Special effect template generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a special effect template generation method and device, electronic equipment and a storage medium, special effect generation data is obtained by responding to a first operation, the special effect generation data comprises configuration parameters representing a special effect style of a self-defined special effect, and the configuration parameters comprise a first prompt word and / or a first reference graph; displaying an effect picture of the user-defined special effect according to the special effect generation data and the user personalized image; in response to the second operation, the effect picture and the construction data corresponding to the effect picture are packaged, a special effect template of the user-defined special effect is generated, the effect picture is used for displaying the visual effect of the user-defined special effect based on the user personalized image on the resource platform, and after the special effect template is called, a corresponding special effect image is generated through the construction data. The flexibility and convenience of creating the self-defined special effect by the user and the propagation attribute of the special effect template are improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of Internet technology, and in particular, to a special effect template generation method, device, electronic device and storage medium. Background Art

[0002] Currently, image generation and editing functions based on artificial intelligence (AI) technology are increasingly being used in various user-generated content (UGC) scenarios, helping users quickly generate the pictures and video materials needed for creation.

[0003] In the prior art, in an application or platform with an image editing function, several specific special effect styles are usually provided to users in the form of special effect templates, and the user generates the desired special effect image by applying the special effect templates.

[0004] However, the above-mentioned special effects templates in the prior art are usually provided by the developers of the application or platform, and it is impossible to realize the creation and release of templates based on user intentions, resulting in poor diversity and low dissemination capabilities of special effects templates within the application or platform, which cannot meet the user's usage needs. Summary of the invention

[0005] The embodiments of the present disclosure provide a special effect template generation method, device, electronic device and storage medium to overcome the problem that it is impossible to create and publish templates based on user intentions.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for generating a special effect template, comprising:

[0007] In response to a first operation, special effect generation data is obtained, wherein the special effect generation data includes configuration parameters of a special effect style characterizing a custom special effect, wherein the configuration parameters include a first prompt word and / or a first reference image; a rendering of the custom special effect is displayed according to the special effect generation data and a user personalized image; in response to a second operation, the rendering and construction data corresponding to the rendering are packaged to generate a special effect template of the custom special effect, wherein the rendering is used to display the visual effect of the custom special effect based on the user personalized image on a resource platform, and after the special effect template is called, the corresponding special effect image is generated through the construction data.

[0008] In a second aspect, an embodiment of the present disclosure provides a special effect template generation device, comprising:

[0009] An acquisition module, configured to obtain special effect generation data in response to a first operation, wherein the special effect generation data includes configuration parameters representing a special effect style of a custom special effect, wherein the configuration parameters include a first prompt word and / or a first reference image;

[0010] A generation module, used to generate data for the special effect and a user-personalized image, and display an effect diagram of the custom special effect;

[0011] A packaging module is used to package the rendering and the construction data corresponding to the rendering in response to the second operation, and generate a special effect template for the custom special effect, wherein the rendering is used to display the visual effect of the custom special effect based on the user's personalized image on the resource platform, and after being called, the special effect template generates a corresponding special effect image through the construction data.

[0012] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0013] The memory stores computer-executable instructions;

[0014] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the special effect template generation method described in the first aspect and various possible designs of the first aspect.

[0015] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the special effects template generation method described in the first aspect and various possible designs of the first aspect is implemented.

[0016] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the special effect template generation method described in the first aspect and various possible designs of the first aspect.

[0017] The special effect template generation method, device, electronic device and storage medium provided in this embodiment obtain special effect generation data in response to a first operation, wherein the special effect generation data includes configuration parameters representing the special effect style of the custom special effect, and the configuration parameters include a first prompt word and / or a first reference image; display the effect image of the custom special effect according to the special effect generation data and the user personalized image; in response to a second operation, the effect image and the construction data corresponding to the effect image are packaged to generate a special effect template of the custom special effect, wherein the effect image is used to display the visual effect of the custom special effect based on the user personalized image on the resource platform, and the special effect template generates the corresponding special effect image through the construction data after being called. The effect image of the custom special effect is generated by inputting the special effect generation data, and the configuration parameters in the input special effect generation data are combined with the user personalized image, and then the special effect template of the custom special effect is generated by packaging the effect image of the custom special effect and the corresponding construction data. On the one hand, it realizes the creation of special effects templates based on user intentions, and there is no need for users to perform complex editing operations. The template production efficiency is high, which improves the flexibility and convenience of users in creating customized special effects. On the other hand, after the special effects template is published to the platform, the special effects image based on the user personalized image input by the user can be displayed through the rendering, thereby improving the dissemination properties of the special effects template. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 An application scenario diagram of the special effect template generation method provided in the embodiment of the present disclosure;

[0020] Figure 2 A schematic diagram of a process for generating a special effect template provided in an embodiment of the present disclosure Figure 1 ;

[0021] Figure 2A A schematic diagram of an interactive operation for obtaining special effect generation data provided by an embodiment of the present disclosure;

[0022] Figure 3 for Figure 2 A flowchart of a specific implementation method of step S103 in the illustrated embodiment;

[0023] Figure 4 A schematic diagram of a process of generating and consuming special effect templates provided in an embodiment of the present disclosure;

[0024] Figure 5 Schematic diagram of the process of generating a special effect template provided by the embodiment of the present disclosure Figure 2 ;

[0025] Figure 6 for Figure 2 A flowchart of a specific implementation method of step S202 in the illustrated embodiment;

[0026] Figure 7 A schematic diagram of a special effect template generation and consumption process when special effect generation data includes portrait parameters provided by an embodiment of the present disclosure;

[0027] Figure 8 A schematic diagram of a special effect template generation and consumption process when another special effect generation data includes portrait parameters provided by an embodiment of the present disclosure;

[0028] Fig. 9 A schematic diagram of a special effect template generation and consumption process when special effect generation data includes stylized parameters provided by an embodiment of the present disclosure;

[0029] Fig.10 A structural block diagram of a special effect template generation device provided in an embodiment of the present disclosure;

[0030] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure;

[0031] Fig.12 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0033] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0034] The application scenarios of the embodiments of the present disclosure are explained below:

[0035] The special effect template generation method provided by the embodiment of the present disclosure can be applied to applications (APP, Application) with AI image generation functions, such as video editing applications, image drawing applications, etc. More specifically, it can be applied to application scenarios for making and publishing AI special effect templates. The execution subject of this embodiment can be a terminal device running the above-mentioned application with AI image generation function, or a server that deploys the server corresponding to the above-mentioned application, or other electronic devices that perform similar functions. Among them, when the execution subject is a terminal device, the terminal device executes the method provided in this embodiment by running the above-mentioned application; when the execution subject is a server, the server of the above-mentioned application with AI image generation function can be partially or completely run on the server, and the method provided in this embodiment is executed on the server side, and the terminal device runs the client of the application, and the communication between the server and the terminal device is based on the server-client, so that the terminal device can obtain the execution result of the method provided in this embodiment and display it as needed.

[0036] Among them, in some embodiments, the terminal device or server can implement the special effect template generation method provided by the embodiment of the present disclosure by running various computer executable instructions or computer programs. For example, computer executable instructions can be program-level commands, machine instructions or software instructions. The computer program can be a native program or software module in the operating system; it can be a local application, that is, a program that needs to be installed in the operating system to run, or it can be a small program embedded in any APP, that is, a program that runs based on a browser environment. In summary, the above-mentioned computer executable instructions can be instructions in any form, and the above-mentioned computer program can be an application, module or plug-in in any form, and the specific implementation form can be configured as needed. Furthermore, in the process of implementing the special effect template generation method provided by the embodiment of the present disclosure, the terminal device can execute the method by running a computer executable instruction or computer program set locally, or it can execute the method by calling a computer executable instruction or computer program set in an external server. In some embodiments, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud storage, cloud communications, cloud databases, cloud computing, cloud functions, network services, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms. Among them, cloud services can be interactive processing services for terminal devices to call.

