Expression creation method and device, equipment and storage medium

Abstract

According to the embodiment of the invention, the invention provides an expression creation method and device, equipment and a storage medium. The method comprises the steps that in response to expression creation operation, a target image input by a user is acquired, and the target image at least comprises the face of a target object; at least one expression image of a first type is acquired, the at least one expression image is generated at least based on the target image by using an image generation model, the at least one expression image corresponds to at least one expression style, and each expression image comprises a change object corresponding to the target object; and storing the at least one expression image in an expression library associated with the user for use in message interaction. Therefore, by means of the image generation capability of the model, the user can customize the expression image by simply providing the target image and obtain the unique expression image of the user.

Description

Technical Field

[0001] 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 creating expressions. Background Art

[0002] Currently, more and more applications are designed to provide various services to users. Many applications can support message interaction between users. Messages can include various types of messages, such as video, image, audio, text, etc. In the process of message interaction with other users, users can send emoticons to enhance the fun of interaction. Users expect to be able to interact with multiple emoticons in order to further improve the amount of information and interaction efficiency in the message interaction process. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for creating an expression is provided. The method includes: in response to an expression creation operation, obtaining a target image input by a user, the target image at least including a face of a target object; obtaining at least one expression image of a first type, the at least one expression image being generated based on at least the target image using an image generation model, the at least one expression image corresponding to at least one expression style, and each expression image including a change object corresponding to the target object; and storing the at least one expression image in an expression library associated with the user for use in message interaction.

[0004] In a second aspect of the present disclosure, a device for expression creation is provided. The device includes: a target image acquisition module, configured to acquire a target image input by a user in response to detecting an expression creation operation, the target image at least including the face of a target object; an expression image acquisition module, configured to acquire at least one expression image of a first type, the at least one expression image is generated based on at least the target image using an image generation model, the at least one expression image corresponds to at least one expression style, and each expression image includes a change object corresponding to the target object; and an expression image storage module, configured to store at least one expression image in an expression library associated with a user for use in message interaction.

[0005] 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, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.

[0006] 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.

[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they 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

[0008] 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:

[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0010] Figure 2 A schematic diagram showing an example architecture for expression creation according to some embodiments of the present disclosure;

[0011] Figure 3A and Figure 3B A schematic diagram showing an example of an image capture interface according to some embodiments of the present disclosure;

[0012] FIG. 4A to FIG. 4C A schematic diagram showing an example of an image capture interface according to some embodiments of the present disclosure;

[0013] Figure 4D A schematic diagram showing an example of a progress page according to some embodiments of the present disclosure;

[0014] FIG. 5A to FIG. 5E A schematic diagram showing an example of an image selection interface according to some embodiments of the present disclosure;

[0015] Figure 6 A schematic diagram showing an example of a progress page according to some embodiments of the present disclosure;

[0016] Figure 7 A schematic diagram showing an example of other pages presenting a second progress indicator according to some embodiments of the present disclosure;

[0017] Fig. 8A and Figure 8B A schematic diagram showing an example of presenting a push notification according to some embodiments of the present disclosure;

[0018] Fig. 9A schematic diagram showing an example of a message sending and receiving interface presenting at least one emoticon image according to some embodiments of the present disclosure;

[0019] Fig. 10A A schematic diagram showing an example of a message sending and receiving interface presenting an expression guide card according to some embodiments of the present disclosure;

[0020] Fig. 10B A schematic diagram showing an example of a message transceiving interface presenting a first embedded message according to some embodiments of the present disclosure;

[0021] Fig.11A and Fig. 11B A schematic diagram showing an example of a message transceiving interface presenting a second embedded message according to some embodiments of the present disclosure;

[0022] FIG. 12A to FIG. 12D A schematic diagram showing an example of a message sending and receiving interface presenting an emoticon viewing panel according to some embodiments of the present disclosure;

[0023] FIG. 13A to FIG. 13C A schematic diagram showing an example of presenting an expression panel according to some embodiments of the present disclosure;

[0024] Fig.14A and Fig. 14B A schematic diagram showing an example of a message sending and receiving interface presenting an emoticon navigation bar according to some embodiments of the present disclosure;

[0025] Fig.15A and Fig. 15B A schematic diagram showing an example of a comment reply interface presenting an expression navigation bar according to some embodiments of the present disclosure;

[0026] FIG. 16A to FIG. 16C A schematic diagram showing an example of a message page according to some embodiments of the present disclosure;

[0027] Fig.17 A flowchart showing a process for emoticon creation according to some embodiments of the present disclosure is shown;

[0028] Fig.18 A flowchart showing an apparatus for creating expressions according to some embodiments of the present disclosure; and

[0029] Fig.19 A block diagram of an electronic device is shown in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0030] Embodiments of the present disclosure will be described in more detail below 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 being limited to the embodiments set forth herein. On the contrary, 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 only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0031] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "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 also be included below.

[0032] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0033] 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) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0034] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present 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.

[0035] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt 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 software or hardware such as electronic devices, applications, servers or storage media that execute operations of the technical solution of the present disclosure based on the prompt message.

[0036] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information is sent to the user in a manner such as a pop-up window, in which the prompt information can be presented in text form. In addition, the pop-up window can also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0037] 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 meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0038] As briefly mentioned above, users can interact with other users in the application. In the process of interacting with other users, users can send emoticons to enhance the fun of interaction.

[0039] In some schemes that allow users to customize expressions, most practices provide users with predetermined options to generate expression images. In some scenarios, users can also provide images and fill in predetermined templates based on these images to generate corresponding expression images. In other scenarios, users can be allowed to choose the color of facial skin, hair style, facial features style, etc. in the expression image. However, although traditional expression creation schemes support expression images created by users themselves, users need to create images based on limited options or templates, which will result in no significant differences in expression images created by different users, and there is a possibility that different users create the same expression image. That is, traditional expression creation schemes cannot realize the creation of customized expressions for different users. Therefore, it is expected that the customization of expression images for different users can be realized simply and conveniently.

[0040] According to an embodiment of the present disclosure, an improved scheme for expression creation is proposed. According to the scheme of the embodiment of the present disclosure, if an expression creation operation corresponding to the first type is detected in a user interface supporting message interaction, a target image input by the user that includes at least the face of the target object is obtained. An image generation model is used to generate at least one expression image of the first type based on the target image and the prompt word input. At least one expression image of the first type is obtained. The prompt word input indicates at least one expression style to be generated, and each expression image includes a change object corresponding to the target object, and the face of the change object has a corresponding expression style. At least one expression image is stored in an expression library associated with the user for use in message interaction.

[0041] In this way, according to the embodiments of the present disclosure, with the help of the image generation capability of the model, users can customize the expression image by simply providing the target image and obtain their own unique expression image. Such an image creation process is simple, and different expression images can be provided for different users, making the message interaction process richer.

[0042] Example embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0043] Example Environment

[0044] Figure 1A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In the environment 100, a user 110 can publish a video in a target platform through an associated terminal device 120. In some scenarios, the user 110 is also referred to as a publisher of the video.

[0045] One or more users 110-1, 110-2, 110-3, ..., 110-N can send and receive messages through their associated terminal devices 120-1, 120-2, 120-3, ..., 120-N. For ease of discussion, users 110-1, 110-2, 110-3, ..., 110-N can be collectively or individually referred to as users 110, and terminal devices 120-1, 120-2, 120-3, ..., 120-N can be collectively or individually referred to as terminal devices 120.

[0046] The terminal device 120 may be installed with an application 125 that supports message interaction (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 message sending and receiving functions, such as a dedicated chat application, a social application, a content sharing application, an office support application, and the like.

[0047] exist Figure 1 In the environment 100 of FIG. 1 , if the application 125 is in an active state, the terminal device 120 can present the user interface of the application 125. This user interface can include various interfaces that the application 125 can provide, such as a user interface that supports message interaction, a user interface that supports content browsing, a message sending and receiving interface, etc. Through different user interfaces, the application 125 can provide different content to the user 110. Through appropriate means, such as clicking or selecting any appropriate element in the user interface, the application 125 can also provide the user 110 with the selection and switching of the presentation mode of the associated content.

[0048] In some embodiments, different terminal devices 120 may also communicate with the server 130 via the network 132 to provide message interaction services. The server 130 may provide management, configuration, and maintenance functions for the application 125.

[0049] The terminal device 120 can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, television receivers, radio broadcast receivers, e-book devices, gaming devices, or any combination of the foregoing, 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 "wearable" circuits, 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.

[0050] It should be understood that the structure and function of the various elements in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0051] Various example implementations of the present disclosure will be described in detail below.

[0052] Example Framework

[0053] Figure 2 FIG. 2 is a schematic diagram showing an example architecture 200 for creating emoticons according to some embodiments of the present disclosure. Figure 2 As shown, the architecture 200 involves the terminal device 120 and the image generation model 210 .

