the terminal device 120 can determine that the priority of the first object > the priority of the second object > the priority of the third object. The terminal device 120 can then generate a virtual image corresponding to the first object.

[0084] During the avatar generation process, terminal device 120 may present example 200P, as shown in FIG. Example 200P illustrates an example of an avatar creation progress interface. Example 200P includes prompt information indicating the avatar creation progress. For example, example 200P includes the prompt "Estimated time: XX hours, XX minutes." Example 200P may also include operation controls 251 and 252. In response to receiving a trigger operation on operation control 252, terminal device 120 determines to cancel avatar generation. For example, terminal device 120 may switch back to presenting example 200A, as shown in FIG. 2A . To prevent accidental touches, terminal device 120 may also present a card prompting confirmation to cancel avatar generation. As shown in FIG. 2Q , in example 200Q, terminal device 120 may present card 260. Upon detecting a return control in card 260, terminal device 120 may determine to continue avatar generation. Upon detecting a cancel control in card 160, terminal device 120 may cancel avatar generation. For example, terminal device 120 may switch back to presenting example 200A as shown in FIG. 2A , or switch to presenting example 200R as shown in FIG. Example 200R includes operation control 261. For example, terminal device 120 may repeat the above-described operations of acquiring an image and generating an avatar in response to detecting a trigger operation on operation control 261.

[0085] Referring back to FIG2P , the terminal device 120 may also switch to presenting other interfaces that the application 120 can provide in response to detecting a trigger operation on the operation control 251. For example, the terminal device 120 may switch to presenting the content recommendation interface shown in FIG2S (e.g., FIG200S ) in response to detecting a trigger operation on the operation control 251. It is understood that the terminal device 120 may also present any appropriate interface in response to detecting a trigger operation on the operation control 251, and this disclosure is not limited thereto.

[0086] Example 200S may include, for example, entry 271. The terminal device 120 may present prompt information (e.g., the text "Generating your avatar...") at entry 271 indicating that an avatar is being generated. In some embodiments, the terminal device 120 may also present creation progress information of an avatar (e.g., a first avatar) at entry 271. For example, the terminal device 120 may present the text "Created: XX%" at entry 271 to present creation progress information of the first avatar. In response to detecting a trigger operation on entry 271, the terminal device 120 may switch back to presenting example 200P.

[0087] After the creation of the avatar is complete, the terminal device 120 may also provide a push notification to indicate that the avatar creation is complete. The push notification may include a first viewing portal for viewing the created avatar. In some embodiments, the terminal device 120 may also provide first viewing portals of different styles. For example, if the user interface currently presented by the terminal device 120 is an interface provided by the application 120, the terminal device 120 may provide a first viewing portal of a first style. If the user interface currently presented by the terminal device 120 is not an interface that can be provided by the application 120, the terminal device 120 may provide a first viewing portal of a second style.

[0088] As shown in Figures 2T and 2U, example 200T may be, for example, a content recommendation interface provided by application 120, and example 200U may be, for example, an interface not provided by application 120 (i.e., an interface outside the interface provided by application 120). For example, terminal device 120 may provide a first viewing entry 272 in example 200T and a first viewing entry 273 in example 800B. In response to detecting a triggering operation on first viewing entry 272 or first viewing entry 273, terminal device 120 may present the created avatar.

[0089] In some embodiments, after the avatar is created, the terminal device 120 may also provide a second viewing entry for the avatar in the user interface, allowing users to view the created avatar. The user interface including the second viewing entry may, for example, be a user's message interface. As shown in Figures 2V and 2W, examples 200V and 200W may be user message interfaces. For example, in response to the creation of the avatar, the terminal device 120 may present a notification message viewing entry 274 in the message interface shown in example 200V. In some embodiments, the notification message viewing entry 274 may be permanently displayed in example 200V. In response to the creation of the avatar, the terminal device 120 may present a message prompt (e.g., the number 1) at the notification message viewing entry 274. In response to detecting a trigger operation for the notification message viewing entry 274, the terminal device 120 presents the message interface shown in example 200W. Example 200W includes a second viewing entry 275. In response to detecting a trigger operation for the second viewing entry 275, the terminal device 120 presents the created avatar.

[0090] In some embodiments, the terminal device 120 may also present an avatar image information interface (i.e., examples 200X to 200Z) for the avatar shown in Figures 2X to 2Z. The terminal device 120 may present the avatar information interface, for example, in response to the generation of the avatar or in response to a trigger for the avatar's image information. The avatar information interface may include at least one of a viewing portal corresponding to at least one style (e.g., portal 276-1, portal 276-2, portal 276-3, portal 276-4, etc., the present disclosure does not limit the number of at least one style) and a launch interface portal generated for a stylized image (e.g., portal 277). In response to detecting a trigger operation for a viewing portal corresponding to a style (e.g., portal 276-1), the terminal device 120 may present a style information interface for that style (as described below). In response to detecting a trigger operation for a launch interface portal (e.g., portal 277), the terminal device 120 may switch to presenting a launch interface generated for the stylized image, as described below.

[0091] The terminal device 120 may also present entry 278 in example 200X to provide more operations for the avatar. In response to detecting a trigger operation on entry 278, the terminal device 120 may present example 200Y of an interface such as that shown in FIG. 2Y. Example 200Y includes panel 280. Panel 280 may, for example, include controls 281, 282, and 283. In response to receiving a selection operation on control 281, the terminal device 120 may present a user interface including more operations for the avatar. In response to receiving a selection operation on control 283, the terminal device 120 may cancel presentation of panel 280. For example, the terminal device 120 may switch to presenting the interface shown in example 200X. In response to receiving a selection operation on control 282, the terminal device 120 may determine that a delete operation has been received for the avatar. To prevent accidental touches, the terminal device 120 may switch to presenting the interface shown in example 200Z. Example 200Z presents card 290. Card 290 includes a prompt indicating whether to delete the avatar. Terminal device 120 may determine to delete the avatar in response to a trigger operation on the delete control in card 290. Terminal device 120 may also determine to cancel the deletion of the avatar in response to a trigger operation on the return control in card 290. For example, terminal device 120 may return to presenting example 200X or example 200Y.

[0092] Example interface for generating element-specific images

[0093] The following describes an example process for generating an element-specific image. In some embodiments, element-specific image generation may be triggered by a startup interface for image generation. Exemplarily, the terminal device 120 may present a startup interface for image generation in response to a preset operation. Such a preset operation may, for example, include a trigger operation for a startup interface entry (e.g., entry 277) in the image information interface (e.g., example 200X) of the virtual image mentioned above. That is, the terminal device 120 may present a startup interface for image generation in response to detecting a trigger operation for a startup interface entry in the image information interface. Such a preset operation may also, for example, include a trigger operation for a specified operation control in the content shooting interface.

[0094] Some example embodiments are described with style as an example of an element and with stylized image generation as an example of element-specific image generation. However, it should be understood that the embodiments described with reference to "style" are applicable to other types of elements. Figure 3A shows an example of a content shooting interface (i.e., example 300A). The interface shown in example 300A includes a first startup interface entrance 301. In response to detecting a trigger operation for the first startup interface entrance 301, the terminal device 120 can switch to presenting a startup interface for stylized image generation.

[0095] Figure 3B shows an example of a startup interface generated for a stylized image (i.e., example 300B). As shown in Figure 3B, the interface shown in example 300B includes multiple image generation portals for different styles (e.g., portal 303-1, portal 303-2, portal 303-3, portal 303-4, etc.). It should be noted that in some embodiments, at least some of the multiple styles in the startup interface are pre-defined styles. Pre-defined styles may be styles that are provided by default by the application 120. In response to detecting a trigger for an image generation portal for a first style among the multiple styles (it is understood that the first style may be any of the multiple styles), the terminal device 120 may obtain a first image of a first avatar having the first style. The first avatar described herein is the avatar associated with the user who triggered the portal. In some embodiments, the first style may be any of the multiple pre-defined styles. For example, in response to detecting a trigger for portal 303-2, the terminal device 120 may obtain an image of the first avatar having style two. It is understood that the first image here can be generated locally by the terminal device 120, or generated by the server 130 and obtained by the terminal device 120 from the server 130. For ease of description, the following example uses the case where the first image is generated locally by the terminal device 120 as an example. For example, a machine learning model can be used to generate the first image based on the configuration information of the first avatar and the first style.

[0096] In some embodiments, in response to receiving a trigger operation for an image generation entrance of the first style in the startup interface, the terminal device 120 can also determine whether an image of the first virtual image with the first style has been previously generated, and / or whether an image of the first virtual image with the first style is currently being generated.