[0037] Figure 1 An application scenario diagram of the special effect template generation method provided in the embodiment of the present disclosure, referring to Figure 1 As shown in , taking the terminal device as an example, a target application with AI image generation function is running in the terminal device. User User_1 enters the description words (i.e., prompt words, shown as "XXX" in the figure) used to describe the special effect style through the interactive interface of the target application. After the reference image, the target application generates the corresponding effect picture through the AI ​​model deployed locally or in the cloud. The user can preview the effect picture and adjust the parameters by triggering the return modification control to regenerate the effect picture. After repeating the above steps, by triggering the output template control, a custom special effect template #1 (shown as #1) is finally generated locally on the terminal device, and the special effect template can be further released to the image generation platform unless the release control is released, thereby completing the production and release process of the custom special effect template. Other users, such as user User_2, can access the image generation platform by running the target application, and view and apply the custom special effect template from the image generation platform to generate the corresponding special effect image.

[0038] In the prior art, in applications or platforms with image editing functions, several specific special effect styles are usually provided to users in the form of special effect templates, such as image style conversion effects, background replacement effects, etc. Users generate the required special effect images by applying the above special effect templates. However, the above special effect templates in the prior art are usually provided by the developers of the application or platform, and it is impossible to realize the creation and release of templates based on user intentions. Therefore, the number of special effect templates in the application or platform is small, the style is single, and the dissemination ability is poor, which cannot meet the user's usage needs and platform dissemination needs.

[0039] The disclosed embodiment provides a special effect template generation method to solve the above-mentioned problem.

[0040] refer to Figure 2 , Figure 2 A schematic diagram of a process for generating a special effect template provided in an embodiment of the present disclosure Figure 1 The method of this embodiment can be applied in a terminal device or a server. The special effect template generation method includes:

[0041] Step S101: in response to a first operation, obtaining special effect generation data, the special effect generation data including configuration parameters of a special effect style representing a custom special effect, the configuration parameters including a first prompt word and / or a first reference image.

[0042] Step S102: Generate and display a rendering of the customized special effect according to the special effect generation data and the user personalized image.

[0043] refer to Figure 1 In the application scenario schematic diagram shown, the terminal device is used as the execution subject to introduce the special effect template generation method provided in this embodiment. For example, a target application with AI image generation function is running in the terminal device. The user selects the special effect generation data stored locally or in the cloud of the terminal device through the interactive interface of the target application, or inputs the special effect generation data, so that the terminal device obtains the special effect generation data. Among them, the special effect generation data is the data used to describe the style and content of the special effect, which may include prompt words and / or pictures, and the special effect generation data is used to realize the subsequent control of the generated special effect template. Specifically, the special effect generation data includes configuration parameters representing the special effect style of the custom special effect, and the configuration parameters include a first prompt word and / or a first reference picture, wherein the first prompt word is a text used to describe the special effect style of the custom special effect, and the content of the first prompt word is, for example, "portrait photography, portrait, surrealism, solid color background". Through the above exemplary first prompt word, the description of the perspective effect and special effect content of the custom special effect can be realized. The first reference image is used as a reference object to generate a custom special effect. That is, the style, content and other features of the first reference image are extracted and applied to other images as special effects. There are multiple ways to implement the configuration parameters, for example, only including the first prompt word; another example, only including one or more reference images; another example, including both the first prompt word and the first reference image. The user enters the configuration parameters in the special effect generation data to describe the custom special effect to be created.

[0044] Afterwards, the terminal device obtains the user personalized image, and generates a rendering of the custom special effect based on the special effect generation data and the user personalized image, and displays it in the interactive interface. Among them, the user personalized image is the image uploaded or loaded by the user who created the custom special effect, such as a portrait photo of the user. Afterwards, the terminal device calls the corresponding image generation model based on the above special effect generation data, applies the custom special effect described by the special effect generation data to the above user personalized image, and generates a user personalized image with the above custom special effect, that is, a rendering of the custom special effect. Afterwards, the user can modify the special effect generation data according to the actual visual effect of the rendering, and control the terminal device to re-execute the above steps to realize the modification and debugging of the custom special effect.

[0045] Furthermore, the terminal device obtains special effect generation data by receiving a specific interactive operation. In a possible implementation, the first operation includes a first sub-operation, a second sub-operation, and a third sub-operation. The specific implementation of step S101 includes:

[0046] Step S1011: In response to the first sub-operation, the first reference image is imported and a special effect template control is displayed.

[0047] Step S1012: In response to the second sub-operation for the special effect template control, a template operation item is displayed, where the template operation item is used to load a created special effect template or create a new special effect template.

[0048] Step S1013: In response to the third sub-operation for the template operation item, receiving the first prompt word input by the user, or loading the original configuration parameters in the created special effect template.

[0049] Step S1014: generating the special effect generation data based on the first reference image and the first prompt word; or generating the special effect generation data based on the original configuration parameters.

[0050] Figure 2A A schematic diagram of an interactive operation for obtaining special effect generation data provided by an embodiment of the present disclosure is shown below in conjunction with Figure 2A The above steps are introduced as follows: Figure 2A As shown, first, in the interactive interface of the target application, in response to the first sub-operation, the gallery page is displayed, and the first reference image is selected and loaded from the gallery. After that, the special effect template control is displayed in the interactive interface, that is, the "special effect gameplay" described in the figure. After that, through the point-selection operation (second sub-operation) of the "special effect gameplay" control, the template operation items are displayed in the "special effect gameplay" page. The template operation items include the first type of operation items for creating a new special effect module, such as the "create template" operation item described in the figure; and the "A template", "B template" and other operation items for loading the created special effect template. After that, when "create template" (the third sub-operation) is clicked, the user can select the effect style corresponding to the special effect template through further operations on the creation page of the new template, such as general, comics, photo, etc. Enter the first prompt word (represented by XXX in the figure) in the "effect description" column, so that the terminal device obtains the first prompt word. Furthermore, effect parameters can also be set in the creation page, including "canvas ratio" (for example, original ratio, 3:4, 9:16, etc.) and "style intensity", so as to achieve more refined control over the special effects. The information in the above creation page will be stored in the configuration parameters corresponding to the special effects template. Alternatively, in another implementation method, the original configuration parameters in the created special effects template can be loaded so that the terminal device obtains the original configuration parameters, that is, the configuration parameters written when the special effects template is created. Finally, the special effect generation data is generated based on the first reference image and the first prompt word; or, the special effect generation data is generated based on the original configuration parameters.

[0051] Further, for the case of inputting the first prompt word, more specifically, the specific implementation of step S1013 includes:

[0052] Step S1013 - 1 : receiving a first description word input by a user.

[0053] Step S1013-2: Based on the first description participle, generate and display a second description participle corresponding to the first description participle, wherein the second description participle and the first description participle respectively describe the features of the special effect style in different feature dimensions.

[0054] Step S1013 - 3 : Generate the first prompt word according to the first description participle and the second description participle.

[0055] In this embodiment, after the user inputs the first description segmentation word, the terminal device automatically associates the features that match the first description segmentation word and are no longer in the same feature dimension based on the feature dimension of the first description segmentation word, and generates a second description segmentation word. For example, the first prompt word is "long black hair", and then the second description segmentation word automatically generated by the terminal device is "black eyes", "melon-seed face", etc. The second description segmentation word can be generated based on the user history record, or based on the preset prompt word generation logic, combined with the semantics of the first description segmentation word after reasoning, which is not limited here. In the above manner, the efficiency of prompt word generation is further improved.

[0056] Furthermore, in the case of loading the original configuration parameters, the original configuration parameters include, in addition to the first prompt word and the first reference image, effect parameters, which are used to characterize the special effect display parameters corresponding to the special effect image generated based on the created special effect template, wherein the special effect display parameters include at least one of the following: canvas ratio, style intensity, background change enable; on this basis, the original configuration parameters can be further modified for a second time to generate new configuration parameters. Specifically, the specific implementation of step S1014 includes:

[0057] Step S1014-1: generating edited configuration parameters in response to a third operation on the original configuration parameters, wherein the third operation is used to modify the first prompt word and / or the first reference image and / or the effect parameter in the original configuration parameters.

[0058] Step S1014-2: Generate the special effect generation data based on the edited configuration parameters.

[0059] By responding to the third operation for input, the modification of the original configuration parameters is realized, specifically, including the modification of any one of the first prompt word, the first reference image, and the effect parameter corresponding to the original configuration parameters. Thus, the secondary editing of the generated special effect template is realized. Step S103: In response to the second operation, the effect graph and the construction data corresponding to the effect graph are packaged to generate a special effect template of a custom special effect, wherein the effect graph is used to display the visual effect of the custom special effect based on the user's personalized image on the resource platform, and after the special effect template is called, the corresponding special effect image is generated by the construction data.