[0054] The image generation model 210 can be run locally on the terminal device 120 or deployed remotely, for example, on a server (e.g., server 130), in a cloud environment, etc. In the case of local operation, the terminal device 120 can directly provide the model input to the image generation model 210 installed locally, and obtain the model output generated by the image generation model 210. In the case of remote operation, the terminal device 120 provides data to other electronic devices through a communication connection with other electronic devices. Other electronic devices determine the model input based on the acquired data and provide the model input to the image generation model 210. After the other electronic devices obtain the model output of the image generation model 210, they provide the model output to the terminal device 120 through the communication connection with the terminal device 120 so that the terminal device 120 obtains the model output. For the convenience of description, the following is an exemplary description using the image generation model 210 installed locally on the terminal device 120 (that is, the terminal device 120 can directly provide the model input to the image generation model 210 and can directly obtain the model output from the image generation model 210).

[0055] In an embodiment of the present disclosure, the terminal device 120 obtains the target image input by the user in response to the expression creation operation to start the expression creation process. In some embodiments, when the application 125 is in an active state, the terminal device 120 can present the user interface supporting message interaction provided by the application 125. The terminal device 120 can detect the expression creation operation in the user interface supporting message interaction. In some embodiments, the expression creation operation can be a general expression creation operation, or an expression creation operation corresponding to the first type. The first type here can be, for example, a type corresponding to an AI expression. This user interface supporting message interaction can include, for example, a total creation entry for creating an expression, or a first expression creation entry for creating an expression corresponding to the first type. The terminal device 120 can determine that an expression creation operation is detected in response to detecting a trigger operation of the user 110 on the total creation entry or the first expression creation entry. It can be understood that in some embodiments, multiple creation entries corresponding to multiple types of expressions can be provided in the user interface supporting message interaction, and these multiple creation entries include a first expression creation entry and creation entries corresponding to other types of expressions. The present disclosure does not limit the number of creation entries included in the user interface and the types of expressions corresponding to other creation entries.

[0056] In response to detecting the expression creation operation, the terminal device 120 obtains the target image 202 (also referred to as the target image 202) including the face input by the user 110. The target image 202 is an image including at least the face of the target object, where the target object may be an object with various facial expressions, such as a person or an animal. The terminal device 120 may, for example, capture the target image 202 input by the user 110 through an image acquisition device (such as a camera). The terminal device 120 may also, for example, obtain the target image 202 selected by the user 110 and stored locally in the terminal device 120.

[0057] The terminal device 120 can then use the image generation model 210 to generate at least one expression image 212 of the first type based on at least the target image 202 (for example, it can include expression images 212-1, 212-2, 212-3, ..., 212-N, where N is a positive integer, and the expression images 212-1, 212-2, 212-3, ..., 212-N can be collectively or individually referred to as expression images 212). At least one expression image corresponds to at least one expression style. Different expression styles can convey different facial expressions and emotions, such as smiling, laughing, sadness, crying, etc.

[0058] Herein, the image generation model 210 may be any appropriate machine learning model with image generation capability. For example, the image generation model 210 may be based on a diffusion model, such as a three-dimensional animation diffusion model.

[0059] The quality of the image generated by the image generation model 210 will be affected by the model training data and the currently input target image 202. In some embodiments, in order to ensure the quality of the generated expression image 212 as much as possible, the terminal device 120 can also use a series of facial detection models (for example, it can include an eye detection model, an angle detection model, an expression detection model, etc.) to detect the target image 202. For example, the terminal device 120 can only provide the target image 202 to the image generation model 210 after the target image 202 passes the detection of a series of facial detection models. In some embodiments, this series of facial detection models can also be used to guide the user 110 to provide a target image 202 that meets the requirements. For example, if the target image 202 fails to pass the detection, the terminal device 120 can present prompt information to prompt the user 110 how to obtain a target image 202 that meets the requirements based on the detection results output by the series of facial detection models.

[0060] In some embodiments, the expression style used to generate the expression image 212 may include at least one predefined expression style, at least one expression style indicated by the user, and / or at least one expression style determined based on a trend event, and the like. The predefined expression style here may be, for example, a default expression style acquired in advance, that is, an expression style that the model outputs by default during the expression creation process. The expression style indicated by the user may be, for example, an expression style that is optional or customizable by the user. For example, before creating an expression image, a list of optional expression styles may be provided to the user, from which the user may select one or more expression styles to be created. In some implementations, the user may also be allowed to define the expression style to be generated by natural language input or by providing a reference image. The expression style determined based on the trend event here may be at least one expression style that matches the trend event determined by the terminal device 120 analyzing the trend event. For example, if the current time is a festival, the terminal device 120 may determine at least one expression style that matches the festival, and automatically use the determined expression style to generate an expression image when the user needs to create an expression.

[0061] In some embodiments, the image generation model 210 can generate at least one expression image 212 based on the target image 202 and the prompt word input. The prompt word input can indicate the style of at least one change object to be generated and / or at least one expression style. The style of the change object refers to the appearance style and type of the change object presented in the generated expression image 212. The prompt word input is used to at least guide the image generation model 210 to generate the corresponding style and / or expression style. In some embodiments, the prompt word input and the object style / expression style can be a one-to-one, one-to-many or many-to-one relationship. That is, one expression style can correspond to one prompt word input, one prompt word input can correspond to multiple expression styles, or one expression style can correspond to multiple prompt word inputs. Exemplarily, Table 1 shows an example of the corresponding relationship between expression styles and prompt word inputs.

[0062] Table 1

[0063]

[0064] As shown in Table 1, the terminal device 120 can determine the corresponding prompt word input based on the expression style, or determine the corresponding expression style based on the prompt word input. For example, the terminal device 120 can obtain at least one expression style corresponding to at least one expression image 212 to be generated, and determine at least one prompt word input corresponding to the at least one expression style based on Table 1.

[0065] In some embodiments, alternatively or additionally, the image generation model 210 can also generate at least one expression image 212 based on the user selection (plus the target image 202, and / or the prompt word input). The user selection indicates the style and / or expression style of at least one change object to be generated. In other words, the user can be allowed to select the style or expression style of the change object as needed.

[0066] The terminal device 120 can provide the target image 202 input by the user and the constructed prompt word input to the image generation model 210, so that the image generation model 210 generates at least one expression image 212 based on the prompt word input and the target image 202. In this article, the expression image may also be referred to as an expression, an emoticon, an expression sticker, etc. In this article, the expression image 212 generated by the model is also called an AI expression image or simply an AI expression to distinguish it from an expression that is not generated by the model. The number of expression images 212 generated can be, for example, the number indicated by the prompt word input. In some embodiments, the expression image 212 can be a static expression image or a dynamic expression image (i.e., a gif).

[0067] It should be noted that, in the case where a certain expression style corresponds to multiple prompt word inputs, the terminal device 120 can, for example, provide all of the multiple prompt word inputs as prompt word inputs corresponding to the expression style to the image generation model 210 to obtain multiple expression images 212 corresponding to the multiple prompt word inputs generated by the image generation model 210. Although the multiple expression images 212 correspond to the same expression style, they are different images. That is, the image generation model 210 can generate multiple different expression images 212 corresponding to one expression style based on multiple prompt word inputs.

[0068] Each expression image 212 includes a change object corresponding to the target object. The change object refers to converting the target image into a specific image or appearance style. For example, the change object included in the expression image 212 can be designed according to a specific painting style such as a cartoon character, a sketch, or an oil painting. In some embodiments, the face of the change object in each expression image 212 has a corresponding expression style.

[0069] The terminal device 120 may store the at least one acquired expression image 212 in an expression library associated with the user 110 for use in message interaction. The expression library may be, for example, an expression library of the account corresponding to the user 110 in the application 125. After the user 110 logs in to the corresponding account, the expression image desired by the user 110 may be selected from the expression library to interact with the message during the message interaction. In some embodiments, the terminal device 120 may also review the at least one acquired expression image 212 to determine whether the at least one expression image 212 includes an inappropriate expression image (for example, whether it includes an expression image with an expression that is too strange or distorted). The terminal device 120 may then store the expression images that have passed the review. Alternatively or additionally, in some embodiments, the image generation model 210 may also review the generated at least one expression image 212 by itself, and only provide the expression image 212 that has passed the review to the terminal device 120.

[0070] In some embodiments, if the image generation model 210 is installed on other electronic devices, after the image generation model 210 generates at least one expression image 212 , the other electronic devices (or the image generation model 210 ) can immediately delete the acquired target image 202 to ensure the information security of the user 110 .

[0071] In this way, the model's image generation capability can be used to enable users to customize emoticon images by simply providing target images and obtain their own unique emoticon images. This image creation process is simple and can provide different emoticon images for different users, making the message interaction process richer.

[0072] Continue to refer to FIG. 3A to FIG. 16CThe example interface / example page shown is used to describe an example embodiment of emoticon creation.

[0073] Example interface for creating emoticons

[0074] FIG. 3A to FIG. 16C Schematic diagrams of example interfaces / example pages according to some embodiments of the present disclosure are shown. It should be understood that the interfaces / pages shown in the drawings are merely examples, and various page designs may actually exist. The various graphical elements in the interface / page may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also exist. The embodiments of the present disclosure are not limited in this respect. FIG. 3A to FIG. 16C The example interface / example page shown may be presented at the terminal device 120. For ease of discussion, reference will be made to Figure 1 The environment 100 is described FIG. 3A to FIG. 16C Example interface / example page shown.

