Interaction method and device of multimedia generation page, electronic equipment and storage medium

Abstract

The invention relates to an interaction method and device for a multimedia generation page, electronic equipment and a storage medium. The method comprises the following steps: displaying a multimedia generation page, wherein a plurality of multimedia generation controls are displayed in the multimedia generation page; the multiple multimedia generation controls correspond to multiple multimedia generation modes; under the condition that a first multimedia generation control in the multiple multimedia generation controls is in a selected state, displaying first style information corresponding to a first style library configured in a first multimedia generation mode on the multimedia generation page; the first multimedia generation mode is a multimedia generation mode corresponding to the first multimedia generation control in the multiple multimedia generation modes. According to the technical scheme provided by the invention, the style expression in each generation scene can be more accurate, so that the multimedia resource generation efficiency and the multimedia resource generation quality in each generation scene can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer vision, and particularly relates to a multimedia generation page interaction method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the wide use of AIGC (Artificial Intelligence Generated Content), more and more applications provide functions of generating multimedia resources, such as image generation, video generation, and the like. In the related art, in order to guide a user to generate a style description of a multimedia resource, style prompt information for generating the multimedia resource is provided, but the style prompted by the style prompt information is generally fixed and single. This results in that the style prompt cannot meet the user demand, the interaction rate of the style prompt is low, thereby causing waste of display resources in multimedia resource generation; and the style expression in multimedia resource generation is not accurate enough, and the efficiency and quality of generating the multimedia resource are both poor. SUMMARY The present disclosure provides a multimedia generation page interaction method, device, electronic equipment and storage medium, so as to at least enable the style expression in each generation scene to be more accurate, thereby effectively improving the efficiency and quality of generating the multimedia resource in each generation scene. The technical solutions of the present disclosure are as follows: According to a first aspect of an embodiment of the present disclosure, a multimedia generation page interaction method is provided, comprising: displaying a multimedia generation page, wherein a plurality of multimedia generation controls are displayed in the multimedia generation page; the plurality of multimedia generation controls correspond to a plurality of multimedia generation modes; in a case where a first multimedia generation control in the plurality of multimedia generation controls is in a selected state, displaying first style information corresponding to a first style library configured in a first multimedia generation mode in the multimedia generation page; the first multimedia generation mode is a multimedia generation mode corresponding to the first multimedia generation control in the plurality of multimedia generation modes.

[0003] In a possible implementation manner, the method further comprises: in a case where a second multimedia generation control in the plurality of multimedia generation controls is in a selected state, switching the multimedia generation page to display second style information corresponding to a second style library configured in a second multimedia generation mode; the second multimedia generation mode is a multimedia generation mode corresponding to the second multimedia generation control in the plurality of multimedia generation modes; The first style information and the second style information are different in at least one of the following: different style categories, different display styles; and the first style library and the second style library are different in at least one of the following: different style categories, different display styles, and different style recommendation strategies.

[0004] In a possible implementation, the first style information corresponding to the first style library includes at least one style reference picture in the first style library, or style display entry information corresponding to the first style library; and the first style information corresponding to the first style library configured in the multimedia generation page displaying the first multimedia generation manner includes: displaying, in the multimedia generation page, at least one style reference picture in the first style library; or displaying, in the multimedia generation page, the style display entry information corresponding to the first style library.

[0005] In a possible implementation, the first style information includes a plurality of style classification labels and at least one style reference picture under a target style classification label; and the first style information corresponding to the first style library configured in the multimedia generation page displaying the first multimedia generation manner includes: displaying, in the multimedia generation page, the plurality of style classification labels corresponding to the first style library; displaying at least one style reference picture under the target style classification label; the target style classification label is one of the plurality of style classification labels.

[0006] In a possible implementation, the first multimedia generation manner includes a text-to-image manner, and the first style information includes style display entry information; and the first style information corresponding to the first style library configured in the multimedia generation page displaying the first multimedia generation manner includes: displaying, in the multimedia generation page, the style display entry information corresponding to the first style library; The method further includes: displaying, in the multimedia generation page, at least one style reference picture in the first style library in response to triggering of the style display entry information.

[0007] In a possible implementation, the first multimedia generation manner includes an image conversion manner, a video generation manner, or a reference text-to-image manner, and the first style information includes at least one style reference picture in the first style library; and the first style information corresponding to the first style library configured in the multimedia generation page displaying the first multimedia generation manner includes: displaying, in the multimedia generation page, at least one style reference picture in the first style library.