[0060] Exemplarily, after obtaining a special effect graph that meets the user's intention, the user inputs a second operation to the terminal device to control the terminal device to generate a corresponding special effect template. The terminal device will respond to the second operation, package the effect graph generated in the above steps and the corresponding construction data, and generate a special effect template for the custom special effect. Among them, the construction data is the data used to generate the effect graph, which can be a configuration parameter, or it can be data obtained by processing the configuration parameters, such as a second reference image generated based on the first prompt word. By encapsulating the construction data into the special effect template, the special effect template has the ability to restore the custom special effects corresponding to the above effect graph, and the special effect graph generated based on the user's personalized image can realize personalized display for the special effect template, improve the display effect of the special effect template, and facilitate the dissemination of the special effect template. Afterwards, the terminal device can publish the special effect template to the resource platform by further responding to the user's publishing instruction, for example Figure 1 In the template library of the image generation platform in the illustrated embodiment, it is available for other users to call. Specifically, since the special effect template contains the effect picture and the corresponding construction data, the template will be displayed based on the effect picture on the resource platform side, and when the special effect template is downloaded by the terminal device of other users, the terminal device that downloads the special effect template will generate the corresponding special effect image based on the personalized image input by other users and the construction data in the special effect template, thereby realizing the application of the special effect template.

[0061] In a possible implementation, the special effect generation data includes a special effect type parameter, and the special effect type parameter includes one of the following: a portrait parameter, a stylization parameter, and a background parameter, wherein the portrait parameter is used to control the special effect template to generate a custom special effect for a character portrait, such as a character portrait special effect; the stylization parameter is used to control the special effect template to generate a custom special effect for a specific image style, such as a cartoon style special effect; the background parameter is used to control the special effect template to generate a custom special effect for replacing the image background, such as a starry sky background special effect. Specifically, Figure 3 As shown, the specific implementation of step S103 includes:

[0062] Step S1031: Determine the corresponding model identifier according to the construction data of the effect diagram and the special effect type parameters.

[0063] Step S1032: Pack the construction data, special effect type parameters and corresponding model identifiers into template calling parameters. The template calling parameters are used to call the corresponding processing model to generate special effect images when calling the special effect template based on the construction data and special effect type parameters.

[0064] Step S1033: Encapsulate the template calling parameters and effect diagram to generate a special effect template.

[0065] Exemplarily, for different special effect types, different functional models need to be called in the implementation process to provide corresponding image processing capabilities. For example, for stylized parameters, a style transfer model needs to be called for image processing, and for portrait parameters, a Wenshengtu model needs to be called for image processing, and so on. Therefore, in the process of packaging special effect templates, it is necessary to record the functional models corresponding to different feature types in the special effect templates, so that after the special effect templates are called, the matching functional models can be called according to different special effect types. Specifically, the terminal device first determines the corresponding model identifier according to the combination of the construction data and the special effect type parameters, wherein a set of data pairs can be formed according to the construction data and the special effect type parameters, such as [construction data, special effect type parameters], and the data pairs formed by the construction data and the special effect type parameters have a fixed mapping relationship with the model identifier. For example, [first prompt word, portrait parameter p1], the corresponding model identifier is M1; [second reference image, portrait parameter p2], the corresponding model identifier is M2; [(first reference image, first prompt word), stylized parameter], the corresponding model identifier is M3. After that, the construction data, special effect type parameters and corresponding model identifiers are packaged as template call parameters. For example, [first prompt word, image parameter p1, model identifier M1] is one type of template call parameter; [second reference image, image parameter p2, model identifier M2] is another type of template call parameter. After obtaining the template call parameters, the template call parameters are packaged with the effect image generated in the previous step to obtain a special effect template.

[0066] Figure 4 A schematic diagram of a process of generating and consuming special effect templates provided in an embodiment of the present disclosure is shown below in conjunction with Figure 4 The above process is described in more detail, such as Figure 4As shown, the first terminal device is a terminal device for generating a special effect template. First, the first terminal device responds to the first operation and obtains the special effect generation data D1. The special effect generation data D1 includes the configuration parameter P1 and the special effect type parameter P2. The configuration parameter P1 is the construction data of the effect diagram. Afterwards, the first terminal device calls the corresponding function model M1 (model identifier M1) based on the configuration parameter P1 and the special effect type parameter P2, and generates the effect diagram in combination with the user's personalized image. Afterwards, the first terminal device responds to the second operation and packages the special effect generation data D1 including the configuration parameter P1 and the special effect type parameter P2, and the model identifier M1 of the corresponding function model into a template call parameter. Finally, the template call parameters and the above-mentioned effect diagram are encapsulated as a special effect template #1. The second terminal device is a terminal device that consumes special effect templates. In the application stage of the special effect template #1, the second terminal device first displays the special effect template #1 through the effect diagram in the special effect template #1; then, based on the template call parameters in the special effect template #1, the prompt information is displayed, and the prompt information is used to characterize the special effect type of the special effect template #1 (determined based on the special effect type parameter P2), such as portrait photography. Finally, according to the user image input by the user on the second terminal device, the special effect template #1 is applied, so that the custom special effect represented by the special effect template #1 is applied to the user image to obtain a special effect image.

[0067] Furthermore, in a possible implementation, after the special effects template of the custom special effect is generated, it is equivalent to creating a new special effects template (or updating an old special effects template). Therefore, in combination with the interaction steps in the previous embodiment, the newly generated special effects template can be added to the special effects template control, so that after the special effects template control is triggered, the template operation item corresponding to the custom special effect is generated and displayed in the special effects template page. In the case of updating an old special effects template, the updated special effects template can also be added to the special effects template control, so that after the special effects template control is triggered, the template operation item corresponding to the custom special effect is displayed in the special effects template page based on different version identifiers to distinguish it from the original special effects template.

[0068] In this embodiment, by responding to the first operation, special effect generation data is obtained, the special effect generation data includes configuration parameters that characterize the special effect style of the custom special effect, and the configuration parameters include a first prompt word and / or a first reference image; according to the special effect generation data and the user personalized image, a rendering of the custom special effect is generated; in response to the second operation, the rendering and the construction data corresponding to the rendering are packaged to generate a special effect template of the custom special effect, wherein the rendering is used to display the visual effect of the custom special effect based on the user personalized image on the resource platform, and the special effect template generates the corresponding special effect image through the construction data after being called. The rendering of the custom special effect is generated by inputting the special effect generation data, and according to the configuration parameters in the input special effect generation data combined with the user personalized image, the rendering of the custom special effect is generated, and then the rendering of the custom special effect and the corresponding construction data are packaged to generate the special effect template of the custom special effect. On the one hand, it realizes the creation of special effects templates based on user intentions, and there is no need for users to perform complex editing operations. The template production efficiency is high, which improves the flexibility and convenience of users in creating customized special effects. On the other hand, after the special effects template is published to the platform, the special effects image based on the user personalized image input by the user can be displayed through the rendering, thereby improving the dissemination properties of the special effects template.

[0069] refer to Figure 5 , Figure 5 Schematic diagram of the process of generating a special effect template provided by the embodiment of the present disclosure Figure 2 In this embodiment Figure 2 On the basis of the embodiment shown, step S102 is further refined, the special effect generation data includes a special effect type parameter, and the special effect type parameter includes one of the following: a portrait parameter, a stylized parameter, and a background parameter; the special effect template generation method includes:

[0070] Step S201: in response to a first operation, obtaining special effect generation data, the special effect generation data including configuration parameters and special effect type parameters characterizing a special effect style of a custom special effect, the configuration parameters including a first prompt word and / or a first reference image.

[0071] Step S202: When the special effect type parameter is a portrait parameter, and the parameter value of the portrait parameter is the first parameter value, a second reference image is generated according to the configuration parameters, and the user personalized image is integrated into the second reference image to generate a rendering of the custom special effect.