[0075] In some embodiments, the terminal device 120 may provide an image capture interface or an image selection interface when an expression creation operation corresponding to the first type is detected. The terminal device 120 may capture an image using a camera in the image capture interface. The terminal device 120 may select a captured image in the image selection interface. In some embodiments, if an expression creation operation is detected, the terminal device 120 may provide a tab sheet including at least a first option corresponding to the image capture interface and a second option corresponding to the image selection interface. The terminal device 120 may present an image capture interface in response to detecting a selection operation for the first option, and present an image selection interface in response to detecting a selection operation for the second option.

[0076] In some embodiments, the terminal device 120 may also predetermine a default interface. In response to detecting an expression creation operation, 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 other interfaces. Exemplarily, the default interface may be an image capture interface, and the terminal device 120 may switch to presenting an image selection interface in response to detecting a trigger operation on any appropriate interface element (e.g., an interface switching control) in the image capture interface.

[0077] In some embodiments, the terminal device 120 may also present a prompt panel for providing prompt information on the image capture interface. Figure 3AAs shown, the terminal device 120 may, for example, present an example 300A including a prompt panel 310 in response to detecting an expression creation operation. Example 300A may, for example, be an image capture interface including a prompt panel presented by default. The prompt panel 310 may present prompt information (e.g., text "Create your own AI expression selfie, upload a picture, or simply use your avatar, and then let AI do the work.") that prompts how to create an expression image (i.e., an AI expression). The prompt panel 310 may also present, for example, an example effect of an expression image (e.g., an exemplary expression image may be presented). The prompt panel 310 also includes an operation control 311 and an operation control 312. The terminal device 120 may cancel the presentation of the prompt panel 310 in response to detecting a trigger operation on the operation control 311, the operation control 312, or any area outside the prompt panel 310 in example 300A.

[0078] It should be noted that, regarding the prompt logic of the prompt panel, in some embodiments, the terminal device 120 will present an image capture interface including the prompt panel by default each time it detects an expression creation operation. In some embodiments, the terminal device 120 may also present an image capture interface including the prompt panel only when an expression creation operation is detected for the first time (or the first few (predetermined) times that an expression creation operation is detected), and present an image capture interface without the prompt panel when an expression creation operation is detected again.

[0079] After canceling the presentation of the prompt panel 310, the terminal device 120 may present, for example, Figure 3B Example 300B shown. Example 300B may be, for example, an image capture interface that does not include a prompt panel. Example 300B may include a predetermined border 302 for defining a facial contour. In some embodiments, Example 300B may include an area 301 for presenting a captured image. That is, the terminal device 120 may present an image captured by a camera in area 301. The predetermined border 301 may be, for example, superimposed on area 301, or presented in area 301.

[0080] In some embodiments, before presenting the image capture interface (for example, before presenting the image capture interface for the first time), the terminal device 120 also needs to obtain permission to access the camera. The terminal device 120 may present, for example, Figure 4A Example 400A shown in FIG. Example 400A may present a prompt text “Allow “XX application” to access your camera” for prompting the user 110. Example 400A may also present an operation control 401. In response to detecting a trigger operation on the operation control 401, the terminal device 120 may determine that the permission to access the camera is obtained, and then present the following prompt text: Figure 3BThe image capture interface shown (ie, example 300B).

[0081] In some embodiments, after the terminal device 120 captures an image using a camera in Example 300B, while presenting the image in area 301, it can also determine whether the captured image satisfies the conditions related to the facial region. The conditions related to the facial region may include, for example, at least one of the following conditions: the facial region of the target object in the captured image is located within a predetermined border 302, the face of the target object in the captured image is at an eye level angle, and the face of the target object in the captured image shows a neutral expression. As mentioned above, the terminal device 120 may, for example, use a series of face detection models to determine whether the captured image satisfies the conditions related to the facial region.

[0082] In some embodiments, if it is determined that the image captured in Example 300B does not meet the conditions related to the facial area, the terminal device 120 may also provide prompt information for prompting the recapture of the image. In some embodiments, the prompt information may be a fixed prompt information that is set in advance. For example, it may be a prompt information such as "Please adjust the facial position". In some embodiments, the prompt information may also be determined based on one or more conditions that are not met in at least one condition. Exemplarily, if it is determined that the captured image does not meet the condition that the facial area of ​​the target object in the captured image is within the predetermined border 302, the terminal device 120 may present a prompt information such as "Put your face in the predetermined area". If it is determined that the captured image does not meet the condition that the face of the target object in the captured image is at the eye level angle, the terminal device 120 may present a prompt information such as "Please use the eye level angle". If it is determined that the captured image does not meet the condition that the face of the target object in the captured image shows a neutral expression, the terminal device 120 may present a prompt information such as "Please use a neutral expression". Figure 4B As shown, in response to the facial region being located in the predetermined border 402 (the predetermined border 402 corresponds to Figure 3B The terminal device 120 may present a prompt message 403 if the area outside the predetermined frame 302 in the terminal device 120 is completely outside the predetermined frame 402 or partially outside the predetermined frame 402. The prompt message 403 may be located in the area 401 (the area 401 corresponds to Figure 3B The prompt information 403 may be located at any appropriate position of the area 301 in the example, for example, above or below the area 401. The prompt information 403 may also be located at other positions of the example 400B, which is not limited in the present disclosure.

[0083] In some embodiments, if it is determined that the captured image meets the condition related to the facial region, the terminal device 120 may acquire the captured image as the target image. Specifically, in some embodiments, if it is determined that the captured image meets the condition related to the facial region, the terminal device 120 may present prompt information for prompting the user 110 to capture an image. Figure 4C As shown, if it is determined that the captured image meets the condition related to the facial area, the terminal device 120 can present prompt information 404 in example 400C to prompt the user to capture the image. The terminal device 120 can capture the image currently presented in the area 401 in response to detecting the selection operation of the shooting control 410.

[0084] The terminal device 120 may determine the captured image as the target image. After the terminal device 120 obtains the captured image, it may present the image as follows: Figure 4D Example 400D shown. Example 400D can be, for example, a progress page that presents the captured target image and presents the first progress indicator 435. The first progress indicator 435 here can be used to indicate the creation progress of creating at least one emoticon image based on the captured target image. In some embodiments, the terminal device 120 can present an area 430 for presenting the first progress indicator 435, and the area 430 can be displayed superimposed on the area 401, for example. Area 430 can also present a description text for describing the real-time creation progress. It can be understood that area 430 can be located at any position in Example 400D, and the present disclosure is not limited to this.

[0085] The above describes multiple examples of using a camera to capture images in an image shooting interface and determining the captured images as target images. The following will continue to describe multiple examples of selecting captured images in an image selection interface and determining the selected images as target images.

[0086] Return to reference Figure 3B , Example 300B also includes a switch control 320. The terminal device 120 can switch to presenting an image selection interface in response to detecting a selection operation on the switch control 320. It can be understood that in some embodiments, the terminal device 120 can also present an image selection interface in response to detecting an expression creation operation. Similar to the image capture interface, in some embodiments, before presenting the image selection interface (for example, before presenting the image selection interface for the first time), the terminal device 120 also needs to obtain permission to access the captured image. The terminal device 120 can, for example, present the following Figure 5A Example 500A shown.

[0087] In example 500A, a prompt card 510 may be presented. The prompt card 510 presents a prompt text for prompting the user 110, "XX application wants to access your photos. You will be able to apply effects and functions to all photos." The prompt card 510 may also include, for example, an operation control 512 indicating that an image is selected and only the selected image is allowed to be obtained, an operation control 514 indicating that access to all images stored in the terminal device 120 is allowed, and an operation control 516 that does not allow access to images. In response to detecting a selection operation on the operation control 512 or the operation control 514, the terminal device 120 may obtain access rights to the image selected by the user 110 or obtain access rights to all images, and then present an image selection interface that only includes the selected image or presents an image selection interface that includes all images. It can be understood that at least a portion of the selected image or all images may be presented in the image selection interface, and the user 110 may, for example, view more images by sliding operations. For the convenience of description, the following is an exemplary description using the image selection interface that includes all images presented by the terminal device 120 as an example.

[0088] In some embodiments, the terminal device 120 may also present a prompt panel for providing prompt information on the image selection interface. Figure 5B As shown, the terminal device 120 may, for example, present example 500B including a prompt panel 520 in response to detecting an expression creation operation or in response to detecting a selection operation on the switch control 320 in example 300B. Example 500B may, for example, be an image selection interface including a prompt panel. The prompt panel 520 may, for example, also present examples of appropriate target images (e.g., images that satisfy conditions related to facial regions) and examples of inappropriate target images (e.g., images that do not satisfy conditions related to facial regions). The prompt panel 520 also includes an operation control 525. The terminal device 120 may cancel the presentation of the prompt panel 520 in response to detecting a trigger operation on the operation control 525 or any area outside the prompt panel 520 in example 500B. After canceling the presentation of the prompt panel 520, the terminal device 120 may, for example, present an example as shown in FIG. Figure 5C Example 500C is shown. Example 500C may be, for example, an image selection interface that does not include a prompt panel. In example 500C, multiple images with access rights may be presented.