[0097] If an image of the first virtual image in the first style has not been previously generated and an image of the first virtual image in the first style is not currently being acquired, the terminal device 120 may present an interface as shown in example 300C of Figure 3C. The interface shown in example 300C includes a generation control 304. The terminal device 120 may begin generating the first image in response to receiving a trigger operation for the generation control 304. For example, the terminal device 120 may present a generation progress interface indicating the progress of image generation in response to receiving a trigger operation for the generation control 304, such as example 300D shown in Figure 3D (i.e., the terminal device 120 may present example 300D when the generation of the first image has just begun). The terminal device 120 may also update the generation progress interface during the generation of the first image, such as example 300E shown in Figure 3E. Examples 300D and 300E illustrate multiple examples of generation progress interfaces for the first image. In some embodiments, the terminal device 120 may also present a card 310 in response to a preset operation (e.g., a long press operation on the creation progress interface). For example, the terminal device 120 may switch to another interface provided by the presentation application 120 in response to receiving a trigger operation on the return control in the card 310, or in response to receiving a trigger operation on the confirmation control (e.g., control 305) in the generation progress interface. For example, the terminal device 120 may switch to the content recommendation interface of the presentation application 120 in response to detecting a trigger operation on the control 305.

[0098] In response to the first image being generated, the terminal device 120 may provide an example 300F as shown in FIG3F . Example 300F may be an example of a first content preview interface. As shown in FIG3F , the terminal device 120 may present the first image in the first content preview interface. The first image may be one of a plurality of images. For example, in response to receiving a selection operation for one or more images among a plurality of images, the terminal device 120 may determine that an editing operation for the one or more images has been received, and present a card 320. For example, in response to receiving a trigger operation for a delete control in the card 320, the terminal device 120 may delete the selected one or more images. For example, in response to receiving a trigger operation for a completion control in the card 320, the terminal device 120 may determine that the editing operation for the selected one or more images has been completed, and cancel the presentation of the card 320.

[0099] The content preview interface shown in Example 300F also includes an operation control 307 and an operation control 308. For example, the terminal device 120 can trigger the regeneration of all the first images in Example 300F in response to receiving a trigger operation for the operation control 307. For example, the terminal device 120 can switch to presenting Example 300G shown in Figure 3G in response to receiving a trigger operation for the operation control 308. Example 300G shows an example of a content editing interface for the first image. Card 330 is presented in Example 300G. The terminal device 120 can delete the generated first image in response to receiving a trigger operation for the delete control in card 330. The terminal device 120 can save the first image in response to receiving a trigger operation for the save control in card 330.

[0100] Example 300G also includes options for the publishing format of the first image. For example, example 300G may include an operation control 340. The operation control 340 includes the options "Picture" and "Video". The terminal device 120 may determine to publish the first image in picture format in response to receiving a trigger operation for the option "Picture". The terminal device 120 may determine to publish the first image in video format in response to receiving a trigger operation for the option "Video". Example 300G may also include an operation control 309. The terminal device 120 may determine to receive an edit confirmation (i.e., complete the editing of the first image) in response to receiving a trigger operation for the operation control 309, and switch to presenting a content publishing interface for the first image. Figure 3H shows an example of a content publishing interface for the first image (i.e., example 300H). Example 300H includes a publishing control 351, and the terminal device 120 may determine to receive a publishing confirmation and publish the first image in response to receiving a trigger operation for the publishing control 351. In some embodiments, the content publishing interface shown in example 300H may also include a style usage portal 371 for the first style (in this example, style 2). After the first image is published, the style usage portal 371 may be presented together with the first image, as will be described below with reference to FIG8A.

[0101] In some embodiments, if an image of a first avatar in a first style has been previously generated and is not currently being generated, the terminal device 120 may present example 300I, as shown in FIG3I . The interface shown in example 300I includes a view control 352 and a generate control 353. Generate control 353 here has similar functionality to generate control 304 in example 300C. In response to receiving a trigger operation on view control 352, the terminal device 120 may determine whether the previously generated first image has been published. If the previously generated first image has not been published, the terminal device 120 may switch to presenting example 300J, as shown in FIG3J . The interface shown in example 300J includes the previously generated first image of the first avatar in the first style. The interface shown in example 300J includes a publish control 354, a generate control 355, and a delete control 356. In response to receiving a trigger operation on publish control 354, the terminal device 120 may publish the previously generated first image. In response to receiving a trigger operation for the generate control 355, the terminal device 120 may continue to generate the first image of this time. In response to receiving a trigger operation for the delete control 356, the terminal device 120 may delete the previously generated first image. If the previously generated first image has been published, the terminal device 120 may switch to presenting example 300K as shown in Figure 3K. The content preview interface shown in example 300K may include the previously generated first image. The interface shown in example 300K may also include operation controls 307 and operation controls 308. Operation controls 307 and operation controls 308 will not be described in detail here.

[0102] In some embodiments, when a first image of a first virtual image having a first style is currently being acquired, the terminal device 120 may present an example 300L as shown in FIG3L . Example 300L includes an operation control 357 and a generation control 353. Since the first image is currently being generated, the generation control 353 may be in an unselectable state. In response to detecting a trigger operation for the generation control 353, the terminal device 120 may present a prompt indicating that the generation control 353 is unselectable in example 300L in any appropriate manner (including but not limited to a pop-up window, a card, etc.). For example, the terminal device 120 may present a creation progress interface of the first image in response to detecting a trigger operation for the operation control 357.

[0103] Example interface for adjusting image elements

[0104] In some embodiments, the user can be supported to adjust image elements and generate an image of the virtual image with the adjusted elements. The terminal device 120 can present an element adjustment interface in response to an element adjustment request for the first image of the first virtual image with the first element. The terminal device 120 can receive adjustment information for the first element via the element adjustment interface, and based on the received adjustment information, present a second image of the first virtual image with the adjusted first element. That is, if the user is not satisfied with the generated first image or has his own preferences, he can adjust the first element and generate a second image of the first virtual image with the adjusted first element based on the adjusted first element. In some embodiments, if the first element is a predetermined element, the first element can be regarded as a parent element, and the adjusted first element can be regarded as a child element of the parent element.

[0105] Continuing with the example of style, we will describe an example embodiment for adjusting image elements. However, it should be understood that the embodiments described with reference to style are applicable to other elements. In some embodiments, users can be supported to adjust style, and an image of a virtual avatar having the adjusted style can be generated. For example, terminal device 120 can present a style adjustment interface in response to a request to adjust the style of a first image of a first virtual avatar having a first style. Terminal device 120 can receive adjustment information for the first style via the style adjustment interface and, based on the received adjustment information, present a second image of the first virtual avatar having the adjusted first style. In other words, if the user is dissatisfied with the generated first image or has their own preferences, they can adjust the first style and generate a second image of the first virtual avatar having the adjusted first style based on the adjusted first style. In some embodiments, if the first style is a predetermined style, the first style can be considered a parent style, and the adjusted first style can be considered a child style of the parent style.

[0106] In some embodiments, the first content preview interface described above (e.g., examples 300F and 300K shown in FIG. 3F and FIG. 3K ) may include a style adjustment entry (e.g., entry 306). The terminal device 120 may determine, in response to detecting a trigger operation for the style adjustment entry, that a style adjustment request for a first image having a first style of a first virtual image has been received. The terminal device 120 may present a style adjustment interface in response to the style adjustment request for the first image. The style adjustment interface may, for example, include a first input control (e.g., a text input box, a voice input control, etc.) for receiving adjustment information, a first prompt information for the adjustment information, or at least one item in the first image. The first prompt information indicates an adjustable portion of the first style.

[0107] Figure 4A shows an example of a style adjustment interface (i.e., example 400A). As shown in Figure 4A, example 400A may include a first image 410. The terminal device 120 may present the first image 410 so that the user can adjust the configuration information of the first style by referring to the first image 410. This makes it easy for the user to adjust the style intuitively. Example 400A may also include a first input control 420, an area 430, and an input panel 440. The user may input adjustment information for the first style through the first input control 420. Alternatively, at least a portion of the current configuration information of the first style may be presented in the first input control 420. The user may modify the configuration information displayed in the first input control 420.