[0072] Exemplarily, in the steps of this embodiment, the special effect generation data includes a portrait parameter, and the portrait parameter is used to characterize the consistency between the special effect images generated multiple times by the custom special effect template. When the special effect generation data includes a portrait parameter, it indicates that the custom special effect corresponding to the special effect template is a special effect for portraits, such as a photo special effect. Different parameter values ​​of the portrait parameter characterize the degree of freedom of the custom special effect. Specifically, in one possible case, the portrait parameter is a first parameter value, and the first parameter value represents a low-degree-of-freedom special effect, that is, the special effect images generated multiple times by the custom special effect template are the same, that is, they have high consistency; on the contrary, in another possible case, the portrait parameter is a second parameter value, and the second parameter value represents a high-degree-of-freedom special effect, that is, the special effect images generated multiple times by the custom special effect template are not the same, that is, they have low consistency.

[0073] In the steps of this embodiment, when the portrait parameter is the first parameter value, a second reference image is generated according to the configuration parameters, and the second reference image is used as the construction data to fuse the user's personalized image into the second reference image to generate a custom special effect effect image. The effect image generated by the above method is based on the image content of the second reference image, and most of the image content is consistent with the second reference image. Figure 1 Only a small part of the image content fused to the user personalized image is different, for example, a face-changing effect using the second reference image as the base image (i.e., replacing the facial area in the second reference image with the facial area in the user personalized image), or a torso-changing effect using the second reference image as the base image (i.e., replacing the human torso area in the second reference image with the human torso area in the user personalized image).

[0074] Further, in one possible implementation, the user personalized image includes a facial image, such as Figure 6 As shown, the specific implementation of step S202 includes:

[0075] Step S2021: when the configuration parameters include the first prompt word, the configuration parameters are processed by the text graph model to generate a second reference graph having a special effect style represented by the first prompt word;

[0076] Step S2022: When the configuration parameters do not include the first prompt word, the first reference image is configured as the second reference image.

[0077] Step S2023: Process the facial image and the second reference image through the face-changing model to replace the facial features of the target object in the second reference image with the facial features corresponding to the facial image, thereby generating an effect image of the custom special effect.

[0078] Exemplarily, when the configuration parameters include the first prompt word, that is, the configuration parameters are only the first prompt word, or when the configuration parameters are the first prompt word and the first reference image, the configuration parameters are processed by calling the Wensheng graph model to generate a second reference image with a special effect style represented by the first prompt word. Specifically, the Wensheng graph model is a neural network model that generates a corresponding image based on the input description text. The Wensheng graph model can generate a corresponding image using only the content described by the first prompt word, or using the content described by the first prompt word and the content in the first reference image at the same time. The training process and implementation principle of the Wensheng graph model are prior art and will not be described here. In another possible case, when the configuration parameters do not include the first prompt word, that is, when the configuration parameters only include the first reference image, the first reference image can be directly used as the second reference image to perform subsequent steps, that is, the first reference image is configured as the second reference image.

[0079] After the second reference image is generated, since the portrait parameter is the first parameter value, that is, a low degree of freedom special effect, the facial features are replaced with the user's personalized image only on the basis of the second reference image to generate a custom special effect effect image. This process can be achieved through a pre-trained face-changing model, that is, the face-changing model processes the facial image and the second reference image to replace the facial features of the target object in the second reference image with the facial features corresponding to the facial image, and generates a custom special effect effect image, wherein the specific implementation principle and training process of the face-changing model are not repeated here.

[0080] Figure 7 A schematic diagram of a special effect template generation and consumption process when special effect generation data includes portrait parameters provided by an embodiment of the present disclosure, such as Figure 7As shown, first, in the special effect template generation stage, the special effect generation data includes configuration parameters para_0 and portrait parameters para_1, and the parameter value of the portrait parameter para_1 is the first parameter value (shown as para_1=1 in the figure). Based on the specific situation of the configuration parameters in the above special effect generation data, when the configuration parameter para_0 only includes the first reference image, the second reference image is directly generated based on the first reference image; when the configuration parameter para_0 includes the first prompt word, or includes the first prompt word and the first reference image, the second reference image is generated through the Wensheng graph model. After that, the second reference image is used as the construction data, and the second reference image and the user's personalized image are input into the face-changing model. After being processed by the face-changing model, the effect image is output. After that, the effect image, the second reference image (the construction data corresponding to the effect image), and other data required to generate the special effect template are packaged to generate the special effect template #1. Furthermore, after the special effects template #1 is released, in the special effects template consumption stage, the user calls the special effects template #1 and inputs the initial image. After being processed by the special effects template, the corresponding functional model is called using the model identifier recorded in the template calling parameters of the special effects template #1. Specifically, by calling the face-changing model and processing the second reference image and the initial image, the special effects image corresponding to the special effects template #1 is generated.

[0081] In this embodiment, a scheme for generating portrait special effects templates with low degrees of freedom is implemented. The generated special effects templates can restore the user's design intent and achieve accurate portrait special effects. With the help of AI model generation, the production process is simple. The user only needs to input the special effects generation data without manual drawing, thereby effectively improving the generation efficiency of the special effects templates.

[0082] Step S203: when the portrait parameter is a portrait parameter and the parameter value of the portrait parameter is a second parameter value, the image is redrawn according to the configuration parameter and the user personalized image to generate an effect image of the customized special effect.

[0083] Exemplarily, in another possible case, the portrait parameter is the second parameter value, and the second parameter value represents a high degree of freedom special effect, that is, the special effect images generated multiple times by the custom special effect template are not the same, that is, they have low consistency. In the steps of this embodiment, when the portrait parameter is the second parameter value, the image is directly redrawn according to the configuration parameters and the user's personalized image, and the effect map of the custom special effect is regenerated. The effect map generated by the above method directly uses the configuration parameters as construction data, so that the generated effect map has randomness, thereby making the special effect image generated by the special effect template have better diversity.

[0084] Specifically, in a possible implementation, the specific implementation of step S203 includes:

[0085] Step S2031: When the configuration parameters include the first prompt word, the configuration parameters and the user personalized image are processed by the text graph model to generate a rendering having the special effect style represented by the first prompt word and the image content features represented by the user personalized image.

[0086] Step S2032: When the configuration parameters do not include the first prompt word, the first reference image is processed by the image generation model to generate a third reference image, and the user personalized image and the third reference image are processed by the face-changing model to generate an effect image, wherein the third reference image adds random facial features relative to the first reference image.

[0087] Exemplarily, when the portrait parameter is the second parameter value, different generation links are executed according to the specific situation of the configuration parameters. Specifically, when the configuration parameters include the first prompt word, for example, only the first prompt word, or the first prompt word and the first reference image, the configuration parameters and the user personalized image are processed by the text-generated image model to generate a rendering with the special effect style represented by the first prompt word and the image content features represented by the user personalized image. When the configuration parameters do not include the first prompt word, that is, when the configuration parameters only include the first reference image, the first reference image is processed by the image-generated image model to generate a third reference image, that is, the image-generated image model is used to extract features of the content special effects of the first reference image and reversely redraw it, so that the third reference image adds random facial features relative to the first reference image. Then, the face-changing model is used to combine the user personalized image to perform face-changing and generate a rendering.

[0088] Figure 8 A schematic diagram of a special effect template generation and consumption process when another special effect generation data includes portrait parameters provided by an embodiment of the present disclosure, combined with Figure 8 The above process is introduced as follows: Figure 8As shown, first, in the special effect template generation stage, the special effect generation data includes configuration parameters para_0 and portrait parameters para_1, and the parameter value of the portrait parameter para_1 is the second parameter value (shown as para_1=2 in the figure). Based on the specific situation of the configuration parameters in the above special effect generation data, when the configuration parameter para_0 only includes the first reference image, the first reference image is first processed by the image generation model to generate the third reference image, and the user personalized image and the third reference image are processed by the face-changing model to generate the effect image. When the configuration parameter para_0 includes the first prompt word, or includes the first prompt word and the first reference image, the configuration parameter para_0 and the user personalized image are processed by the text generation model to generate the effect image. After that, the effect image, the configuration data para_0 (the construction data corresponding to the effect image), and other data required to generate the special effect template are packaged to generate the special effect template #2. Afterwards, in the special effects template consumption stage, the user calls the special effects template #2 and inputs the initial image. After being processed by the special effects template, the corresponding functional model is called using the model identifier recorded in the template calling parameters of the special effects template. Specifically, when the configuration data para_0 contains the first prompt word, the text-generated image model is called to process the first prompt word in combination with the initial image, or the first prompt word and the first reference image to generate the special effects image corresponding to the special effects template #1; when the configuration data para_0 only contains the first reference image, the image-generated image model and the face-changing model are called to process the first prompt word in combination with the initial image to generate the special effects image corresponding to the special effects template #1.