[0089] Similarly, regarding the prompt logic of the prompt panel, in some embodiments, each time the terminal device 120 presents the image selection interface, the image selection interface including the prompt panel will be presented by default. In some embodiments, the terminal device 120 may also present the image selection interface including the prompt panel only when the image selection interface is presented for the first time (or the first few times (which may be a predetermined number of times) the image selection interface is presented), and then present the image selection interface without the prompt panel when the image selection interface is presented again.

[0090] The terminal device 120 may determine to acquire the selected image in response to receiving a trigger operation on any image presented in the image selection interface. The terminal device 120 may also determine whether the selected image satisfies the condition related to the facial region. The terminal device 120 may, for example, determine whether the selected image satisfies the condition related to the facial region through a series of face detection models. The terminal device 120 may, for example, present the following information during the process of determining whether the selected image satisfies the condition related to the facial region: Figure 5D Example 500D is shown. Element 530 is presented in example 500D. Element 530 indicates that terminal device 120 is currently detecting the selected image to determine whether the selected image satisfies the condition related to the facial region.

[0091] Similarly, if it is determined that the image selected in the image selection interface does not satisfy the conditions related to the facial area, the terminal device 120 may provide prompt information for prompting the reselection of the image. This prompt information may be pre-set and fixed, or it may be determined based on one or more conditions that are not satisfied in at least one condition. Exemplarily, if it is determined that the selected image does not satisfy the condition that the facial area of ​​the target object is within a predetermined border, the terminal device 120 may present a prompt information such as "No face is detected. Select another photo or use the camera." If it is determined that the selected image does not satisfy the condition that the face of the target object is at an eye level angle, the terminal device 120 may present a prompt information such as "The photo must be taken from eye level. Select another photo or use the camera." If it is determined that the selected image does not satisfy the condition that the face of the target object in the image shows a neutral expression, the terminal device 120 may present a prompt information such as "The expression is not neutral. Select another photo or use the camera." Figure 5E As shown, if it is determined that the image selected in the image selection interface does not meet the condition related to the facial region, the terminal device 120 can present prompt information 540. The prompt information 540 can be located at any appropriate position of the example 500E.

[0092] If it is determined that the selected image satisfies the condition related to the facial region, the terminal device 120 may acquire the selected image as the target image. That is, the terminal device 120 may determine the image selected by the user 110 as the target image.

[0093] In some embodiments, in addition to selecting a captured image in the image selection interface, the terminal device 120 can also obtain the avatar image of the user 110, and detect the avatar image to determine whether the avatar image satisfies the conditions related to the facial area. In some embodiments, if it is determined that the user's avatar image satisfies the conditions related to the facial area, the terminal device 120 can present a second expression creation portal for the user's avatar image in the image capture interface. The terminal device 120 can then obtain the user's avatar image as the target image based on the triggering of the second expression creation portal. For example, the terminal device 120 can determine that a selection of the user's avatar image is received in response to the triggering of the second expression creation portal, and then determine the selected user's avatar image as the target image.

[0094] Return to reference Figure 3B If it is determined that the user's avatar image meets the conditions related to the facial area, the terminal device 120 can present the creation entry 330 (i.e., the second expression creation entry) in example 300B. It can be understood that if it is determined that the user's avatar image does not meet the conditions related to the facial area, the terminal device 120 may not present the creation entry 330 in example 300B. In response to detecting the selection operation on the creation entry 330, the terminal device 120 can determine the user's avatar image as the target image.

[0095] After the terminal device 120 obtains the selected target image (the image selected by the user 110 in the image selection interface or the user's avatar image), it can present the following Figure 6 Example 600 shown. Example 600 can be, for example, a progress page that presents a selected target image and a first progress indicator 615. The first progress indicator 615 here can be used to indicate the creation progress of creating at least one emoticon image based on the selected target image. In some embodiments, the terminal device 120 can present an area 610 for presenting the first progress indicator 615, and the area 610 can be superimposed and displayed on the area 601, for example. The area 601 can be used to present the selected target image, for example. The area 610 can also present a description text for describing the real-time creation progress. It can be understood that the area 610 can be located at any position in the example 600, and the present disclosure is not limited to this.

[0096] In the process of creating at least one emoticon image, the terminal device 120 may also provide other pages besides the progress page, and present a second progress indicator for indicating the creation progress of at least one emoticon image in the other pages. For example, the terminal device 120 may jump to the progress page in response to detecting a triggering operation on the second progress indicator. Figure 4D , Figure 6 as well as Figure 7 As shown, example 400 also includes an operation control 440, and example 600 also includes an operation control 620. In response to detecting a trigger operation on the operation control 440 or the operation control 620, the terminal device 120 may present a Figure 7 Example 700 is shown. Example 700 may be, for example, another page other than the progress page, on which the second progress indicator 710 is presented. Example 700 may be, for example, a message sending and receiving interface between user 110 and other users. The second progress indicator 710 may be presented, for example, in the form of a dynamic island. The terminal device 120 may switch back to display example 400D or example 600 based on triggering the second progress indicator 710.

[0097] After the creation of at least one emoticon image is completed, the terminal device 120 may also provide a push notification to indicate that the emoticon creation is complete. The push notification includes a first emoticon viewing entrance to view at least one emoticon that has been created. In some embodiments, the terminal device 120 may also provide first emoticon viewing entrances of different styles. Exemplarily, 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 emoticon viewing entrance of a first style, and 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 emoticon viewing entrance of a second style.

[0098] like Fig. 8A , Figure 8B as well as Fig. 9 As shown, example 800A may be, for example, a user interface provided by application 120, and example 800B may be, for example, a user interface that application 120 cannot provide (i.e., outside the user interface that application 120 can provide). For example, terminal device 120 may provide a first expression viewing entrance 810 in example 800A, and provide a first expression viewing entrance 820 in example 800B. In response to detecting a trigger operation on the first expression viewing entrance 810 or the first expression viewing entrance 820, terminal device 120 may switch back to example 900 provided by presentation application 120 to view at least one created expression. Example 900 may be, for example, a message sending and receiving interface.

[0099] The above describes a plurality of exemplary embodiments of creating at least one expression image after detecting an expression creation operation. The specific process of detecting an expression creation operation will be described below in conjunction with the accompanying drawings.

[0100] As mentioned above, the terminal device 120 detects an expression creation operation corresponding to the first type in a user interface that supports message interaction. The terminal device 120 can present a first expression creation portal for the first type in the user interface. The terminal device 120 can detect an expression creation operation based on triggering the first expression creation portal. The user interface here may, for example, include a message sending and receiving interface between the user 110 and another user or multiple users (that is, a private chat interface between the user 110 and another user or a group chat interface between the user and multiple other users. For the sake of convenience, the message sending and receiving interface is referred to as a private chat interface between the user 110 and another user in this article), a comment reply interface for a work, or a message page including a list of message sending and receiving interfaces, etc.

[0101] For the message sending and receiving interface, the terminal device 120 can present an expression guide card that at least includes an entry for creating a first expression of the first type in the message sending and receiving interface. The expression guide card is maintained and presented after the last message in the message sending and receiving interface. That is, if the message sending and receiving page includes 3 messages, the expression guide card is presented after the 3rd message. If a new message appears in the message sending and receiving page (that is, if the message sending and receiving page includes 4 messages, the new message can be a message received by the user 110 or a message sent by the user 110), the expression guide card is presented after the 4th message (that is, the newly appeared message).

[0102] Regarding when to present the expression guide card in the message sending and receiving interface, the terminal device 120 can pre-acquire at least one condition for presenting the expression guide card. This at least one condition may include, for example, that the user has not created an expression image of the first type, the message sending and receiving interface includes at least one historical message, and the message sending and receiving interface does not include at least one of the unread messages. The terminal device 120 presents the expression guide card in the message sending and receiving interface only when at least one condition for presenting the expression guide card is met. That is, the terminal device 120 presents the expression guide card in the message sending and receiving interface only when the user has not created an expression image of the first type, the message sending and receiving interface includes at least one historical message, and the message sending and receiving interface does not include at least one of the unread messages. In some embodiments, since there is a situation where the terminal device 120 needs to present a pop-up window / banner / window, etc. when presenting the message sending and receiving interface, in this case, in order to avoid affecting the user 110 browsing information, even if at least one condition for presenting the expression guide card is met, the terminal device 120 will not present the expression guide card.

[0103] In some embodiments, when the terminal device 120 presents an expression guide card in the message sending and receiving interface, if a cancellation presentation operation of the expression guide card is detected, the terminal device 120 can cancel the presentation of the expression guide card and present a first embedded message including at least the first expression creation entrance in the message sending and receiving interface. Exemplarily, the expression guide card may include a cancel control, for example. For example, the terminal device 120 may, in response to detecting a triggering operation of the cancel control in the expression guide card, determine that a cancellation presentation operation of the expression guide card is detected and cancel the presentation of the expression guide card. Further, if it is detected that a new message is received or sent in the message sending and receiving interface, or in response to detecting that the message sending and receiving interface is canceled, the terminal device 120 may cancel the presentation of the first embedded message. It should be noted that the cancellation logic of the first embedded message is different from the cancellation logic of the expression guide card. In some embodiments, if it is detected that a new message is received or sent in the message sending and receiving interface, the terminal device 120 may still present the expression guide card, and the expression guide card is presented after the new message.