[0108] In some embodiments, the terminal device 120 may also stop displaying the first image in the style adjustment interface in response to receiving a preset operation for the style adjustment interface. That is, the first image is not displayed in the style adjustment interface. In addition, the terminal device 120 may increase the rendering area of ​​the first input control. As shown in Figures 4A and 4B, the terminal device 120 may, for example, present the interface shown in Example 400B in response to receiving an upward drag operation for the operation control 401 in Example 400A. The first image 410 is no longer presented in Example 400B, and the rendering area of ​​the first input control 420 in Example 400B is larger than the rendering area of ​​the first input control 420 in Example 400A.

[0109] Area 430 may include a cancel control 402 and a regenerate control 403. The terminal device 120 may obtain adjustment information input by the user via the input panel 440. In response to receiving a trigger operation for the cancel control 402, the terminal device 120 may determine to cancel the configuration information for adjusting the first style. For example, the terminal device 120 may return to presenting the first content preview interface. Furthermore, in response to detecting a trigger operation for the regenerate control 403, the terminal device 120 may determine the adjusted first style based on the adjusted configuration information for the first style and obtain a second image of the first virtual image having the adjusted first style. In some embodiments, the terminal device 120 may utilize a target model to generate the second image. For example, a prompt word may be generated based on the adjusted configuration information for the first style and provided to the target model. In another example, the adjusted configuration information for the first style and the first virtual image may be provided to the target model as image generation conditions. The embodiments of the present disclosure are not limited in this respect.

[0110] For example, the terminal device 120 may start acquiring the second image in response to receiving a trigger operation for regenerating the control 403. For example, the terminal device 120 may present the example 400C shown in Figure 4C. Example 400C is an example of a creation progress interface for the second image. Before acquiring the second image, the terminal device 120 may, for example, present indicative information about the generation progress based on the generation progress of the second image. For example, the terminal device 120 may present the text "XX%" and the text "Estimated time: XX hours XX minutes" in the interface shown in example 400C. For example, the terminal device 120 may switch to other interfaces that the presentation application 120 can provide in response to receiving a trigger operation for a certain control (such as control 404) in example 400C. Exemplarily, the terminal device 120 may switch to the content recommendation interface of the presentation application 120 in response to detecting a trigger operation for control 305.

[0111] In response to the second image being generated, the terminal device 120 may provide example 400D as shown in FIG4D . Example 400D may be an example of a second content preview interface for the second image. As shown in FIG4D , the terminal device 120 may present the second image in example 400D. In this example, multiple second images are presented. The second content preview interface may include a style adjustment portal (e.g., portal 405). In response to detecting a trigger operation on the style adjustment portal, the terminal device 120 may determine that a style adjustment request has been received for the second image of the first avatar having the adjusted first style. In other words, the user may further adjust the adjusted first style. Example 400D also includes operation controls 406 and 407. For example, in response to receiving a trigger operation on operation control 406, the terminal device 120 may regenerate all second images in example 400D. For example, in response to receiving a trigger operation on operation control 407, the terminal device 120 may switch to presenting example 400E as shown in FIG4E .

[0112] Example 400E is an example of a content editing interface for a second image. The interface shown in Example 400E includes options for the publishing format of the second image. For example, example 400E shows an operation control 404. Operation control 404 includes the options "Picture" and "Video." In response to receiving a trigger operation for the option "Picture," terminal device 120 may determine to publish the second image in picture format. In response to receiving a trigger operation for the option "Video," terminal device 120 may determine to publish the second image in video format. Example 400E may also include an operation control 409. In response to a trigger operation for operation control 409, terminal device 120 may determine that edit confirmation has been received (i.e., that editing of the second image has been completed) and switch to presenting a content publishing interface for the second image. Terminal device 120 may receive a publishing confirmation via this content publishing interface for the second image. In response to receiving the publishing confirmation, terminal device 120 may publish the second image. The content publishing interface for the second image is similar to the content publishing interface for the first image described above, and therefore will not be described in detail.

[0113] The above describes an example of adjusting the configuration information of the first style and obtaining the second image based on the adjusted configuration information. Now, multiple examples of the style adjustment interface (ie, examples 500A to 500J) are described in detail with reference to FIG. 5A to FIG. 5J .

[0114] For example, the terminal device 120 may present a style adjustment interface as shown in example 500A in response to receiving a trigger operation for a style adjustment entry (e.g., entry 306) in the first content preview interface (e.g., examples 300F and 300K shown in Figures 3F and 3K). As shown in Figure 5A, example 500A may include area 510. Area 510 may display at least a portion of the fixed configuration information of the first style. It should be noted that, when the first style includes fixed configuration information, the terminal device 120 may generate a prompt word based on the adjustment information and fixed configuration information for the first style. The terminal device 120 may provide the prompt word to a model (i.e., a target model) for generating an image. The terminal device 120 may obtain the output of the target model and obtain a second image based on the output.

[0115] Example 500A may also include a first input control 520, an area 530, and an input panel 540. Terminal device 120 may obtain adjustment information input by the user via input panel 540. In some embodiments, first input control 520 may present a first prompt for the adjustment information. The first prompt indicates an adjustable portion of the first style. For example, the first prompt may be the text "Add colors, objects, shapes, and other descriptions to customize your avatar," as shown in Example 500A.

[0116] Example 500A also includes a cancel control 501. In response to receiving a trigger operation for cancel control 501, terminal device 120 may determine to cancel the configuration information for adjusting the first style. For example, terminal device 120 may return to presenting the first content preview interface. Area 530 may include a generate control 502. Furthermore, in response to detecting a trigger operation for generate control 502, terminal device 120 may determine an adjusted first style based on the received adjustment information and fixed configuration information, and acquire a second image of the first avatar having the adjusted first style. For example, in response to receiving a trigger operation for generate control 502, terminal device 120 may begin acquiring the second image.

[0117] As shown in Figure 5B, the terminal device 120 can present the acquired adjustment information in the first input control 520 in Example 500B. For example, the terminal device 120 can also present all of the fixed configuration information of the first style in response to receiving a trigger operation for control 510. For example, the terminal device 120 can present the interface shown in Example 500C in response to receiving a trigger operation for control 510 in Example 500B. Control 510 in Example 500C includes all of the fixed configuration information of the first style.

[0118] In the case of obtaining the adjustment information via the first input control 520, the terminal device 120 may also determine the position of the input indicator in the first input control 520. The input indicator here may be, for example, the symbol "|" in the first input control 520 of Figure 5B. In response to the input indicator being located inside the adjustment information, the terminal device 120 may present the menu 503 shown in example 500D. The menu 503 may include a plurality of operation options for the adjustment information, such as the option "Paste", the option "Select", and the option "Select All". For example, the terminal device 120 may also present the menu 504 shown in example 500E in response to determining that part of the information in the adjustment information is selected. The menu 504 may include a plurality of operation options for the selected part of the adjustment information, such as the option "Cut", the option "Copy", and the option "Find".

[0119] For example, the terminal device 120 may also present the interface shown in Example 500F in response to receiving a preset operation (e.g., a cancel operation on the input panel 540) for the style adjustment interface (e.g., Example 500B). In Example 500F, the input panel 540 is no longer presented, and the presentation area of ​​the first input control 520 is increased. For example, the terminal device 120 may also present the interface shown in Example 500G in response to receiving a preset operation (e.g., a delete operation) on the first input control 520. The interface of Example 500G includes a card 505. Card 505 includes a prompt to confirm whether to delete the adjustment information. Card 505 also includes a cancel control and a discard control. In response to receiving a trigger operation on the cancel control in card 505, the terminal device 120 may cancel the deletion of the adjustment information. In response to receiving a trigger operation on the discard control in card 505, the terminal device 120 may delete the received adjustment information presented in the first input control 520.

[0120] In some embodiments, the terminal device 120 may also verify the received adjustment information in response to an image generation request associated with the adjustment information, that is, determine whether the adjustment information meets preset conditions. The preset conditions may involve any suitable attributes related to the adjustment information, for example, may include whether the grammar of the text is correct, whether the wording is appropriate, whether the number of words is less than a threshold, and so on. The terminal device 120 may, for example, determine that an image generation request has been received and verify the received adjustment information in response to receiving a trigger operation for the generation control 502. In the process of verifying the adjustment information, the terminal device 120 may, for example, present the interface shown in Example 500H. In Example 500H, the terminal device 120 may present a prompt message in the generation control 502 indicating that verification is currently being performed. The terminal device 120 may, for example, indicate that verification is currently being performed by presenting a specific interface element.