[0089] In this embodiment, a high-freedom portrait special effects template generation scheme is implemented. The generated special effects template can add certain random features on the basis of restoring the user's design intent, thereby improving the diversity of special effects images. With the help of AI model generation, the production process is simple. The user only needs to input the special effects generation data without manual drawing, thereby effectively improving the generation efficiency of special effects templates.

[0090] Step S204: If the special effect generation data includes stylized parameters, a target stylized model is determined according to the configuration parameters.

[0091] Step S205: Process the configuration parameters and the user's personalized image through the target stylized model to generate a rendering of the customized special effect.

[0092] In the steps of this embodiment, the special effect generation data includes stylized parameters, which are used to characterize the image style of the special effect image generated by the custom special effect template. When the special effect generation data includes stylized parameters, firstly, according to the configuration parameters, a target stylized model matching it is determined, and then the configuration parameters are processed based on the target stylized model, and combined with the user's personalized image, the effect image of the custom special effect is generated.

[0093] Exemplarily, the specific implementation of step S204 includes:

[0094] Step S2041: when the configuration parameters include the first reference image, determining that the target stylization model is a style transfer model, the style transfer model is used to perform image style transfer based on the first reference image to generate an effect image having image style features corresponding to the first reference image and image content features of the user personalized image;

[0095] Step S2042: When the configuration parameters do not include the first reference image, determine that the target stylization model is a style generation model, and the style generation model is used to generate an image based on the first prompt word to generate a rendering having the image style features described by the first prompt word and the image content features of the user personalized image.

[0096] Exemplarily, when the configuration parameters include the first reference image, that is, when the configuration parameters only include the first parameter image, or when the configuration parameters include the first parameter image and the first prompt word, image style transfer is performed based on the first parameter image, so that the target stylization model is determined to be a style transfer model. After processing the first reference image and the user personalized image based on the style transfer model, the image style of the first reference image can be transferred to the user personalized image, so that the user personalized image has the image style of the first reference image. When the configuration parameters do not include the first reference image, it is necessary to determine the image style with the help of the content described by the first prompt word, and then generate a stylized image. In this case, the target stylization model is determined to be a style generation model. The style generation model is used to generate an image based on the first prompt word to generate an effect image having the image style features described by the first prompt word and the image content features of the user personalized image. The style generation model can directly use the content described by the first prompt word to add a corresponding image style to the user personalized image, or it can further combine the first reference image, combine the first prompt word and the content of the first reference image, and add a corresponding image style to the user personalized image, so as to generate an effect image. In the case where the special effect generation data includes stylization parameters, the construction data is a configuration parameter.

[0097] Fig. 9 A schematic diagram of a special effect template generation and consumption process when special effect generation data includes stylized parameters provided by an embodiment of the present disclosure, combined with Fig. 9The above process is introduced as follows: Fig. 9 As shown, first, in the special effect template generation stage, the special effect generation data includes configuration parameters para_0 and stylization parameters para_2. Based on the specific conditions of the configuration parameters in the above special effect generation data, when the configuration parameter para_0 only includes the first prompt word, the first prompt word and the user personalized image are directly processed by the style generation model to generate the effect graph. When the configuration parameter para_0 includes the first reference image, or includes the first prompt word and the first reference image, the configuration parameter para_0 and the user personalized image are processed by the style transfer model to generate the effect graph. After that, the effect graph, the configuration data para_0 (the construction data corresponding to the effect graph), and other data required to generate the special effect template are packaged to generate the special effect template #3. Furthermore, in the consumption stage of the special effect template, the user calls the special effect template #3 and inputs the initial image. After being processed by the special effect template #3, the corresponding functional model is called using the model identifier recorded in the template calling parameters of the special effect template #3. Specifically, when the configuration data para_0 includes the first reference image, the style transfer model is called to process the first reference image in combination with the initial image, or the first prompt word and the first reference image to generate a special effect image corresponding to the special effect template #3; when the configuration data para_0 only includes the first prompt image, the style generation model is called to process the first prompt word and the initial image to generate a special effect image corresponding to the special effect template #1.

[0098] Step S206: If the special effect generation data includes background parameters, a target background replacement model is determined according to the configuration parameters.

[0099] Step S207: The configuration parameters and the user personalized image are processed by the target background replacement model to generate a rendering of the customized special effect.

[0100] Similarly, in the steps of this embodiment, the special effect generation data includes background parameters, and the background parameters are used to characterize the image background of the special effect image generated by the custom special effect template. When the special effect generation data includes background parameters, firstly, according to the configuration parameters, a target background replacement model matching therewith is determined, and then the configuration parameters are processed based on the target background replacement model, and combined with the user's personalized image, a rendering of the custom special effect is generated.

[0101] Exemplarily, the specific implementation of step S206 includes:

[0102] Step S2061: when the configuration parameters include a first reference image, determining that the target background replacement model is a pad background replacement model, the pad background replacement model is used to generate a first virtual background image based on the first reference image, and replace the background image of the user personalized image with the first virtual background image;

[0103] Step S2062: When the configuration parameters do not include the first reference image, determine that the target background replacement model is a prompt word background replacement model, the prompt word background replacement model is used to generate a second virtual background image based on the first prompt word, and replace the background image of the user personalized image with the second virtual background image.

[0104] Exemplarily, in the case where the special effect generation data includes background parameters, it is necessary to determine the function model that matches it based on the configuration parameters, and then realize the processing of the configuration parameters. Specifically, when the configuration parameters include the first reference image, that is, when the configuration parameters only include the first parameter image, or when the configuration parameters include the first parameter image and the first prompt word, the pad image background replacement is performed based on the first parameter image, so the target background replacement model is determined to be the pad image background replacement model. After processing the first reference image and the user personalized image based on the pad image background replacement model, the background of the first reference image can be replaced into the user personalized image, thereby achieving the effect of changing the image background of the user personalized image. In this implementation, the consistency of the image background can be guaranteed. When the configuration parameters do not include the first reference image, it is necessary to determine the image background with the help of the content described by the first prompt word, and then perform the image background replacement. In this case, the target background replacement model is determined to be the prompt word background replacement model. The prompt word background replacement model is an image generation model, which is used to generate a background image based on a first prompt word, or to generate a background image based on the first prompt word and a first reference image, and then combine the user's personalized image to fuse the objects in the user's personalized image into the background image, and generate a rendering with the image style characteristics described by the first prompt word and the image content characteristics of the user's personalized image. In the case where the special effect generation data includes background parameters, the construction data is a configuration parameter. The processing chain for generating special effect templates and consuming special effects in this case is similar to the processing chain for generating special effect templates and consuming special effects when the special effect generation data includes stylized parameters. The difference is that the functional models used are different. The processing chain will not be described here in detail. Please refer to Fig. 9 The link process in the illustrated embodiment.

[0105] Step S208: In response to the second operation, the rendering and the construction data corresponding to the rendering are packaged to generate a special effects template for the custom special effects, wherein the rendering is used to display the visual effects of the custom special effects based on the user's personalized image on the resource platform, and after being called, the special effects template generates the corresponding special effects image through the construction data.

[0106] In this embodiment, the implementation of step S201 and step S208 is the same as that of the present disclosure. Figure 2 The implementation methods of step S101 and step S103 in the illustrated embodiment are the same and will not be described in detail here.

[0107] Corresponding to the special effect template generation method of the above embodiment, Fig.10 A structural block diagram of a special effect template generation device provided in an embodiment of the present disclosure. The method described in the above embodiment can be executed by the special effect template generation device, which can be implemented by software and / or hardware, and can be integrated in an electronic device with certain data processing functions. Among them, the electronic device can include but is not limited to mobile terminals with big data processing capabilities, as well as fixed terminals with big data processing capabilities such as desktop computers and supercomputers.