[0104] like Fig. 10A and Fig. 10BAs shown, example 1000A and example 1000B can be, for example, a message sending and receiving interface between user 110 and another user (for example, user 123). If the user has not created an expression image of the first type, example 1000A includes at least one historical message, and example 1000A does not include at least one item of unread messages, the terminal device 120 can present an expression guide card 1010 in example 1000A. Guidance information in text form and image form can be presented in the expression guide card 1010. The expression guide card 1010 includes a first expression creation entry 1014 for the first type. For example, the terminal device 120 can determine that an expression creation operation corresponding to the first type is detected in response to detecting a trigger operation on the first expression creation entry 1014. The expression guide card 1010 may also include a cancel control 1012. The terminal device 120 may, for example, cancel the presentation of the expression guide card 1010 in response to detecting a touch operation on the cancel control 1012, or detecting a touch operation on an area outside the first expression creation entry 1014 in the expression guide card 1010. The terminal device 120 may then present the example 1000B. In the example 1000B, the terminal device 120 presents the first embedded message 1020. The first embedded message 1020 also includes a first expression creation entry. The first expression creation entry in the first embedded message 1020 may, for example, be the text "Create your own AI expression". The terminal device 120 may cancel the presentation of the first embedded message 1020 in response to receiving or sending a new message in the example 1000B, or in response to detecting that the example 1000B is canceled (for example, the user 110 exits the private chat with the user 123).

[0105] In some embodiments, in order to avoid frequent presentation of the expression guide card or the first embedded message to affect the user experience of the user, the terminal device 120 may present the expression guide card or the first embedded message again only when the duration from the moment when the expression guide card or the first embedded message is canceled to the current moment satisfies the predetermined duration. The expression guide card and the first embedded message may correspond to different predetermined durations, for example, the first predetermined duration corresponding to the expression guide card may be 7 days, and the second predetermined duration corresponding to the first embedded message may be 30 days. That is, there is a situation where the duration from the moment when the expression guide card was last canceled to the current moment satisfies the first predetermined duration, and the duration from the moment when the first embedded message was last canceled to the current moment does not satisfy the second predetermined duration. In this case, the terminal device 120 may present the expression guide card in the message sending and receiving interface. In response to detecting the cancel presentation operation of the expression guide card, the terminal device 120 cancels the presentation of the expression guide card and does not present the first embedded message. It is understandable that if the time between the last time the expression guide card was canceled and the current time does not meet the first predetermined time, the terminal device 120 will not present the expression guide card in the message sending and receiving interface, nor will it present the first embedded message.

[0106] Also for the messaging interface, in some embodiments, the terminal device 120 may also present in the messaging interface a second embedded message including at least a first emoticon creation entry based on receiving a message from another user in the messaging interface and the message including a first emoticon image of a first type.

[0107] Regarding the presentation logic of the second embedded message, in some embodiments, the terminal device 120 may pre-acquire at least one condition for presenting the second embedded message. This at least one condition may, for example, include at least one condition that the user has not created an expression image of the first type, and the expression guide card has not been presented in the message sending and receiving interface. The terminal device 120 presents the second embedded message in the message sending and receiving interface only when at least one condition for presenting the second embedded message is met. That is, the terminal device 120 presents the second embedded message in the message sending and receiving interface only when at least one of the conditions for presenting the second embedded message is met: the user has not created an expression image of the first type, and the expression guide card has not been presented in the message sending and receiving interface.

[0108] like Fig.11AAs shown, example 1100A can be, for example, a message sending and receiving interface between user 110 and another user (for example, user 123). If at least one of the following conditions is satisfied: the user has not created an expression image of the first type, and the expression guide card is not presented in the message sending and receiving interface, the terminal device 120 can present a second embedded message 1110 in example 1100A. The second embedded message 1110 includes a first expression creation entry, and the first expression creation entry in the second embedded message 1110 can be, for example, the text "Create your AI expression".

[0109] In some embodiments, the terminal device 120 may present the second embedded message after the message from another user. If a new message (i.e., a new message from another user) is received in the message sending and receiving interface, the terminal device 120 may present the received new message after the second embedded message. Fig.11A and Fig. 11B As shown, if a new message (ie, a new message from user 123) is received in example 1100A, terminal device 120 may present example 1100B. In example 1100B, terminal device 120 presents the received new message after second embedded message 1110.

[0110] In some embodiments, if there is a second emoticon image of the first type sent or received in the message sending and receiving interface, the terminal device 120 can present an emoticon viewing panel for the second emoticon image in the message sending and receiving interface in response to detecting a trigger operation on the second emoticon image. The emoticon viewing panel can include a first emoticon creation portal.

[0111] It should be noted that the expression viewing panel may not include the first expression creation entry. The terminal device 120 determines that the first expression creation entry is provided in the expression viewing panel only when it is determined that the user 110 has not created at least one of the first type of expression images and the second expression image is not created by the user, and then presents the expression viewing panel including the first expression creation entry. For example, Fig. 12A As shown, the terminal device 120 can present an example 1200A including an expression viewing panel 1210 in response to detecting a trigger operation on the second expression image. The expression viewing panel 1210 presents the expression viewing panel 1210 only when the user 110 has not created an expression image of the first type and the second expression image is not created by the user 110. Fig. 12A The second expression image and the first expression creation entry 1211 are shown.

[0112] In some embodiments, if the user 110 (ie, the user 456 shown in the figure) has created the first type of emoticon image or the second emoticon image is created by the user 110, the emoticon viewing panel includes at least one of a send control and a favorite control for the second emoticon image. FIG. 12B to FIG. 12D As shown, the expression viewing panel 1210 presented in Examples 1200B to 1200D includes a send control 1212 and a favorite control 1213. If the second expression image is not created by the user 110, but the user 110 has created an expression image of the first type, the terminal device 120 can present Example 1200B. If the user 110 has created an expression image of the first type, the terminal device 120 can present Example 1200C. If a triggering operation on the favorite control 1213 is detected in Example 1200C, the terminal device 120 can present Example 1200D. In response to the favorite control 1213 being triggered, the terminal device 120 can adjust the presentation style of the favorite control 1213 in the expression viewing panel 1210 in Example 1200D, and present prompt information 1205 for prompting that the expression image has been collected in Example 1200D.

[0113] In some embodiments, the terminal device 120 may also present an expression panel that at least provides a first expression creation entry for the first type in the message sending and receiving interface in response to detecting a trigger operation on the expression panel in the message sending and receiving interface. The terminal device 120 may, for example, determine that a trigger operation on the expression panel is detected in response to detecting a trigger operation on an input box, or a trigger operation on any appropriate control. In some embodiments, the expression panel may include at least one of a first expression creation entry specific to the first type and a total first expression creation entry. For example, the terminal device 120 may present at least a first expression creation entry specific to the first type based on triggering the total first expression creation entry.

[0114] like FIG. 13A to FIG. 13CAs shown, example 1300A and example 1300B can be, for example, a message sending and receiving interface with an expression panel. For example, the terminal device 120 can present example 1300A or example 1300B in response to detecting a trigger operation on the expression panel in the message sending and receiving interface. The expression panel in example 1300A includes a first expression creation entrance 1310 specific to the first type and a total first expression creation entrance 1320. The first expression creation entrance 1310 can be presented in the expression panel in the form of a banner, for example. The expression panel in example 1300B only includes the total first expression creation entrance 1320. In some embodiments, the terminal device 120 can, for example, give priority to presenting example 1300A, and in response to the presentation number of the first expression creation entrance 1310 reaching a predetermined number of times (for example, 3 times), directly present example 1300B. For example, the terminal device 120 can present example 1300C in response to detecting a trigger operation on the total first expression creation entrance 1320. In example 1300C, for example, a card 1330 can be presented. The card 1330 presents a first expression creation entry 1331 and a cancel control 1332. In response to detecting a trigger operation on the cancel control 1332, the terminal device 120 may return to the presentation example 1300B.

[0115] For a message sending and receiving interface or a comment reply interface for a work, in some embodiments, the terminal device 120 may present an expression navigation bar in the message sending and receiving interface or the comment reply interface for the work. The expression navigation bar includes a first label corresponding to the first type and a second label corresponding to at least one other expression type. For example, the terminal device 120 may present a first expression creation entry for the first type in response to detecting that the first label is triggered.

[0116] like Fig.14A and Fig. 14B As shown, example 1400A and example 1400B may be, for example, a message sending and receiving interface with an expression navigation bar 1420. The expression navigation bar 1420 may be presented in area 1410. The expression navigation bar 1420 includes a first label 1422 and a second label 1421. In response to detecting a trigger operation on the first label 1422, the terminal device 120 presents the following Fig.14A Example 1400B is shown. In example 1400B, a first expression creation entry 1415 for the first type may be presented.

[0117] like Fig.15A and Fig. 15B As shown, example 1500A and example 1500B may be, for example, a comment reply interface presenting an expression navigation bar 1510. The expression navigation bar 1510 may include a first label 1514 and a second label 1512. In response to detecting a trigger operation on the first label 1514, the terminal device 120 presents the following Fig. 15B Example 1500B is shown. In example 1500B, a first expression creation entry 1520 for a first type may be presented.