[0121] If the adjustment information meets the preset conditions, i.e., passes verification, terminal device 120 may acquire a second image based on the adjustment information and the fixed configuration information. If the adjustment information does not meet the preset conditions, i.e., fails verification, terminal device 120 may present a corresponding prompt indicating that the adjustment information has failed verification. As shown in FIG5I , if the adjustment information fails verification, terminal device 120 may present example 500I. Terminal device 120 may present a prompt in area 530 of example 500I, "Unable to process this prompt. Please edit and try again," to inform the user that the adjustment information has failed verification.

[0122] In some embodiments, the terminal device 120 may also, in response to receiving the adjustment information, directly verify the adjustment information by default. As shown in Figure 5H, if the adjustment information fails verification, the terminal device 120 may also present example 500H. The terminal device 120 may present a pop-up window 506 in example 500H. For example, the terminal device 120 may present a prompt message in the pop-up window, "You have reached the upper limit of XX words," to inform the user that the adjustment information failed verification.

[0123] By verifying the adjustment information input by the user, the validity of the adjustment can be guaranteed, which helps the user to adjust the style conveniently.

[0124] In this embodiment, users can adjust the existing style to obtain a style that satisfies their preferences. In this way, the threshold for using styles is lowered while also ensuring the diversity of styles.

[0125] Example interface for custom image elements

[0126] In some embodiments, users can be supported to customize new elements without being limited to the predetermined elements provided by the application 120. For example, the terminal device 120 can present an element customization interface in response to an element customization request. The terminal device 120 can receive customization information for a new element (also referred to as a second element) via the element customization interface, and based on the received customization information, present a third image of the first virtual image with the second element. The customization information can be configuration information of the second element or at least a partial definition of the second element. That is, the user can customize a new element by himself, and generate a third image of the first virtual image with the second element based on the second element. In some embodiments, this customized second element can be regarded as a parent element. In addition, adjustment of the second element can also be supported. The adjusted second element can be regarded as a sub-style.

[0127] Continuing to use style as an example to describe the example embodiments of customizing image elements, it should be understood that the embodiments described with reference to style are applicable to other elements. In some embodiments, users can be supported to customize new styles, without being limited to the predetermined styles provided by application 120. For example, terminal device 120 can present a style customization interface in response to a style customization request. Terminal device 120 can receive customization information for a new style (also referred to as a second style) via the style customization interface, and based on the received customization information, present a third image of the first virtual image with the second style. The customization information can be configuration information of the second style or at least a partial definition of the second style. That is, the user can customize a new style by himself and generate a third image of the first virtual image with the second style based on the second style. In some embodiments, this customized second style can be regarded as a parent style. In addition, adjustments to the second style can also be supported. The adjusted second style can be regarded as a child style.

[0128] In some embodiments, the startup interface generated for the stylized image described above (e.g., example 300B shown in FIG. 3B ) may include a style customization portal (e.g., portal 302 ). The terminal device 120 may determine that a style customization request has been received in response to detecting a trigger operation for the style customization portal. The terminal device 120 may present a style customization interface in response to the style customization request. The style customization interface may include, for example, a second input control (e.g., a text input box, a voice input control, etc.) for receiving customization information and / or a second prompt for the customization information. The second prompt indicates a customizable element.

[0129] Figure 6A is an example of a style customization interface (i.e., example 600A). As shown in Figure 6A, the interface shown in example 600A may include a second input control 610, an area 620, and an input panel 630. In some embodiments, a second prompt for customization information may be presented in second input control 610 to indicate to the user the style configuration information that can be entered. The second prompt may be, for example, the text "Add colors, objects, shapes, and other descriptions to customize your avatar" as shown in example 600A.

[0130] Region 620 may include a generate control 601. Terminal device 120 may obtain customized information input by the user via input panel 630. As shown in FIG6B , terminal device 120 may present the obtained customized information in second input control 610 in example 600B.

[0131] In response to detecting a trigger operation on the generation control 601, the terminal device 120 may also determine a second style based on the received customization information and obtain a third image of the first avatar in the second style. In some embodiments, the terminal device 120 may utilize a target model to generate the third image. For example, a prompt word may be generated based on the customization information and provided to the target model. In another example, the customization information and the first avatar may be provided to the target model as image generation conditions, and the target model may generate the third image accordingly.

[0132] For example, the terminal device 120 may start acquiring the third image in response to receiving a trigger operation for generating control 601. For example, the terminal device 120 may present example 600C shown in Figure 6C. Example 600C shows an example of a creation progress interface for the third image. Before acquiring the third image, the terminal device 120 may, for example, present indicative information about the generation progress based on the generation progress of the third image. For example, the terminal device 120 may present indicative information about the generation progress of the third image by presenting the text "estimated time: XX hours XX minutes" in example 600C. For example, the terminal device 120 may switch to other interfaces that can be provided by the presentation application 120 in response to receiving a trigger operation for a certain control (such as control 602) in example 600C. Exemplarily, the terminal device 120 may switch to the content recommendation interface of the presentation application 120 in response to detecting a trigger operation for control 602.

[0133] In response to the third image being generated, the terminal device 120 may provide example 600D as shown in FIG6D . Example 600D may be an example of a third content preview interface corresponding to the third image. As shown in FIG6D , the terminal device 120 may present the third image in example 600D. The third image may also include multiple images. Example 600D may include a style adjustment portal (e.g., portal 605). In response to detecting a trigger operation on the style adjustment portal, the terminal device 120 may determine that a style adjustment request has been received for a third image having a second style of the first virtual avatar. Example 600D also includes operation controls 604 and operation controls 605. For example, in response to receiving a trigger operation on operation control 604, the terminal device 120 may regenerate all third images in example 600D. For example, in response to receiving a trigger operation on operation control 605, the terminal device 120 may switch to presenting example 600E as shown in FIG6E .

[0134] Example 600E illustrates an example of a content editing interface for a third image. Example 600E includes options for the publishing format of the third image. For example, example 600E may include an operation control 606. Operation control 606 includes the options "Picture" and "Video." In response to receiving a trigger operation for the "Picture" option, terminal device 120 may determine to publish the third image in picture format. In response to receiving a trigger operation for the "Video" option, terminal device 120 may determine to publish the third image in video format. Example 600E may also include an operation control 607. In response to receiving a trigger operation for operation control 607, terminal device 120 may determine that edit confirmation has been received (i.e., that editing of the third image has been completed) and switch to presenting a content publishing interface for the third image. Terminal device 120 may receive a publishing confirmation via this content publishing interface for the third image. In response to receiving the publishing confirmation, terminal device 120 may publish the third image. The content publishing interface for the third image is similar to the content publishing interface for the first image described above, and therefore will not be described in detail.

[0135] The above describes an example of obtaining customization information for a second style and obtaining a third image based on the customization information. Multiple examples of the style adjustment interface (i.e., examples 700A to 700G) are described in detail below in conjunction with Figures 7A to 7G. The second input control 710 in Examples 700A to 700G may correspond to the second input control 610 in Examples 600A and 600B, the area 720 and the generated control 701 may correspond to the area 620 and the generated control 601, and the input panel 730 may correspond to the input panel 630.

[0136] In the case of obtaining customized information via the second input control 710, the terminal device 120 may also determine the position of the input indicator in the second input control 710. The input indicator here may be, for example, the symbol "|" in the second input control 710. In response to the input indicator being located inside the adjustment information, the terminal device 120 may present the menu 702 shown in example 700A. The menu 702 may include a plurality of operation options for customized information, such as the option "Paste", the option "Select", and the option "Select All". For example, the terminal device 120 may also present the menu 703 shown in example 700B in response to determining that part of the information in the adjustment information is selected. The menu 703 may include a plurality of operation options for the selected part of the customized information, such as the option "Cut", the option "Copy", and the option "Find".

[0137] For example, the terminal device 120 may also present example 700C in response to receiving a preset operation for the style customization interface (e.g., a cancel operation for the input panel 730). In example 700C, the input panel 730 is canceled and the rendering area of ​​the second input control 710 is increased. For example, the terminal device 120 may also present example 700D in response to receiving a preset operation for the second input control 710 (e.g., a delete operation). Example 700D includes card 704. Card 704 includes prompt information prompting confirmation whether to delete the customized information. Card 704 also includes a cancel control and a discard control. In response to receiving a trigger operation for the cancel control in card 704, the terminal device 120 may cancel the deletion of the customized information. In response to receiving a trigger operation for the discard control in card 704, the terminal device 120 may delete the received customized information presented in the second input control 710.