[0108] For the sake of convenience, only the parts related to the embodiments of the present disclosure are shown. Fig.10 , the special effect template generating device 3 comprises:

[0109] An acquisition module 31 is used to obtain special effect generation data in response to a first operation, wherein the special effect generation data includes configuration parameters representing a special effect style of a custom special effect, and the configuration parameters include a first prompt word and / or a first reference image;

[0110] A generating module 32, configured to display an effect diagram of the customized special effect according to the special effect generating data and the user personalized image;

[0111] The packaging module 33 is used to package the renderings and the construction data corresponding to the renderings in response to the second operation, and generate a special effects template for the custom special effects, wherein the renderings are used to display the visual effects of the custom special effects based on the user's personalized images on the resource platform, and after being called, the special effects template generates the corresponding special effects image through the construction data.

[0112] According to one or more embodiments of the present disclosure, the special effect generation data includes portrait parameters, and the parameter values ​​of the portrait parameters are used to characterize the consistency between special effect images generated multiple times by a custom special effect template; the generation module 32 is specifically used to: when the portrait parameter is a first parameter value, generate a second reference image according to the configuration parameters, and merge the user's personalized image into the second reference image to display the effect image of the custom special effect; when the portrait parameter is a second parameter value, redraw the image according to the configuration parameters and the user's personalized image to display the effect image of the custom special effect.

[0113] According to one or more embodiments of the present disclosure, when the generation module 32 generates the second reference image according to the configuration parameters, it is specifically used to: when the configuration parameters include the first prompt word, process the configuration parameters through the text graph model to generate a second reference image with a special effect style represented by the first prompt word; when the configuration parameters do not include the first prompt word, configure the first reference image as the second reference image.

[0114] According to one or more embodiments of the present disclosure, the user personalized image includes a facial image; when the generation module 32 fuses the user personalized image into the second reference image and displays the effect image of the custom special effect, it is specifically used to: process the facial image and the second reference image through a face-changing model to replace the facial features of the target object in the second reference image with the facial features corresponding to the facial image, and display the effect image of the custom special effect.

[0115] According to one or more embodiments of the present disclosure, when the generation module 32 redraws the image according to the configuration parameters and the user personalized image to display the effect diagram of the custom special effect, it is specifically used to: when the configuration parameters include a first prompt word, process the configuration parameters and the user personalized image through the text-generated image model to generate a rendering having the special effect style represented by the first prompt word and the image content characteristics represented by the user personalized image; when the configuration parameters do not include the first prompt word, process the first reference image through the text-generated image model to generate a third reference image, and process the user personalized image and the third reference image through the face-changing model to generate a rendering, wherein the third reference image adds random facial features relative to the first reference image.

[0116] According to one or more embodiments of the present disclosure, the special effect generation data includes stylization parameters, and the stylization parameters are used to characterize the image style of the special effect image generated by the custom special effect template; the generation module 32 is specifically used to: if the special effect generation data includes stylization parameters, determine the target stylization model according to the configuration parameters; process the configuration parameters and the user personalized image through the target stylization model, and display the effect diagram of the custom special effect.

[0117] According to one or more embodiments of the present disclosure, when the generation module 32 determines the target stylization model according to the configuration parameters, it is specifically used to: when the configuration parameters include a first reference image, determine that the target stylization model is a style transfer model, and the style transfer model is used to perform image style transfer based on the first reference image, so as to generate a rendering having image style features corresponding to the first reference image and image content features of the user personalized image; when the configuration parameters do not include the first reference image, determine that the target stylization model is a style generation model, and the style generation model is used to perform image generation based on the first prompt word, so as to generate a rendering having image style features described by the first prompt word and image content features of the user personalized image.

[0118] According to one or more embodiments of the present disclosure, the special effect generation data includes background parameters, and the background parameters are used to characterize the image background of the special effect image generated by the custom special effect template; the generation module 32 is specifically used to: if the special effect generation data includes background parameters, determine the target background replacement model according to the configuration parameters; process the configuration parameters and the user personalized image through the target background replacement model, and display the effect diagram of the custom special effect.

[0119] According to one or more embodiments of the present disclosure, when the generation module 32 determines the target background replacement model according to the special effects generation data, it is specifically used to: when the configuration parameters include a first reference image, determine that the target background replacement model is a pad background replacement model, and the pad background replacement model is used to generate a first virtual background image based on the first reference image, and replace the background image of the user's personalized image with the first virtual background image; when the configuration parameters do not include the first reference image, determine that the target background replacement model is a prompt word background replacement model, and the prompt word background replacement model is used to generate a second virtual background image based on the first prompt word, and replace the background image of the user's personalized image with the second virtual background image.

[0120] According to one or more embodiments of the present disclosure, the special effect generation data includes special effect type parameters, and the special effect type parameters include one of the following: portrait parameters, stylization parameters, and background parameters; the packaging module 33 is specifically used to package the rendering and the construction data corresponding to the rendering, and generate a special effect template for the custom special effect, including: determining the corresponding model identifier according to the construction data and special effect type parameters of the rendering; packaging the construction data, special effect type parameters and the corresponding model identifier into a template calling parameter, the template calling parameter is used to call the corresponding processing model to generate a special effect image when calling the special effect template based on the construction data and the special effect type parameters; encapsulating the template calling parameters and the rendering to generate a special effect template.

[0121] The acquisition module 31, the generation module 32 and the packaging module 33 are connected in sequence. The special effect template generation device 3 provided in this embodiment can implement the technical solution of the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated in this embodiment.

[0122] Fig.11 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown in FIG. Fig.11 As shown, the electronic device 4 includes:

[0123] A processor 41, and a memory 42 communicatively connected to the processor 41;

[0124] The memory 42 stores computer executable instructions;

[0125] The processor 41 executes the computer execution instructions stored in the memory 42 to implement the following Figure 2-Figure 9 The special effect template generation method in the illustrated embodiment.

[0126] Optionally, the processor 41 and the memory 42 are connected via a bus 43 .

[0127] For related instructions, please refer to Figure 2-Figure 9The relevant descriptions and effects corresponding to the steps in the corresponding embodiments can be understood, and no further elaboration is made here.

[0128] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, which are used to implement the present invention when executed by a processor. Figure 2-Figure 9 A special effects template generation method provided in any one of the corresponding embodiments.

[0129] The present invention provides a computer program product, including a computer program. When the computer program is executed by a processor, the present invention is realized. Figure 2-Figure 9 A special effects template generation method provided in any one of the corresponding embodiments.

[0130] In order to implement the above embodiment, the embodiment of the present disclosure also provides an electronic device.

[0131] refer to Fig.12 , which shows a schematic diagram of the structure of an electronic device 900 suitable for implementing the embodiment of the present disclosure, and the electronic device 900 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.12 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0132] like Fig.12 As shown, the electronic device 900 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 to a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0133] Typically, the following devices may be connected to the I / O interface 905: input devices 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 908 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.12 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0134] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 909, or installed from a storage device 908, or installed from a ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0135] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0136] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0137] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0138] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0139] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each 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 implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0140] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit or module does not, in some cases, constitute a limitation on the unit itself.

[0141] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may 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.

[0142] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0143] In a first aspect, according to one or more embodiments of the present disclosure, a method for generating a special effect template is provided, comprising:

[0144] In response to a first operation, special effect generation data is obtained, wherein the special effect generation data includes configuration parameters of a special effect style characterizing a custom special effect, wherein the configuration parameters include a first prompt word and / or a first reference image; a rendering of the custom special effect is displayed according to the special effect generation data and a user personalized image; in response to a second operation, the rendering and construction data corresponding to the rendering are packaged to generate a special effect template of the custom special effect, wherein the rendering is used to display the visual effect of the custom special effect based on the user personalized image on a resource platform, and after the special effect template is called, the corresponding special effect image is generated through the construction data.

[0145] According to one or more embodiments of the present disclosure, the special effect generation data includes portrait parameters, and the parameter value of the portrait parameter is used to characterize the consistency between the special effect images generated multiple times by the custom special effect template; the display of the effect graph of the custom special effect based on the special effect generation data and the user personalized image includes: when the portrait parameter is a first parameter value, generating a second reference image according to the configuration parameters, and fusing the user personalized image into the second reference image to display the effect graph of the custom special effect; when the portrait parameter is a second parameter value, redrawing the image according to the configuration parameters and the user personalized image to display the effect graph of the custom special effect.

[0146] According to one or more embodiments of the present disclosure, generating a second reference image based on the configuration parameters includes: when the configuration parameters include the first prompt word, processing the configuration parameters through a text graph model to generate a second reference image having a special effect style represented by the first prompt word; when the configuration parameters do not include the first prompt word, configuring the first reference image as a second reference image.