[0118] In some embodiments, the expression creation operation may also include an expression creation operation for the avatar image of the user 110. For example, the terminal device 120 may present a second expression creation entry for the avatar image of the user 110 in the message page. In some embodiments, in response to the user 110 uploading the avatar image, the terminal device 120 may directly detect the avatar image to determine whether the avatar image satisfies the conditions related to the facial region described above. The terminal device 120 then presents a second expression creation entry for the avatar image of the user 110 in the message page only when it is determined that the avatar image of the user 110 satisfies the conditions related to the facial region.

[0119] The terminal device 120 can then detect an expression creation operation for the avatar image of the user 110 based on the triggering of the second expression creation entrance. In response to detecting the expression creation operation for the avatar image of the user 110, the terminal device 120 obtains the avatar image of the user 110 and directly creates at least one expression image based on the avatar image. In some embodiments, the terminal device 120 can also directly create at least one expression image based on the avatar image in response to the avatar image of the user 110 satisfying the conditions related to the facial area, and save the acquired at least one expression image only when the triggering operation for the second expression creation entrance is detected. That is, in this case, if the triggering operation for the second expression creation entrance is not detected, the terminal device 120 can delete the generated at least one expression image. In some embodiments, the terminal device 120 can also provide a second expression viewing entrance for at least one expression image in the user interface after the creation of at least one expression image is completed to view at least one expression that has been created.

[0120] like FIG. 16A to FIG. 16CAs shown, examples 1600A to 1600C can be, for example, message pages. For example, the terminal device 120 can present the interface 1610 in example 1600A in response to the avatar image of the user 110 satisfying the condition related to the facial area. A second expression viewing entrance 1611 is presented in the interface 1610. A cancel control 1613 and an operation control 1612 can also be presented in the interface 1610. In response to detecting a trigger operation on the cancel control 1613 or the operation control 1612, the terminal device 120 can determine not to use the avatar image to generate at least one expression image and cancel the presentation of the interface 1610. In response to detecting a trigger operation on the second expression viewing entrance 1611, the terminal device 120 can use the avatar image of the user 110 to create at least one expression image. In the process of creating at least one expression image, the terminal device 120 can present example 1600B. In example 1600B, the interface 1610 presents an element 1614, which is used to prompt the user 110 that at least one expression image is currently being created based on the avatar image. In response to the completion of the creation of at least one expression image, the terminal device 120 may present example 1600C. In example 1600C, the interface 1610 presents a second expression viewing entry 1615 for at least one expression image. For example, in response to detecting a trigger operation on the second expression viewing entry 1615, the terminal device 120 may switch to presenting the example 1600C. Fig. 9 Example 900 is shown to view at least one emoticon that has been created.

[0121] In summary, according to the embodiments of the present disclosure, with the help of the image generation capability of the model, users can customize the expression image by simply providing the target image and obtain their own unique expression image. Such an image creation process is simple and can provide different expression images for different users, making the message interaction process richer.

[0122] Example Process

[0123] Fig.17 FIG. 1 is a flowchart of a process 1700 for creating an expression according to some embodiments of the present disclosure. The process 1700 may be implemented at the terminal device 120. Figure 1 Describe process 1700.

[0124] In box 1710, the terminal device 120 obtains a target image input by the user in response to the expression creation operation, and the target image at least includes the face of the target object.

[0125] In box 1720, the terminal device 120 obtains at least one expression image of the first type, at least one expression image is generated using an image generation model based at least on a target image, at least one expression image corresponds to at least one expression style, and each expression image includes a change object corresponding to a target object.

[0126] In box 1730, the terminal device 120 stores at least one emoticon image in an emoticon library associated with the user for use in message interaction.

[0127] In some embodiments, process 1700 further includes: in a user interface supporting message interaction, detecting an expression creation operation corresponding to the first type, and acquiring the target image is based on the expression creation operation corresponding to the first type.

[0128] In some embodiments, at least one expression image is generated using an image generation model based on a target image and also based on a prompt word input indicating a style and / or expression pattern of at least one variation object to be generated.

[0129] In some embodiments, at least one expression image is generated using an image generation model based on the target image and also based on a user selection indicating a style and / or expression pattern of at least one variation object to be generated.

[0130] In some embodiments, the face of the changed object has a corresponding expression pattern.

[0131] In some embodiments, acquiring a target image includes: providing an image capture interface or an image selection interface based on detecting an expression creation operation, capturing an image using a camera in the image capture interface, and selecting a captured image in the image selection interface; if it is determined that the image captured in the image capture interface or the image selected in the image selection interface does not satisfy conditions related to the facial area, providing prompt information to prompt recapture or reselection of the image; and if it is determined that the captured image or the selected image satisfies the conditions related to the facial area, acquiring the captured image or the selected image as the target image.

[0132] In some embodiments, the image capture interface includes a predetermined border for defining a facial outline.

[0133] In some embodiments, the condition related to the facial area indicates at least one of the following conditions: the facial area of ​​the target object is located within a predetermined border in the captured image, the face of the target object is at an eye-level angle in the captured image, and the face of the target object shows a neutral expression in the captured image, and wherein the prompt information is determined based on one or more conditions that are not met in at least one of the conditions.

[0134] In some embodiments, obtaining the target image includes: if it is determined that the user's avatar image satisfies conditions related to the facial area, presenting a second expression creation entry for the user's avatar image in the image capture interface; and based on triggering the second expression creation entry, obtaining the user's avatar image as the target image.

[0135] In some embodiments, process 1700 also includes: providing a progress page, which presents a first progress indicator while presenting the target image to indicate the creation progress of at least one emoticon image; and / or providing other pages outside the progress page, presenting a second progress indicator in the other pages to indicate the creation progress of at least one emoticon image, and triggering the second progress indicator can jump to the progress page.

[0136] In some embodiments, process 1700 further includes: after the creation of at least one emoticon image is completed, providing a push notification to indicate that the emoticon creation is completed, wherein the push notification includes a first emoticon viewing entrance to view the at least one emoticon that has been created.

[0137] In some embodiments, the at least one expression style includes at least one of the following: at least one predefined expression style, at least one expression style indicated by a user, and at least one expression style determined based on a trending event.

[0138] In some embodiments, the user interface includes a message sending and receiving interface between a user and another user, a comment reply interface for a work, or a message page, the message page includes a list of message sending and receiving interfaces, and detecting an expression creation operation includes: presenting a first expression creation entry for a first type in the user interface; and detecting an expression creation operation based on triggering the first expression creation entry.

[0139] In some embodiments, presenting a first expression creation entry includes: presenting an expression guide card in a message sending and receiving interface, the expression guide card including at least a first expression creation entry for a first type, wherein the expression guide card is maintained presented after the last message in the message sending and receiving interface.

[0140] In some embodiments, presenting an expression guide card includes: presenting an expression guide card in a messaging interface if at least one of the following is determined: the user has not created an expression image of the first type, the messaging interface includes at least one historical message, and the messaging interface does not include unread messages.

[0141] In some embodiments, process 1700 also includes: in response to detecting a cancel presentation operation on the emoticon guide card, canceling the presentation of the emoticon guide card; presenting a first embedded message in the messaging interface, the first embedded message including at least a first emoticon creation entry; and in response to detecting that a new message is received or sent in the messaging interface, or in response to detecting that the messaging interface is canceled from presentation, canceling the presentation of the first embedded message in the messaging interface.

[0142] In some embodiments, presenting a first emoticon creation portal includes: based on receiving a message from another user in the messaging interface and the message including a first emoticon image of a first type, presenting a second embedded message in the messaging interface, the second embedded message including at least the first emoticon creation portal.

[0143] In some embodiments, presenting the second inline message includes presenting the second inline message after a message from another user, wherein a new message received in the messaging interface is presented after the second inline message.

[0144] In some embodiments, presenting the second embedded message includes: presenting the second embedded message in the messaging interface based on at least one of the following: the user has not created an emoticon image of the first type, and the emoticon guide card has not been presented in the messaging interface.

[0145] In some embodiments, presenting a first expression creation portal includes: in response to detecting a trigger operation on a second expression image of a first type sent or received in a messaging interface, presenting an expression viewing panel for the second expression image in the messaging interface, the expression viewing panel including the first expression creation portal.

[0146] In some embodiments, presenting an emoticon viewing panel in a messaging interface includes providing a first emoticon creation entry in the emoticon viewing panel based on determining at least one of the following: the user has not created an emoticon image of the first type, and the second emoticon image is not created by the user.

[0147] In some embodiments, process 1700 further includes: if the user has created the first type of emoticon image or the second emoticon image is created by the user, including at least one of a send control and a favorite control for the second emoticon image in the emoticon viewing panel.

[0148] In some embodiments, presenting a first expression creation entry includes: in response to detecting a trigger operation on an expression panel in a messaging interface, presenting an expression panel in the messaging interface, the expression panel providing at least a first expression creation entry for a first type.