[0138] In some embodiments, the terminal device 120 may also verify the received customization information in response to an image generation request associated with the customization information, that is, determine whether the received customization information meets preset conditions. Such preset conditions may involve any suitable attributes related to the customization information, for example, whether the grammar of the text is correct, whether the wording is appropriate, whether the number of words is less than a threshold, etc. The terminal device 120 may, for example, determine that an image generation request has been received and verify the received customization information in response to receiving a trigger operation for the generation control 701. In the process of verifying the customization information, the terminal device 120 may, for example, present example 700E. In example 700E, the terminal device 120 may present a prompt message in the generation control 701 indicating that verification is currently being performed. The terminal device 120 may, for example, indicate that verification is currently being performed by presenting a specific element.

[0139] If the customized information meets the preset conditions, i.e., passes verification, terminal device 120 may acquire a third image based on the customized information. If the customized information does not meet the preset conditions, i.e., fails verification, terminal device 120 may present a corresponding prompt indicating that the customized information has failed verification. As shown in FIG7F , if the adjustment information fails verification, terminal device 120 may present example 700F. Terminal device 120 may present a prompt in area 720 of example 700F, "Unable to process this prompt. Please edit and try again," to inform the user that the customized information has failed verification.

[0140] In some embodiments, the terminal device 120 may also, in response to receiving the customized information, directly verify the customized information by default. As shown in Figure 7G, if the adjusted information fails verification, the terminal device 120 may also present example 700G. The terminal device 120 may present a pop-up window 705 in example 700G. For example, the terminal device 120 may present a prompt message in the pop-up window, "You have reached the upper limit of XX characters," to inform the user that the customized information failed verification.

[0141] Through the above examples, the embodiments of the present disclosure can provide users with a variety of different styles for generating stylized images. At the same time, users can adjust the styles to suit their preferences. This advantageously increases creative flexibility and stylistic diversity, thereby enhancing interactivity and fun. Furthermore, in some embodiments, users can further customize their styles, further enhancing creative flexibility.

[0142] Example interface for reusing elements

[0143] In some embodiments, if a user posts an image (which may be in the form of a picture or video) with a certain element, other users may be enabled to use this element to generate images of their own associated avatars. Such an example embodiment is described below. For illustrative purposes only, assume that a first user is associated with a first avatar of a first object (e.g., the first object may be the first user); and a second user different from the first user is associated with a second avatar of a second object (e.g., the second object may be the second user). The first user posts a fourth image of the first avatar with a third element.

[0144] Continuing to use style as an example to describe an example embodiment of reusing elements, it should be understood that the embodiments described with reference to style are applicable to other elements. In some embodiments, if a user publishes an image with a certain style (which can be in the form of a picture or a video), other users can be supported to use this style to generate images of virtual images associated with themselves. Such an example embodiment is described below. For descriptive purposes only, it is assumed that a first user is associated with a first virtual image of a first object, for example, the first object can be the first user; a second user different from the first user is associated with a second virtual image of a second object, for example, the second object can be the second user. The first user publishes a fourth image of the first virtual image with a third style.

[0145] The second user's terminal device 120 can present a fourth image of the first virtual avatar in a third style and a style usage entry for the third style. In some embodiments, the fourth image and style usage entry can be presented in a content recommendation interface. For example, when the second user browses an information stream or content posted by a user they follow, the fourth image and style usage entry can be presented to the second user. Then, based on triggering the style usage entry, the terminal device 120 can present a fifth image of the second virtual avatar in the third style. In other words, if a user browses an image in a style they like, they can use that style to generate a new image.

[0146] In some embodiments, the third style may include a parent style and a child style obtained by partially adjusting the parent style. For example, the parent style may be a predefined style in application 125. For another example, the parent style may be a user-customized style, as described above. The child style may be generated through the style adjustment process described above.

[0147] In some embodiments, if a style usage portal is triggered, terminal device 120 may present a style information interface for a third style, such as a style details page. The style information interface may include a portal for generating a first image in the third style, or a portal for viewing at least one image in the third style. Based on an operation associated with the style information interface, terminal device 110 may obtain a fifth image in the third style for the second avatar. In other words, based on an operation associated with the style information interface, the second user may trigger the creation of an image in the same or similar style using their associated avatar.

[0148] Some example interfaces are described with reference to Figures 8A to 8I. Figure 8A shows an example 800A of a content recommendation interface. The interface includes an image 801 of a first virtual image having style two (which is an example of the third style) and a style usage entry 802 for style two. If the style usage entry 802 is triggered, the terminal device 120 can present example 800B of Figure 8B, which is an example of a style information interface. Example 800B shows a style information interface for style two. The style information interface includes basic information of the style, such as the name displayed in area 806, the number of published works, etc.

[0149] The style information interface may include a first image generation entry for the third style, such as first image generation entry 805. In some embodiments, if first image generation entry 805 is triggered, terminal device 120 may obtain the fifth image. In other words, terminal device 120 may use the second avatar to generate an image having the third style.

[0150] The style information interface may include a viewing portal for at least one image having the third style, such as viewing portal 803 and viewing portal 804 shown in FIG8B . If a viewing portal is triggered, a viewing interface for the corresponding image may be presented. This viewing interface may include another image generation portal for the third style, also referred to as a second image generation portal. For example, if viewing portal 803 is triggered, terminal device 110 may present the image viewing interface shown in example 800C of FIG8C . This image viewing interface includes the corresponding image, style usage portal 807, and second image generation portal 808. If second image generation portal 808 is triggered, terminal device 120 may obtain a fifth image.

[0151] It should be noted here that, in some embodiments, if the third style is a parent style, the image corresponding to the viewing entry included in the style information interface may be an image with the parent style and / or an image with a sub-style under the parent style. For example, Style Two is the parent style. The image in the style information interface shown in Example 800B may have Style Two or a sub-style of Style Two. For example, the image corresponding to the viewing entry 803 has the sub-style "Style Two-User 345". The suffix "-User 345" in the style name may indicate that "User 345" adjusted Style Two to obtain the sub-style. In this case, the style name displayed in the style usage entry 807 is the name of the sub-style, as shown in Figure 8C.

[0152] In some embodiments, if the third style is a sub-style, the image corresponding to the viewing portal included in the style information interface can be an image with the sub-style and / or an image with the parent style of the sub-style. In addition, what is displayed in area 806 is the name of the sub-style.

[0153] Continuing with the description of stylized image generation, if the first image generation portal 805 or the second image generation portal 808 is triggered, the terminal device 120 may trigger the generation of the fifth image. If the current second user does not have an associated avatar, that is, if the second avatar has not yet been created, the terminal device 120 may present an avatar creation portal or an introduction interface for avatars. For example, the terminal device 120 may present the interface shown in Figure 2A or Figure 2B to guide the second user in creating their associated second avatar. In this case, if the creation of the second avatar takes a long time, a fifth image of the second avatar in the third style may be automatically generated after the second avatar is created, without requiring the second user to re-enter the process. After the fifth image is generated, a notification or prompt may be sent to the second user via various suitable means, prompting the second user to view the fifth image. Such notification or prompt may include, but is not limited to, a notification in the content recommendation interface, a message in the inbox, a system message on the terminal device 120, and the like.

[0154] In some embodiments, if the current second user has a created avatar, the terminal device 110 may allow the second user to select whether to use the created avatar or to create a new avatar and use the newly created avatar. In some embodiments, if the current second user has multiple created avatars, the terminal device 110 may allow the second user to select a avatar to use from the created avatars.

[0155] In some embodiments, if the current second user has a created second avatar, the terminal device 110 can directly trigger the generation of the fifth image using the second avatar. For example, if the first image generation portal 805 is triggered, the terminal device 120 can present the interface shown in example 800D of Figure 8D, which indicates the triggering of the generation of the fifth image.

[0156] In some embodiments, during the process of generating the fifth image, the terminal device 120 may present a generation progress interface for indicating the image generation progress according to the generation progress of the fifth image, such as example 800E shown in FIG8E and example 800F shown in FIG8F . The generation progress interface may also include a determination control, such as control 809 in example 800E and control 810 in example 800F. If a trigger operation for the determination control in the generation progress interface is received, the terminal device 120 may switch to other interfaces that the presentation application 120 can provide. For example, the terminal device 120 may switch to the content recommendation interface of the presentation application 120 in response to detecting a trigger operation for control 809 or 810.

[0157] After the fifth image is generated or in response to the second user's viewing operation, the terminal device 120 may present a content preview interface for the fifth image. For example, example 800G in Figure 8G is an example of a content preview interface. The content browsing interface may include multiple fifth images. Through the content browsing interface, the second user may further edit these images or delete one or more of them.