[0147] According to one or more embodiments of the present disclosure, the user personalized image includes a facial image; the fusing of the user personalized image into the second reference image to display the effect image of the custom special effect includes: processing the facial image and the second reference image through a face-changing model to replace the facial features of the target object in the second reference image with the facial features corresponding to the facial image, and displaying the effect image of the custom special effect.

[0148] According to one or more embodiments of the present disclosure, the image redrawing according to the configuration parameters and the user personalized image to display the effect graph of the custom special effect includes: when the configuration parameters include the first prompt word, processing the configuration parameters and the user personalized image through a text-generated graph model to generate a rendering having a special effect style represented by the first prompt word and image content features represented by the user personalized image; when the configuration parameters do not include the first prompt word, processing the first reference image through a text-generated graph model to generate a third reference image, and processing the user personalized image and the third reference image through a face-changing model to generate the rendering, wherein the third reference image adds random facial features relative to the first reference image.

[0149] According to one or more embodiments of the present disclosure, the special effect generation data includes stylization parameters, and the stylization parameters are used to characterize the image style of the special effect image generated by the custom special effect template; the displaying the effect graph of the custom special effect according to the special effect generation data and the user personalized image includes: if the special effect generation data includes the stylization parameters, determining the target stylization model according to the configuration parameters; processing the configuration parameters and the user personalized image through the target stylization model, and displaying the effect graph of the custom special effect.

[0150] According to one or more embodiments of the present disclosure, determining the target stylization model according to the configuration parameters includes: when the configuration parameters include the first reference image, determining the target stylization model as a style transfer model, the style transfer model being used to perform image style transfer based on the first reference image, so as to generate a rendering having image style features corresponding to the first reference image and image content features of the user personalized image; when the configuration parameters do not include the first reference image, determining the target stylization model as a style generation model, the style generation model being used to perform image generation based on the first prompt word, so as to generate a rendering having image style features described by the first prompt word and image content features of the user personalized image.

[0151] According to one or more embodiments of the present disclosure, the special effect generation data includes background parameters, and the background parameters are used to characterize the image background of the special effect image generated by the custom special effect template; the displaying the effect diagram of the custom special effect according to the special effect generation data and the user personalized image includes: if the special effect generation data includes the background parameters, determining the target background replacement model according to the configuration parameters; processing the configuration parameters and the user personalized image through the target background replacement model to display the effect diagram of the custom special effect.

[0152] According to one or more embodiments of the present disclosure, determining a target background replacement model based on the special effects generation data includes: when the configuration parameters include the first reference image, determining that the target background replacement model is a pad background replacement model, the pad background replacement model is used to generate a first virtual background image based on the first reference image, and replace the background image of the user personalized image with the first virtual background image; when the configuration parameters do not include the first reference image, determining that the target background replacement model is a prompt word background replacement model, the prompt word background replacement model is used to generate a second virtual background image based on the first prompt word, and replace the background image of the user personalized image with the second virtual background image.

[0153] According to one or more embodiments of the present disclosure, the special effect generation data includes special effect type parameters, and the special effect type parameters include one of the following: portrait parameters, stylization parameters, and background parameters; the packaging of the effect graph and the construction data corresponding to the effect graph to generate the special effect template of the custom special effect includes: determining the corresponding model identifier according to the construction data of the effect graph and the special effect type parameters; packaging the construction data, the special effect type parameters and the corresponding model identifier into a template calling parameter, and the template calling parameter is used to call the corresponding processing model to generate the special effect image when calling the special effect template based on the construction data and the special effect type parameters; encapsulating the template calling parameters and the effect graph to generate the special effect template.

[0154] In a second aspect, according to one or more embodiments of the present disclosure, a special effect template generation device is provided, comprising:

[0155] An acquisition module, configured to obtain special effect generation data in response to a first operation, wherein the special effect generation data includes configuration parameters representing a special effect style of a custom special effect, wherein the configuration parameters include a first prompt word and / or a first reference image;

[0156] A generation module, used to generate data for the special effect and a user-personalized image, and display an effect diagram of the custom special effect;

[0157] A packaging module is used to package the rendering and the construction data corresponding to the rendering in response to the second operation, and generate a special effect template for the custom special effect, wherein the rendering is used to display the visual effect of the custom special effect based on the user's personalized image on the resource platform, and after being called, the special effect template generates a corresponding special effect image through the construction data.

[0158] According to one or more embodiments of the present disclosure, the special effect generation data includes portrait parameters, and the parameter value of the portrait parameter is used to characterize the consistency between the special effect images generated multiple times by the custom special effect template; the generation module is specifically used to: when the portrait parameter is a first parameter value, generate a second reference image according to the configuration parameters, and merge the user personalized image into the second reference image to display the effect image of the custom special effect; when the portrait parameter is a second parameter value, redraw the image according to the configuration parameters and the user personalized image, and display the effect image of the custom special effect.

[0159] According to one or more embodiments of the present disclosure, when the generation module generates the second reference image according to the configuration parameters, it is specifically used to: when the configuration parameters include the first prompt word, process the configuration parameters through the text graph model to generate a second reference image with a special effect style represented by the first prompt word; when the configuration parameters do not include the first prompt word, configure the first reference image as the second reference image.

[0160] According to one or more embodiments of the present disclosure, the user personalized image includes a facial image; when the generation module fuses the user personalized image into the second reference image and displays the effect image of the custom special effect, it is specifically used to: process the facial image and the second reference image through a face-changing model to replace the facial features of the target object in the second reference image with the facial features corresponding to the facial image, and display the effect image of the custom special effect.

[0161] According to one or more embodiments of the present disclosure, when the generation module redraws the image according to the configuration parameters and the user personalized image to display the effect diagram of the custom special effect, it is specifically used to: when the configuration parameters include the first prompt word, process the configuration parameters and the user personalized image through the text-generated graph model to generate a rendering having the special effect style represented by the first prompt word and the image content characteristics represented by the user personalized image; when the configuration parameters do not include the first prompt word, process the first reference image through the text-generated graph model to generate a third reference image, and process the user personalized image and the third reference image through the face-changing model to generate the rendering, wherein the third reference image adds random facial features relative to the first reference image.

[0162] According to one or more embodiments of the present disclosure, the special effect generation data includes stylization parameters, and the stylization parameters are used to characterize the image style of the special effect image generated by the custom special effect template; the generation module is specifically used to: if the special effect generation data includes the stylization parameters, determine the target stylization model according to the configuration parameters; process the configuration parameters and the user personalized image through the target stylization model, and display the effect diagram of the custom special effect.

[0163] According to one or more embodiments of the present disclosure, when the generation module determines the target stylization model according to the configuration parameters, it is specifically used to: when the configuration parameters include the first reference image, determine that the target stylization model is a style transfer model, and the style transfer model is used to perform image style transfer based on the first reference image to generate a rendering having image style features corresponding to the first reference image and image content features of the user personalized image; when the configuration parameters do not include the first reference image, determine that the target stylization model is a style generation model, and the style generation model is used to perform image generation based on the first prompt word to generate a rendering having image style features described by the first prompt word and image content features of the user personalized image.

[0164] According to one or more embodiments of the present disclosure, the special effect generation data includes background parameters, and the background parameters are used to characterize the image background of the special effect image generated by the custom special effect template; the generation module is specifically used to: if the special effect generation data includes the background parameters, determine the target background replacement model according to the configuration parameters; process the configuration parameters and the user personalized image through the target background replacement model, and display the effect diagram of the custom special effect.

[0165] According to one or more embodiments of the present disclosure, when the generation module determines the target background replacement model according to the special effects generation data, it is specifically used to: when the configuration parameters include the first reference image, determine that the target background replacement model is a pad background replacement model, and the pad background replacement model is used to generate a first virtual background image based on the first reference image, and replace the background image of the user personalized image with the first virtual background image; when the configuration parameters do not include the first reference image, determine that the target background replacement model is a prompt word background replacement model, and the prompt word background replacement model is used to generate a second virtual background image based on the first prompt word, and replace the background image of the user personalized image with the second virtual background image.