[0149] In some embodiments, the expression panel includes at least one of the following: a first expression creation entrance specific to the first type, a general first expression creation entrance, and at least presenting the first expression creation entrance specific to the first type based on triggering the general first expression creation entrance.

[0150] In some embodiments, presenting a first emoticon creation entry includes: presenting an emoticon navigation bar in a message sending and receiving interface or a comment reply interface for a work, the emoticon navigation bar including a first label corresponding to the first type and a second label corresponding to at least one other emoticon type; and in response to detecting that the first label is triggered, presenting a first emoticon creation entry for the first type.

[0151] In some embodiments, the expression creation operation includes an expression creation operation for a user's avatar image, and detecting the expression creation operation includes: presenting a second expression creation entry for the user's avatar image in a message page; and based on triggering the second expression creation entry, detecting the expression creation operation for the user's avatar image.

[0152] In some embodiments, process 1700 further includes: after the creation of the at least one expression image is completed, providing a second expression viewing portal for the at least one expression image in the user interface to view the at least one expression that has been created.

[0153] In some embodiments, the at least one expression image includes at least one of the following: at least one static expression image, and at least one dynamic expression image.

[0154] Example devices and equipment

[0155] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Fig.18 A schematic structural block diagram of an apparatus 1800 for creating expressions according to some embodiments of the present disclosure is shown. The apparatus 1800 may be implemented as or included in the terminal device 120. Each module / component in the apparatus 1800 may be implemented by hardware, software, firmware, or any combination thereof.

[0156] like Fig.18As shown, the device 1800 includes a target image acquisition module 1810, which is configured to obtain a target image input by a user in response to an expression creation operation, and the target image at least includes the face of a target object. The device 1800 also includes an expression image acquisition module 1820, which is configured to obtain at least one expression image of a first type, at least one expression image is generated using an image generation model based at least on the target image, at least one expression image corresponds to at least one expression style, and each expression image includes a change object corresponding to the target object. The device 1800 also includes an expression image storage module 1830, which is configured to store at least one expression image in an expression library associated with the user for use in message interaction.

[0157] In some embodiments, the device 1800 further includes: a creation operation detection module configured to detect an expression creation operation corresponding to the first type in a user interface supporting message interaction, and the acquisition of the target image is based on the expression creation operation corresponding to the first type.

[0158] In some embodiments, at least one expression image is generated using an image generation model based on a target image and also based on a prompt word input indicating a style and / or expression pattern of at least one variation object to be generated.

[0159] In some embodiments, at least one expression image is generated using an image generation model based on the target image and also based on a user selection indicating a style and / or expression pattern of at least one variation object to be generated.

[0160] In some embodiments, the face of the changed object has a corresponding expression pattern.

[0161] In some embodiments, the target image acquisition module 1810 includes: an interface providing module, configured to provide an image capturing interface or an image selection interface based on detecting an expression creation operation, using a camera to capture an image in the image capturing interface, and selecting a captured image in the image selection interface; a prompt information providing module, configured to provide prompt information to prompt re-capture or re-selection of the image if it is determined that the image captured in the image capturing interface or the image selected in the image selection interface does not meet the conditions related to the facial area; and an image acquisition module, configured to acquire the captured image or the selected image as the target image if it is determined that the captured image or the selected image meets the conditions related to the facial area.

[0162] In some embodiments, the image capture interface includes a predetermined border for defining a facial outline.

[0163] In some embodiments, the condition related to the facial area indicates at least one of the following conditions: the facial area of ​​the target object is located within a predetermined border in the captured image, the face of the target object is at an eye-level angle in the captured image, and the face of the target object shows a neutral expression in the captured image, and wherein the prompt information is determined based on one or more conditions that are not met in at least one of the conditions.

[0164] In some embodiments, the target image acquisition module 1810 includes: a second entry presentation module, configured to present a second expression creation entry for the user's avatar image in the image capture interface if it is determined that the user's avatar image satisfies conditions related to the facial area; and an avatar image acquisition module, configured to acquire the user's avatar image as the target image based on triggering the second expression creation entry.

[0165] In some embodiments, device 1800 also includes: a progress page providing module, configured to provide a progress page, the progress page presents a first progress indicator while presenting the target image to indicate the creation progress of at least one emoticon image; and / or other page providing modules, configured to provide other pages other than the progress page, presenting a second progress indicator in the other pages to indicate the creation progress of at least one emoticon image, and triggering the second progress indicator can jump to the progress page.

[0166] In some embodiments, device 1800 also includes: a push notification providing module, configured to provide a push notification after the creation of at least one emoticon image is completed to indicate that the emoticon creation is completed, wherein the push notification includes a first emoticon viewing entrance to view at least one emoticon that has been created.

[0167] In some embodiments, the at least one expression style includes at least one of the following: at least one predefined expression style, at least one expression style indicated by a user, and at least one expression style determined based on a trending event.

[0168] In some embodiments, the user interface includes a message sending and receiving interface between a user and another user, a comment reply interface for a work, or a message page, the message page includes a list of message sending and receiving interfaces, and the creation operation detection module includes: a first entry presentation module, configured to present a first expression creation entry for a first type in the user interface; and a first detection module, configured to detect an expression creation operation based on triggering the first expression creation entry.

[0169] In some embodiments, the first entry presentation module includes: a guide card presentation module, configured to present an expression guide card in a message sending and receiving interface, the expression guide card includes at least creating an entry for a first expression of a first type, wherein the expression guide card is maintained and presented after the last message in the message sending and receiving interface.

[0170] In some embodiments, the first entry presentation module is further configured to present an expression guide card in the messaging interface if at least one of the following is determined: the user has not created an expression image of the first type, the messaging interface includes at least one historical message, and the messaging interface does not include unread messages.

[0171] In some embodiments, the device 1800 also includes: a card cancellation presentation module, configured to cancel the presentation of the expression guide card in response to detecting a cancellation presentation operation on the expression guide card; a first embedded message presentation module, configured to present a first embedded message in the message sending and receiving interface, the first embedded message at least including a first expression creation entrance; and a first embedded message cancellation module, configured to cancel the presentation of the first embedded message in the message sending and receiving interface in response to detecting that a new message is received or sent in the message sending and receiving interface, or in response to detecting that the message sending and receiving interface is canceled.

[0172] In some embodiments, the first entry presentation module includes: a second embedded message presentation module, configured to present a second embedded message in the messaging interface based on receiving a message from another user in the messaging interface and the message including a first expression image of a first type, wherein the second embedded message includes at least the first expression creation entry.

[0173] In some embodiments, the second inline message presentation module is further configured to: present the second inline message after a message from another user, wherein a new message received in the messaging interface is presented after the second inline message.

[0174] In some embodiments, the second embedded message presentation module is further configured to: present the second embedded message in the messaging interface based on at least one of the following: the user has not created an expression image of the first type, and the expression guide card is not presented in the messaging interface.

[0175] In some embodiments, the first entry presentation module includes: a viewing panel presentation module, configured to present an expression viewing panel for the second expression image of the first type sent or received in the message sending and receiving interface in response to detecting a trigger operation on the second expression image of the first type sent or received in the message sending and receiving interface, the expression viewing panel including the first expression creation entry.

[0176] In some embodiments, the viewing panel presentation module is further configured to provide a first expression creation entry in the expression viewing panel based on determining at least one of the following: the user has not created the first type of expression image, and the second expression image is not created by the user.

[0177] In some embodiments, the device 1800 further includes: if the user has created the first type of expression image or the second expression image is created by the user, including at least one of a send control and a favorite control for the second expression image in the expression viewing panel.

[0178] In some embodiments, the first entry presentation module includes: an expression panel presentation module, configured to present an expression panel in the message sending and receiving interface in response to detecting a trigger operation on the expression panel in the message sending and receiving interface, and the expression panel provides at least a first expression creation entry for the first type.

[0179] In some embodiments, the expression panel includes at least one of the following: a first expression creation entrance specific to the first type, a general first expression creation entrance, and at least presenting the first expression creation entrance specific to the first type based on triggering the general first expression creation entrance.

[0180] In some embodiments, the first entry presentation module includes: an expression navigation bar presentation module, configured to present an expression navigation bar in a message sending and receiving interface or a comment reply interface for a work, the expression navigation bar including a first label corresponding to a first type and a second label corresponding to at least one other expression type; and a presentation module, configured to present a first expression creation entry for the first type in response to detecting that the first label is triggered.

[0181] In some embodiments, the expression creation operation includes an expression creation operation for a user's avatar image, and the creation operation detection module includes: a second expression creation entry presentation module, configured to present a second expression creation entry for the user's avatar image in a message page; and a detection module, configured to detect the expression creation operation for the user's avatar image based on triggering the second expression creation entry.

[0182] In some embodiments, the device 1800 also includes: a second expression viewing entry providing module, which is configured to provide a second expression viewing entry for at least one expression image in the user interface after the creation of at least one expression image is completed, so as to view the at least one expression that has been created.

[0183] In some embodiments, the at least one expression image includes at least one of the following: at least one static expression image, and at least one dynamic expression image.