[0158] In some embodiments, based on the second user's operation, terminal device 120 may publish a fifth image. The content preview interface shown in example 800G also includes an operation control 813 and an operation control 812. For example, terminal device 120 may trigger the regeneration of the fifth image in response to receiving a trigger operation on operation control 813. For example, terminal device 120 may switch to presenting example 800H shown in FIG8H in response to receiving a trigger operation on operation control 812. Example 800H shows an example of a content editing interface for the fifth image.

[0159] The content editing interface shown in example 800H includes options for the publishing format of the fifth image. For example, example 800H may include an operation control 814. Operation control 814 includes the options "Picture" and "Video." In response to receiving a trigger operation for the option "Picture," the terminal device 120 may determine to publish the fifth image in picture format. In response to receiving a trigger operation for the option "Video," the terminal device 120 may determine to publish the fifth image in video format. The content editing interface shown in example 800H may also include an operation control 815. In response to receiving a trigger operation for operation control 815, the terminal device 120 may determine that edit confirmation has been received (i.e., that editing of the fifth image has been completed) and switch to presenting the content publishing interface for the fifth image. Figure 8I shows an example of a content publishing interface for the fifth image (i.e., example 800I). Example 800I includes a publish control 817. In response to receiving a trigger operation for publish control 817, the terminal device 120 may determine that publish confirmation has been received and publish the fifth image. In some embodiments, the content publishing interface shown in example 800I may further include a style usage entry 816 for a third style (Style 2 in this example). It should be understood that if a sub-style is used, the style usage entry 816 presents the name of the sub-style, such as "Style 2 - User 345".

[0160] In some embodiments, a second user can be supported to adjust the style, and an image of the second virtual avatar having an adjusted third style can be generated. For example, in response to a request to adjust the style of a fifth image of the second virtual avatar having the third style, the terminal device 120 can present a style adjustment interface. The terminal device 120 can receive adjustment information for the third style via the style adjustment interface and, based on the received adjustment information, present a sixth image of the second virtual avatar having the adjusted third style. In other words, if the second user is dissatisfied with the generated fifth image or has their own preferences, they can adjust the third style and generate an image of the second virtual avatar having the adjusted third style based on the adjusted third style.

[0161] In some embodiments, the content preview interface described above may include a style adjustment portal. For example, the content preview interface shown in example 800G may include portal 811. In response to detecting a trigger operation for the style adjustment portal, terminal device 120 may determine that a style adjustment request has been received for a fifth image of the second avatar having a third style. In response to the style adjustment request for the fifth image, terminal device 120 may present the style adjustment interface.

[0162] Adjustments to the third style are similar to those described above for the first style, so they will not be repeated here. Note that if a second user makes adjustments to the third style, creating a new sub-style, the style name displayed in the style usage portal after the image is published may include information about the second user. For example, if the second user is "User 567" and makes adjustments to Style 2, the style name displayed in the style usage portal may be "Style 2 – User 567."

[0163] In this embodiment, existing styles can be used through content published by other users, which helps to enhance interactivity.

[0164] Management of element-specific images and elements

[0165] In some embodiments, an image information interface for a virtual image may be provided to manage images of different elements possessed by the virtual image. Continuing to use style as an example to describe the example embodiment of image and element management, it should be understood that the embodiment described with reference to style is applicable to other elements. In some embodiments, an image information interface for a virtual image may be provided to manage images of different styles possessed by the virtual image. As shown in FIG9A , the terminal device 120 may provide a user information interface for a user as shown in Example 900A. In the case where user 110 (for example, "user 123" in the figure) has created a virtual image, the terminal device 120 may provide an entry 901 for an image information interface for the virtual image in the interface of Example 900A.

[0166] If entry 901 is triggered, the avatar information interface shown in example 900B of FIG9B may be presented. The avatar information interface displays basic information about the avatar, such as the creation time, thumbnail, etc. The avatar information interface may also include viewing entries for images of different styles.

[0167] For example, view entry 902 corresponds to adjusted style 1, and images with this style are currently queued. View entry 903 corresponds to style 3, and images with this style are currently being generated. If view entry 903 is clicked, terminal device 120 may present the interface shown in example 900C of FIG. 9C . This interface displays information on the image generation progress.

[0168] For another example, view entry 904 corresponds to style 1, and an image having this style has been generated. If view entry 904 is triggered, terminal device 120 may present example 900D of FIG. 9D . The interface of example 900D includes the generated image having style 1, view entry 907 for style 1, controls 908, controls 909, and controls 910.

[0169] If the image in example 900D is clicked, example 900E shown in FIG9E may be presented. If the publish control 911 is triggered, the terminal device 120 may present example 900F shown in FIG9F. Example 900F is an example of a content editing interface, which is similar to the content editing interface described above and will not be described in detail. If the share control 912 is triggered, the terminal device 120 may present the interface shown in example 900I shown in FIG9I.

[0170] Continue to refer to Figure 9D. If the publish control 908 is triggered, the terminal device 120 can present a content preview interface, as shown in example 900G of Figure 9G. This content preview interface is similar to the various content preview interfaces described above, so it will not be repeated here. If the regenerate control 909 is triggered, the terminal device 120 can trigger the regeneration of an image with style one of the virtual image. Accordingly, the terminal device 120 can present a generation progress interface for image generation, similar to that described above. If the delete control 910 is triggered, the terminal device 120 can present an interface as shown in example 900J of Figure 9J. The interface includes a card 913 for the user to confirm whether to delete. In some embodiments, if all stylized images are deleted, the terminal device 120 can present the interface shown in example 900K of Figure 9K. The interface includes prompt information 914 to prompt the user to select a style to generate the image.

[0171] 9D . If the viewing entry 907 is triggered, the terminal device 120 may present a style information interface for the style, such as a style details page. FIG9H shows an example of a style information interface 900H, which is similar to that described in FIG8B above and will not be described in detail.

[0172] Continuing with Figure 9B , the avatar's image information interface may also include a startup interface entry 906 for stylized image generation. In response to detecting a trigger operation on startup interface entry 906 , terminal device 120 may switch to a startup interface presenting stylized image generation, such as the interface shown in Figure 3B .

[0173] The avatar's image information interface may also include an entry 920 to provide more operations for the avatar. In response to detecting a trigger operation for entry 920, the terminal device 120 may present an interface such as that shown in example 900L of Figure 9L. The interface includes a panel 930. Panel 930 may, for example, include controls 931, controls 932, and the like. In response to receiving a trigger for control 931, the terminal device 120 may regenerate the avatar. If control 932 is triggered, the terminal device 120 may, for example, switch to the interface shown in example 900M, in which card 940 is presented. Card 940 includes prompt information prompting a user to determine whether to delete the avatar. In response to receiving a trigger operation for the delete control in card 940, the terminal device 120 may determine to delete the avatar.

[0174] In some embodiments, the creator of a style (including the creator of a parent style and the creator of a child style) can manage the created style. Some examples are described with reference to Figures 10A to 10F. The interface shown in example 1000A of Figure 10A includes a style usage entry 1001 for the sub-style "Style 2-XX". If the style usage entry 1001 is triggered, the terminal device 120 can present the style information interface of the style, as shown in example 1000B of Figure 10B.

[0175] In the interface of example 1000B, entrance 1002 is included. If entrance 1002 is triggered, terminal device 120 can present panel 1003 in the interface shown in example 1000C, as shown in Figure 10C. Panel 1003 includes a delete control 1004 for this style. If delete control 1004 is triggered, terminal device 120 can present card 1005, as shown in example 1000D of Figure 10D. If delete control 1006 in card 1005 is triggered, terminal device 120 can present confirmation control 1007, as shown in example 1000E of Figure 10E. If confirmation control 1007 is triggered, the interface shown in example 1000A is updated to the interface shown in example 1000F. That is, the style usage entrance for this style is no longer presented. However, the generated image with this style can still be presented.

[0176] Although in the above description, requests, instructions or selections from users are received or detected through interface elements such as controls and portals, it should be understood that this is merely exemplary. In some embodiments, there may be no such interface elements, and requests, instructions or selections may be given through natural language (including text or voice).

[0177] Example Process

[0178] FIG11 shows a flow chart of a process 1100 for image generation according to some embodiments of the present disclosure. The process 1100 may be implemented at the terminal device 120. The process 1100 is described below with reference to FIG1.

[0179] In block 1110 , the terminal device 120 presents an element adjustment interface in response to an element adjustment request for a first image having a first element of a first virtual avatar, where the first virtual avatar includes media data representing an appearance feature of a first object.

[0180] In block 1120 , the terminal device 120 receives adjustment information for the first element via the element adjustment interface.