[0166] According to one or more embodiments of the present disclosure, the special effect generation data includes special effect type parameters, and the special effect type parameters include one of the following: portrait parameters, stylization parameters, and background parameters; the packaging module is specifically used to package the effect graph and the construction data corresponding to the effect graph, and generate a special effect template for the custom special effect, including: determining the corresponding model identifier according to the construction data of the effect graph and the special effect type parameters; packaging the construction data, the special effect type parameters and the corresponding model identifier into a template calling parameter, and the template calling parameter is used to call the corresponding processing model to generate the special effect image when calling the special effect template based on the construction data and the special effect type parameters; encapsulating the template calling parameters and the effect graph to generate the special effect template.

[0167] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0168] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0169] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for generating a special effect template, characterized in that: include: In response to the first operation, special effect generation data is obtained, wherein the special effect generation data includes configuration parameters representing a special effect style of the custom special effect, and the configuration parameters include a first prompt word and / or a first reference image; Displaying an effect diagram of the customized special effect according to the special effect generation data and the user personalized image; In response to the second operation, the rendering and the construction data corresponding to the rendering are packaged to generate a special effects template for the custom special effect, wherein the rendering is used to display the visual effect of the custom special effect based on the user's personalized image on the resource platform, and after being called, the special effects template generates a corresponding special effects image through the construction data.

2. The method according to claim 1, characterized in that The first operation includes a first sub-operation, a second sub-operation and a third sub-operation, and the obtaining of special effect generation data in response to the first operation includes: In response to the first sub-operation, the first reference image is imported, and a special effect template control is displayed; In response to a second sub-operation on the special effect template control, displaying a template operation item, wherein the template operation item is used to load a created special effect template or to create a new special effect template; In response to the third sub-operation for the template operation item, receiving the first prompt word input by the user, or loading the original configuration parameters in the created special effect template; The special effect generation data is generated based on the first reference image and the first prompt word; or, the special effect generation data is generated based on the original configuration parameters.

3. The method according to claim 2, characterized in that The first prompt word at least includes a first description word and a second description word, and the first prompt word received from the user includes: Receive a first description participle input by a user; According to the first description participle, a second description participle corresponding to the first description participle is generated and displayed, wherein the second description participle and the first description participle respectively describe the characteristics of the special effect style in different characteristic dimensions; The first prompt word is generated according to the first description participle and the second description participle.

4. The method according to claim 2, characterized in that: The original configuration parameters also include effect parameters, which are used to characterize special effect display parameters corresponding to the special effect image generated based on the created special effect template, wherein the special effect display parameters include at least one of the following: canvas ratio, style strength, and background change enable; The generating the special effect generation data based on the original configuration parameters includes: generating edited configuration parameters in response to a third operation on the original configuration parameters, wherein the third operation is used to modify the first prompt word and / or the first reference image and / or the effect parameter in the original configuration parameters; The special effect generation data is generated based on the edited configuration parameters.

5. The method according to claim 2, characterized in that: After generating the special effect template of the custom special effect, the method further includes: Add the special effect template of the custom special effect to the special effect template control to generate a template operation item corresponding to the custom special effect.

6. The method according to claim 1, characterized in that The special effect generation data includes an image parameter, and the parameter value of the image parameter is used to characterize the consistency between the special effect images generated multiple times by the custom special effect template; The step of displaying the effect diagram of the customized special effect according to the special effect generation data and the user personalized image comprises: When the portrait parameter is the first parameter value, a second reference image is generated according to the configuration parameter, and the user personalized image is merged into the second reference image to display the effect image of the custom special effect; When the portrait parameter is a second parameter value, the image is redrawn according to the configuration parameters and the user personalized image to display the effect diagram of the custom special effect.

7. The method according to claim 6, characterized in that Generating a second reference graph according to the configuration parameters includes: When the configuration parameters include the first prompt word, the configuration parameters are processed by a text graph model to generate a second reference graph having a special effect style represented by the first prompt word; When the configuration parameters do not include the first prompt word, the first reference image is configured as a second reference image.

8. The method according to claim 7, characterized in that The user personalized image includes a facial image; the step of fusing the user personalized image to the second reference image to display an effect image of the custom special effect includes: The facial image and the second reference image are processed by a face-changing model to replace the facial features of the target object in the second reference image with the facial features corresponding to the facial image, and an effect image of the custom special effect is displayed.

9. The method according to claim 6, characterized in that The step of redrawing the image according to the configuration parameters and the user personalized image to display the effect diagram of the custom special effect includes: When the configuration parameters include the first prompt word, the configuration parameters and the user personalized image are processed by a text graph model to generate a rendering having a special effect style represented by the first prompt word and an image content feature represented by the user personalized image; When the configuration parameters do not include the first prompt word, the first reference image is processed by a graph-generated image model to generate a third reference image, and the user personalized image and the third reference image are processed by a face-changing model to generate the effect image, wherein the third reference image adds random facial features relative to the first reference image.

10. The method according to claim 1, characterized in that The special effect generation data includes stylized parameters, and the stylized parameters are used to characterize the image style of the special effect image generated by the custom special effect template; The step of displaying the effect diagram of the customized special effect according to the special effect generation data and the user personalized image comprises: If the special effect generation data includes the stylization parameters, determining a target stylization model according to the configuration parameters; The configuration parameters and the user-personalized image are processed by the target stylization model to display an effect diagram of the custom special effect.

11. The method according to claim 10, characterized in that Determining a target stylized model according to the configuration parameters includes: When the configuration parameters include the first reference image, determining that the target stylization model is a style transfer model, the style transfer model is used to perform image style transfer based on the first reference image to generate an effect image having image style features corresponding to the first reference image and image content features of the user personalized image; When the configuration parameters do not include the first reference image, the target stylization model is determined to be a style generation model, and the style generation model is used to generate an image based on the first prompt word to generate a rendering having the image style characteristics described by the first prompt word and the image content characteristics of the user personalized image.

12. The method according to claim 1, characterized in that The special effect generation data includes background parameters, and the background parameters are used to characterize the image background of the special effect image generated by the custom special effect template; The step of displaying the effect diagram of the customized special effect according to the special effect generation data and the user personalized image comprises: If the special effect generation data includes the background parameters, determining a target background replacement model according to the configuration parameters; The configuration parameters and the user personalized image are processed by the target background replacement model to display an effect diagram of the customized special effect.

13. The method according to claim 12, characterized in that The step of determining a target background replacement model according to the special effect generation data includes: When the configuration parameters include the first reference image, determining that the target background replacement model is an underlay background replacement model, the underlay background replacement model is used to generate a first virtual background image based on the first reference image, and replace the background image of the user personalized image with the first virtual background image; When the configuration parameters do not include the first reference image, the target background replacement model is determined to be a prompt word background replacement model, and the prompt word background replacement model is used to generate a second virtual background image based on the first prompt word, and replace the background image of the user personalized image with the second virtual background image.

14. The method according to claim 1, characterized in that The special effect generation data includes a special effect type parameter, and the special effect type parameter includes one of the following: a portrait parameter, a stylization parameter, and a background parameter; The step of packaging the effect graph and the construction data corresponding to the effect graph to generate a special effect template of the custom special effect includes: Determine a corresponding model identifier according to the construction data of the effect diagram and the special effect type parameter; The construction data, the special effect type parameter and the corresponding model identifier are packaged into a template calling parameter, wherein the template calling parameter is used to call the corresponding processing model to generate the special effect image when the special effect template is called based on the construction data and the special effect type parameter; The template calling parameters and the effect diagram are encapsulated to generate the special effect template.

15. A special effect template generation device, characterized in that: include: An acquisition module, configured to obtain special effect generation data in response to a first operation, wherein the special effect generation data includes configuration parameters representing a special effect style of a custom special effect, wherein the configuration parameters include a first prompt word and / or a first reference image; A generation module, used to generate data for the special effect and a user-personalized image, and display an effect diagram of the custom special effect; A packaging module is used to package the rendering and the construction data corresponding to the rendering in response to the second operation, and generate a special effect template for the custom special effect, wherein the rendering is used to display the visual effect of the custom special effect based on the user's personalized image on the resource platform, and after being called, the special effect template generates a corresponding special effect image through the construction data.

16. An electronic device, characterized in that: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the special effect template generation method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the special effect template generation method according to any one of claims 1 to 14 is implemented.

18. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the special effect template generation method according to any one of claims 1 to 14 is implemented.

Images