[0184] The units and / or modules included in the device 1800 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 1800 can be implemented at least in part by one or more hardware logic components. As an 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 chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0185] It should be understood that one or more steps in the above method can be performed by a suitable electronic device or a combination of electronic devices. Such an electronic device or a combination of electronic devices may include, for example, Figure 1 The terminal device 120 and the server 130 in.

[0186] Fig.19 1 shows a block diagram of an electronic device 1900 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Fig.19 The electronic device 1900 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Fig.19 The electronic device 1900 shown can be used to implement Figure 1 terminal device 120.

[0187] like Fig.19 As shown, the electronic device 1900 is in the form of a general electronic device. The components of the electronic device 1900 may include, but are not limited to, one or more processors or processing units 1910, a memory 1920, a storage device 1930, one or more communication units 1940, one or more input devices 1950, and one or more output devices 1960. The processing unit 1910 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 1920. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 1900.

[0188] The electronic device 1900 typically includes a plurality of computer storage media. Such media may be any available media accessible to the electronic device 1900, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1920 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1930 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 1900.

[0189] The electronic device 1900 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig.19 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 1920 may include a computer program product 1925 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0190] The communication unit 1940 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 1900 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 1900 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0191] The input device 1950 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 1960 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 1900 may also communicate with one or more external devices (not shown) through the communication unit 1940 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 1900, or communicate with any device that allows the electronic device 1900 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).

[0192] 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.

[0193] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0194] 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, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0195] 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, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0196] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square 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.

[0197] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for creating an expression, comprising: In response to the expression creation operation, obtaining a target image input by a user, wherein the target image at least includes a face of a target object; Acquire at least one expression image of a first type, wherein the at least one expression image is generated by using an image generation model based at least on the target image, the at least one expression image corresponds to at least one expression style, and each expression image includes a change object corresponding to the target object; as well as The at least one emoticon image is stored in an emoticon library associated with the user for use in message interaction.

2. The method according to claim 1, further comprising: In a user interface supporting message interaction, an expression creation operation corresponding to the first type is detected, and the acquisition of the target image is based on the expression creation operation corresponding to the first type.

3. The method according to claim 1, wherein the at least one expression image is generated based on the target image and also based on a prompt word input using the image generation model, wherein the prompt word input indicates a style and / or expression pattern of at least one change object to be generated.

4. The method of claim 1, wherein the at least one expression image is generated based on the target image using an image generation model and also based on a user selection indicating a style and / or expression pattern of at least one variation object to be generated. The method according to claim 1 , wherein the face of the changed object has a corresponding expression pattern.

6. The method according to claim 1, wherein acquiring the target image comprises: Based on the detection of the expression creation operation, providing an image shooting interface or an image selection interface, in which an image is captured using a camera, and in which a captured image is selected in the image selection interface; If it is determined that the image captured in the image capturing interface or the image selected in the image selecting interface does not satisfy the condition related to the facial region, providing prompt information to prompt re-capture or re-selection of the image; as well as If it is determined that the captured image or the selected image satisfies the condition related to the face area, the captured image or the selected image is acquired as the target image. The method according to claim 6 , wherein the image capturing interface includes a predetermined frame for defining a facial outline.

8. The method of claim 6, wherein the condition related to a facial region indicates at least one of the following conditions: The facial area of ​​the target object is located within a predetermined frame in the captured image, The target object's face is at an eye-level angle in the captured image, The target object's face exhibits a neutral expression in the captured image, and The prompt information is determined based on one or more conditions that are not satisfied among the at least one condition.

9. The method according to claim 6, wherein acquiring the target image comprises: If it is determined that the user's avatar image satisfies the condition related to the facial region, presenting a second expression creation entry for the user's avatar image in the image capture interface; as well as Based on triggering the second expression creation portal, the avatar image of the user is acquired as the target image.

10. The method according to claim 1, further comprising: Providing a progress page, wherein the progress page presents a first progress indicator while presenting the target image to indicate the creation progress of the at least one expression image; and / or Other pages other than the progress page are provided, and a second progress indicator is presented in the other page to indicate the creation progress of the at least one emoticon image, and triggering the second progress indicator can jump to the progress page.

11. The method according to claim 1, further comprising: After the creation of the at least one emoticon image is completed, providing a push notification to indicate that the emoticon creation is completed, The push notification includes a first emoticon viewing entrance for viewing the at least one emoticon that has been created.

12. The method according to claim 1, wherein the at least one expression pattern comprises at least one of the following: At least one predefined expression style, At least one expression pattern indicated by the user, and at least one expression pattern determined based on a trending event.

13. The method according to claim 2, wherein the user interface comprises a message sending and receiving interface between the user and another user, a comment reply interface for a work, or a message page, wherein the message page comprises a list of message sending and receiving interfaces, and Wherein detecting the expression creation operation comprises: Presenting, in the user interface, a first expression creation entry for the first type; as well as Based on triggering the first expression creation entry, the expression creation operation is detected.

14. The method according to claim 13, wherein presenting the first expression creation portal comprises: An expression guide card is presented in the message sending and receiving interface, wherein the expression guide card at least includes a first expression creation entry for the first type, The expression guide card is maintained and presented after the last message in the message sending and receiving interface.

15. The method according to claim 14, wherein presenting the expression guide card comprises: If at least one of the following is determined, the expression guide card is presented in the message sending and receiving interface: The user has not created the first type of emoticon image, The message sending and receiving interface includes at least one historical message, The message sending and receiving interface does not include unread messages.

16. The method according to claim 14, further comprising: In response to detecting a cancel presentation operation on the expression guide card, canceling presentation of the expression guide card; Presenting a first embedded message in the message sending and receiving interface, wherein the first embedded message at least includes the first expression creation entry; as well as In response to detecting that a new message is received or sent in the messaging interface, or in response to detecting that the messaging interface is canceled from being presented, the presentation of the first embedded message in the messaging interface is canceled.

17. The method according to claim 13, wherein presenting the first expression creation portal comprises: Based on receiving a message from the other user in the messaging interface and the message including the first expression image of the first type, presenting a second embedded message in the messaging interface, the second embedded message including at least the first expression creation entry.

18. The method of claim 17, wherein presenting the second embedded message comprises: presenting the second inline message after the message from the other user, The new message received in the message sending and receiving interface is presented after the second embedded message.

19. The method of claim 17, wherein presenting the second embedded message comprises: Also based on at least one of the following, presenting the second embedded message in the message sending and receiving interface: The user has not created the first type of emoticon image, The expression guide card is not presented in the message sending and receiving interface.

20. The method according to claim 13, wherein presenting the first expression creation portal comprises: In response to detecting a trigger operation on the second emoticon image of the first type sent or received in the messaging interface, an emoticon viewing panel for the second emoticon image is presented in the messaging interface, and the emoticon viewing panel includes the first emoticon creation portal.

21. The method according to claim 20, wherein presenting an expression viewing panel in the message sending and receiving interface comprises: Providing the first expression creation entry in the expression viewing panel based on determining at least one of the following: The user has not created the first type of emoticon image, The second expression image is not created by the user.

22. The method according to claim 21, further comprising: If the user has created the first type of emoticon image or the second emoticon image is created by the user, the emoticon viewing panel includes at least one of a sending control and a collection control for the second emoticon image.

23. The method according to claim 13, wherein presenting the first expression creation portal comprises: In response to detecting a triggering operation on an emoticon panel in the message sending and receiving interface, the emoticon panel is presented in the message sending and receiving interface, and the emoticon panel at least provides a creation entry for the first emoticon of the first type.

24. The method according to claim 23, wherein the expression panel includes at least one of the following: a first expression creation entry specific to the first type, A total first expression creation portal, based on triggering the total first expression creation portal, presents at least a first expression creation portal specific to the first type.

25. The method according to claim 13, wherein presenting the first expression creation portal comprises: Presenting an emoticon navigation bar in the message sending and receiving interface or the comment reply interface for the work, the emoticon navigation bar including a first label corresponding to the first type and a second label corresponding to at least one other emoticon type; as well as In response to detecting that the first tag is triggered, presenting a first expression creation entry for the first type.

26. The method according to claim 2, wherein the expression creation operation comprises an expression creation operation for an avatar image of the user, wherein detecting the expression creation operation comprises: Presenting a second expression creation entry for the user's avatar image in the message page; as well as Based on triggering the second expression creation portal, the expression creation operation for the user's avatar image is detected.

27. The method according to claim 26, further comprising: After the creation of the at least one expression image is completed, a second expression viewing entrance for the at least one expression image is provided in the user interface to view the at least one expression that has been created.

28. The method according to any one of claims 1 to 27, wherein the at least one expression image comprises at least one of the following: at least one static expression image, at least one dynamic expression image.

29. A device for creating expressions, comprising: A target image acquisition module, configured to acquire a target image input by a user in response to an expression creation operation, wherein the target image at least includes a face of a target object; an expression image acquisition module, configured to acquire at least one expression image of a first type, wherein the at least one expression image is generated using an image generation model based at least on the target image, the at least one expression image corresponds to at least one expression style, and each expression image includes a change object corresponding to the target object; as well as The expression image storage module is configured to store the at least one expression image in an expression library associated with the user for use in message interaction.

30. 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 28 when executed by the at least one processing unit.

31. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 28.

Images