[0181] In block 1130 , the terminal device 120 presents a second image of the first avatar having the adjusted first element based on the received adjustment information.

[0182] In some embodiments, the element adjustment interface includes at least a portion of fixed configuration information of the first element, and process 1100 further includes acquiring a second image based on the received adjustment information and the fixed configuration information.

[0183] In some embodiments, acquiring the second image includes: determining whether the adjustment information satisfies a preset condition in response to an image generation request associated with the adjustment information; and acquiring the second image based on the adjustment information and the fixed configuration information in response to the adjustment information satisfying the preset condition.

[0184] In some embodiments, the element adjustment interface includes at least one of the following: a first input control for receiving adjustment information, first prompt information for the adjustment information, the first prompt information indicating an adjustable portion of the first element, or a first image.

[0185] In some embodiments, process 1100 further includes: in response to a preset operation on the element adjustment interface, stopping displaying the first image in the element adjustment interface; and increasing a presentation area of ​​the first input control.

[0186] In some embodiments, the element adjustment request is received by: presenting a first content preview interface including a first image and an element adjustment portal; and receiving the element adjustment request via the element adjustment portal.

[0187] In some embodiments, presenting the first content preview interface includes: in response to a preset operation, presenting a startup interface for image generation, the startup interface including image generation entrances for multiple elements, the multiple elements including a first element; based on triggering the image generation entrance of the first element, obtaining the first image; and in response to obtaining the first image, presenting the first content preview interface.

[0188] In some embodiments, the preset operation includes at least one of the following: triggering a first start interface entry in the content shooting interface, or triggering a second start interface entry in the image information interface of the first virtual image.

[0189] In some embodiments, presenting the first content preview interface includes: presenting an image information interface of the first virtual image, the image information interface including a viewing entrance corresponding to at least one element, the at least one element including the first element; and presenting the first content preview interface based on triggering the viewing entrance corresponding to the first element.

[0190] In some embodiments, acquiring the second image includes: generating a prompt word based on the adjustment information and the fixed configuration information; providing the prompt word to the target model to obtain an output of the target model; and acquiring the second image based on the output.

[0191] In some embodiments, the process 1100 further includes: before acquiring the second image, presenting indication information about the generation progress according to the generation progress of the second image.

[0192] In some embodiments, process 1100 also includes: in response to a request to publish the second image, presenting a content editing interface for the second image; in response to receiving an edit confirmation via the content editing interface, presenting a content publishing page for the second image; and in response to receiving a publishing confirmation via the content publishing page, publishing the second image.

[0193] In some embodiments, the content editing interface includes options for a publishing format of the second image.

[0194] In some embodiments, process 1100 further includes: presenting an element customization interface in response to an element customization request; receiving customization information for the second element via the element customization interface; and presenting a third image of the first virtual image with the second element based on the received customization information.

[0195] In some embodiments, process 1100 further includes: in response to an image generation request associated with the customized information, determining whether the customized information satisfies a preset condition; and in response to the customized information satisfying the preset condition, acquiring a third image based on the customized information.

[0196] In some embodiments, the element customization interface includes at least one of the following: a second input control for receiving customization information, or second prompt information for the customization information, the second prompt information indicating a customizable element.

[0197] In some embodiments, the element customization request is received in the following manner: in response to a preset operation, presenting a startup interface for image generation, the startup interface including an image generation entrance and an element customization entrance for each of multiple elements; and receiving the element customization request via the element customization entrance.

[0198] In some embodiments, process 1100 also includes: presenting an image acquisition interface in response to an image creation request; determining multiple images of the first object based on at least one of the following operations via the image acquisition interface: a selection operation of an already captured image, or an image capture operation; and acquiring a first virtual image based on the multiple images in response to an image creation confirmation.

[0199] In some embodiments, process 1100 also includes: in response to image creation confirmation, presenting a creation progress interface based on the creation progress of the first virtual image; and in response to a preset operation for the creation progress interface, presenting a content recommendation interface, the content recommendation interface including creation progress information of the first virtual image.

[0200] In some embodiments, process 1100 further includes presenting an image information interface of the first virtual image, the image information interface including at least one of the following: a viewing portal corresponding to at least one element, or a start interface portal generated for the image.

[0201] In some embodiments, the image information interface of the first virtual image is presented in response to at least one of the following: triggering a notification message indicating that the creation of the first virtual image is complete, or triggering a virtual image entry in the user information interface of the user associated with the first virtual image.

[0202] In some embodiments, the first element includes at least one of the following: image style, image background, or image foreground.

[0203] Example devices and equipment

[0204] Embodiments of the present disclosure also provide corresponding apparatuses for implementing the above-described methods or processes. Figure 12 shows a schematic block diagram of an apparatus 1200 for image generation according to certain embodiments of the present disclosure. Apparatus 1200 may be implemented as or included in a terminal device 120. Each module / component in apparatus 1200 may be implemented using hardware, software, firmware, or any combination thereof.

[0205] As shown in Figure 12, device 1200 includes an interface presentation module 1210 configured to present an element adjustment interface in response to an element adjustment request for a first image of a first virtual avatar having a first element, the first virtual avatar including media data representing the appearance characteristics of a first object. Device 1200 also includes an information receiving module 1220 configured to receive adjustment information for the first element via the element adjustment interface. Device 1200 also includes an image presentation module 1230 configured to present a second image of the first virtual avatar having the adjusted first element based on the received adjustment information.

[0206] In some embodiments, the element adjustment interface includes at least a portion of the fixed configuration information of the first element, and the apparatus 1200 further includes: an image acquisition module configured to acquire a second image based on the received adjustment information and the fixed configuration information.

[0207] In some embodiments, the image acquisition module is further configured to: determine whether the adjustment information meets a preset condition in response to an image generation request associated with the adjustment information; and acquire a second image based on the adjustment information and the fixed configuration information in response to the adjustment information meeting the preset condition.

[0208] In some embodiments, the element adjustment interface includes at least one of the following: a first input control for receiving adjustment information, first prompt information for the adjustment information, the first prompt information indicating an adjustable portion of the first element, or a first image.

[0209] In some embodiments, the device 1200 further includes: a first image stop display module configured to stop displaying the first image in the element adjustment interface in response to a preset operation on the element adjustment interface; and increase the presentation area of ​​the first input control.

[0210] In some embodiments, the device 1200 further includes an element adjustment module configured to receive an element adjustment request by: presenting a first content preview interface including a first image and an element adjustment entry; and receiving the element adjustment request via the element adjustment entry.

[0211] In some embodiments, the element adjustment module is further configured to: in response to a preset operation, present a startup interface for image generation, the startup interface including image generation entrances for multiple elements, the multiple elements including a first element; based on triggering the image generation entrance of the first element, obtain a first image; and in response to obtaining the first image, present a first content preview interface.

[0212] In some embodiments, the preset operation includes at least one of the following: triggering a first start interface entry in the content shooting interface, or triggering a second start interface entry in the image information interface of the first virtual image.

[0213] In some embodiments, the element adjustment module is further configured to: present an image information interface of the first virtual image, the image information interface including a viewing entrance corresponding to at least one element, the at least one element including the first element; and based on triggering the viewing entrance corresponding to the first element, present a first content preview interface.

[0214] In some embodiments, the image acquisition module is further configured to: generate a prompt word based on the adjustment information and the fixed configuration information; provide the prompt word to the target model to obtain an output of the target model; and acquire a second image based on the output.

[0215] In some embodiments, the apparatus 1200 further includes: an indication information presentation module configured to present indication information about a generation progress according to a generation progress of the second image before acquiring the second image.

[0216] In some embodiments, the device 1200 also includes: an editing interface presentation module, configured to present a content editing interface for the second image in response to a request to publish the second image; a second image presentation module, configured to present a content publishing page for the second image in response to receiving an editing confirmation via the content editing interface; and a second image publishing module, configured to publish the second image in response to receiving a publishing confirmation via the content publishing page.

[0217] In some embodiments, the content editing interface includes options for a publishing format of the second image.

[0218] In some embodiments, the device 1200 also includes: a customization interface presentation module, configured to present an element customization interface in response to an element customization request; a customization information receiving module, configured to receive customization information for the second element via the element customization interface; and a third image presentation module, configured to present a third image of the first virtual image with the second element based on the received customization information.

[0219] In some embodiments, the device 1200 also includes: a customized information determination module, configured to determine whether the customized information meets the preset conditions in response to an image generation request associated with the customized information; and a third image acquisition module, configured to acquire a third image based on the customized information in response to the customized information meeting the preset conditions.

[0220] In some embodiments, the element customization interface includes at least one of the following: a second input control for receiving customization information, or second prompt information for the customization information, the second prompt information indicating a customizable element.

[0221] In some embodiments, the element customization module is configured to receive element customization requests in the following manner: in response to a preset operation, presenting a startup interface for image generation, the startup interface including an image generation entrance and an element customization entrance for each of multiple elements; and receiving element customization requests via the element customization entrance.

[0222] In some embodiments, the device 1200 also includes: an acquisition interface presentation module, configured to present an image acquisition interface in response to an image creation request; a multiple image determination module, configured to determine multiple images of the first object based on at least one of the following operations via the image acquisition interface: a selection operation on a captured image, or an image capturing operation; and a virtual image acquisition module, configured to acquire a first virtual image based on multiple images in response to an image creation confirmation.

[0223] In some embodiments, the device 1200 also includes: a creation progress interface presentation module, configured to present a creation progress interface in response to image creation confirmation and based on the creation progress of the first virtual image; and a content recommendation interface presentation module, configured to present a content recommendation interface in response to a preset operation for the creation progress interface, the content recommendation interface including creation progress information of the first virtual image.

[0224] In some embodiments, the device 1200 also includes: an image information interface presentation module, configured to: present an image information interface of the first virtual image, the image information interface including at least one of the following: a viewing entrance corresponding to at least one element, or a start interface entrance generated for the image.

[0225] In some embodiments, the image information interface presentation module is further configured to present the image information interface of the first virtual image in response to at least one of the following: triggering of a notification message indicating that the creation of the first virtual image is complete, or triggering of a virtual image entry in the user information interface of a user associated with the first virtual image.

[0226] In some embodiments, the first element includes at least one of the following: image style, image background, or image foreground.

[0227] The units and / or modules included in the device 1200 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the units and / or modules in the device 1200 can be implemented at least in part by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0228] It should be understood that one or more steps in the above method may be performed by an appropriate electronic device or combination of electronic devices, such as the terminal device 120 and the server 130 in FIG1 .

[0229] Figure 13 shows a block diagram of an electronic device 1300 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 1300 shown in Figure 13 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 1300 shown in Figure 13 can be used to implement the terminal device 120 of Figure 1 or the apparatus 1200 of Figure 12 .

[0230] As shown in FIG13 , electronic device 1300 is a general-purpose electronic device. Components of electronic device 1300 may include, but are not limited to, one or more processors or processing units 1310, memory 1320, storage device 1330, one or more communication units 1340, one or more input devices 1350, and one or more output devices 1360. Processing unit 1310 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 1320. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 1300.

[0231] The electronic device 1300 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 1300, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1320 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1330 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 1300.

[0232] The electronic device 1300 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 13 , a disk drive for reading from or writing to a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 1320 may include a computer program product 1325 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0233] The communication unit 1340 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 1300 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 1300 can operate in a networked environment using a logical connection to one or more other servers, a network personal computer (PC), or another network node.

[0234] Input device 1350 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 1360 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 1300 may also communicate with one or more external devices (not shown) via communication unit 1340, as needed. External devices such as storage devices, display devices, and the like may also be used to communicate with one or more devices that allow a user to interact with electronic device 1300, or with any device that allows electronic device 1300 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0235] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0236] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0237] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0238] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0239] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0240] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating an image, comprising: In response to an element adjustment request for a first image having a first element of a first virtual image, presenting an element adjustment interface, the first virtual image including media data representing an appearance feature of a first object; Receiving adjustment information for the first element via the element adjustment interface; as well as Based on the received adjustment information, a second image of the first virtual image having the adjusted first element is presented.

2. The method according to claim 1, wherein the element adjustment interface includes at least a portion of the fixed configuration information of the first element, and the method further comprises: Based on the received adjustment information and the fixed configuration information, the second image is acquired.

3. The method according to claim 2, wherein acquiring the second image comprises: In response to an image generation request associated with the adjustment information, determining whether the adjustment information satisfies a preset condition; as well as In response to the adjustment information satisfying the preset condition, the second image is acquired based on the adjustment information and the fixed configuration information.

4. The method according to claim 1, wherein the element adjustment interface comprises at least one of the following: a first input control for receiving the adjustment information, first prompt information for the adjustment information, the first prompt information indicating an adjustable part of the first element, or the first image.

5. The method according to claim 4, further comprising: In response to a preset operation on the element adjustment interface, stop displaying the first image in the element adjustment interface; as well as The presentation area of ​​the first input control is increased.

6. The method of claim 1, wherein the element adjustment request is received by: Presenting a first content preview interface including the first image and an element adjustment portal; and The element adjustment request is received via the element adjustment entry.

7. The method according to claim 6, wherein presenting the first content preview interface comprises: In response to a preset operation, presenting a startup interface for image generation, the startup interface including image generation entrances of respective elements, the plurality of elements including the first element; Based on triggering the image generation entrance of the first element, acquiring the first image; as well as In response to acquiring the first image, presenting the first content preview interface.

8. The method according to claim 7, wherein the preset operation comprises at least one of the following: Triggering the first startup interface entry in the content shooting interface, or The second start interface entry in the image information interface of the first virtual image is triggered.

9. The method according to claim 6, wherein presenting the first content preview interface comprises: presenting an image information interface of the first virtual image, the image information interface including a viewing entry corresponding to at least one element, the at least one element including the first element; and Based on triggering the viewing entry corresponding to the first element, the first content preview interface is presented.

10. The method of claim 2, wherein acquiring the second image comprises: generating a prompt word based on the adjustment information and the fixed configuration information; Providing the prompt word to a target model to obtain an output of the target model; as well as The second image is acquired based on the output.

11. The method according to claim 1, further comprising: Before acquiring the second image, indication information about the generation progress is presented according to the generation progress of the second image.

12. The method according to claim 1, further comprising: In response to the publishing request for the second image, presenting a content editing interface for the second image; In response to receiving an edit confirmation via the content editing interface, presenting a content publishing page for the second image; and In response to receiving a publish confirmation via the content publish page, the second image is published.

13. The method of claim 12, wherein the content editing interface includes an option for a publishing format of the second image.

14. The method according to claim 1, further comprising: In response to the element customization request, presenting an element customization interface; Receiving customization information for a second element via the element customization interface; as well as Based on the received customization information, a third image of the first avatar having the second element is presented.

15. The method according to claim 14, further comprising: In response to an image generation request associated with the customized information, determining whether the customized information satisfies a preset condition; as well as In response to the customization information satisfying the preset condition, the third image is acquired based on the customization information.

16. The method according to claim 14, wherein the element customization interface comprises at least one of the following: a second input control for receiving the custom information, or The second prompt information for the customization information indicates a customizable element.

17. The method according to claim 14, wherein the element customization request is received in the following manner: In response to a preset operation, presenting a startup interface for image generation, the startup interface including an image generation portal and an element customization portal for each of a plurality of elements; and The element customization request is received via the element customization portal.

18. The method of claim 1, further comprising: In response to the image creation request, presenting an image acquisition interface; Determining a plurality of images of the first object based on at least one of the following operations via the image acquisition interface: Select operations on captured images, or image capture operations; and In response to the character creation confirmation, the first virtual character is acquired based on the plurality of images.

19. The method according to claim 18, further comprising: In response to the image creation confirmation, presenting a creation progress interface according to the creation progress of the first virtual image; as well as In response to a preset operation on the creation progress interface, a content recommendation interface is presented, wherein the content recommendation interface includes creation progress information of the first virtual image.

20. The method of claim 1, further comprising: Presenting an image information interface of the first virtual image, wherein the image information interface includes at least one of the following: a view entry corresponding to at least one element, or Startup interface entry for image generation.

21. The method according to claim 20, wherein the avatar information interface of the first virtual avatar is presented in response to at least one of the following: triggering a notification message, the notification message indicating that the first virtual image has been created, or Triggering an avatar entry in a user information interface of a user associated with the first avatar.

22. The method according to claim 1, wherein the first element comprises at least one of the following: image style, image background or image foreground.

23. An apparatus for image generation, comprising: an interface presentation module configured to present an element adjustment interface in response to an element adjustment request for a first image having a first element of a first virtual image, the first virtual image including media data representing an appearance feature of a first object; an information receiving module, configured to receive adjustment information for the first element via the element adjustment interface; as well as The image presentation module is configured to present a second image of the first virtual image with the adjusted first element based on the received adjustment information.

24. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 22 when executed by the at least one processing unit.

25. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 22.

Images