[0008] In a possible implementation, the first multimedia generation manner is the reference picture generation manner, and the reference picture generation manner comprises a multi-picture reference generation manner; and the method further comprises: exhibiting, on the multimedia generation page, a plurality of reference picture display areas corresponding to a plurality of reference picture types respectively; the plurality of reference picture types comprise a style reference picture type; exhibiting, on the multimedia generation page, at least one style reference picture in the first style library; and exhibiting, on the multimedia generation page, at least one style reference picture in the first style library in response to triggering of the reference picture display area corresponding to the style reference picture type.

[0009] In a possible implementation, the first multimedia generation manner is the reference picture generation manner or a video generation manner, and the method further comprises: exhibiting a role reference display area and a role library control; exhibiting a plurality of role reference pictures in a role library corresponding to the role library control in response to triggering of the role library control; exhibiting a target role reference picture in the role reference display area in a case where the target role reference picture is selected from the plurality of role reference pictures; the target role reference picture is used for role control of multimedia resource generation.

[0010] In a possible implementation, the exhibiting, on the multimedia generation page, at least one style reference picture in the first style library comprises: exhibiting at least one style reference picture in the first style library in a first style display style configured for the first style library; In a possible implementation, the at least one style reference picture in the first style library is obtained by screening from a plurality of style reference pictures in the first style library based on a first style recommendation policy configured for the first style library; the plurality of style reference pictures comprise a plurality of preset style reference pictures preconfigured for the first style library and / or a plurality of style reference pictures each corresponding to a style corresponding to a target account dynamically matched in the first multimedia generation manner; the target account is an account corresponding to the display multimedia generation page.

[0011] In a possible implementation, the first style recommendation policy configured for the first style library comprises at least one of the following: recommendation based on historical use style information of a target account in the first multimedia generation manner; or recommendation of long-tail styles with a statistical interaction frequency less than an interaction frequency threshold.

[0012] In a possible implementation, the multimedia generation page further exhibits a style description area; and the method further comprises: In response to the selection operation of the first style reference image, the first style description text corresponding to the first style reference image is automatically displayed in the style description area, and the first style reference image and at least one first associated style reference image associated with the first style reference image are displayed at the associated position of the first style description text. Wherein, the at least one first associated style reference map is used to select and switch the style of the generated multimedia resources; the first style reference map is one of the at least one style reference map.

[0013] In one possible implementation, the method further includes: In response to the selection of a second style reference image in the at least one first associated style reference image, the style description area is automatically switched to display second style description text corresponding to the second style reference image, and the second style reference image and at least one first associated style reference image associated with the second style reference image are displayed at the associated position of the second style description text.

[0014] In one possible implementation, the first style display style includes at least two style display styles corresponding to different display sizes; the step of displaying at least one style reference image from the first style library using the first style display style configured in the first style library includes: At least one style reference image from the first style library is displayed using the style display style corresponding to the target display size in the first style display style; the target display size is the display size matched to the target terminal, and the target terminal is the terminal that displays the multimedia generated page.

[0015] According to a second aspect of the present disclosure, an interactive device for generating multimedia pages is provided, comprising: The page display module is configured to display a multimedia generation page, which displays a variety of multimedia generation controls; the various multimedia generation controls correspond to a variety of multimedia generation methods. The style display module is configured to, when the first multimedia generation control among the multiple multimedia generation controls is selected, display the first style information corresponding to the first style library configured under the first multimedia generation method on the multimedia generation page; the first multimedia generation method is the multimedia generation method corresponding to the first multimedia generation control among the multiple multimedia generation methods.

[0016] In one possible implementation, the device further includes: The generation mode switching module is configured to execute the following: in a case where a second multimedia generation control in the plurality of multimedia generation controls is in a selected state, switching the multimedia generation page to display second style information corresponding to a second style library configured in a second multimedia generation mode; the second multimedia generation mode is a multimedia generation mode corresponding to the second multimedia generation control in the plurality of multimedia generation modes. The first style information and the second style information are different in at least one of the following: style categories and display styles. The first style library and the second style library are different in at least one of the following: style categories, display styles, and style recommendation strategies.

[0017] In a possible implementation, the first style information corresponding to the first style library includes at least one style reference picture in the first style library or style display entry information corresponding to the first style library. The style display module includes: The first display unit is configured to execute the following: displaying at least one style reference picture in the first style library on the multimedia generation page; or displaying the style display entry information corresponding to the first style library on the multimedia generation page.

[0018] In a possible implementation, the first style information includes a plurality of style classification labels and at least one style reference picture under a target style classification label. The style display module includes: The style classification label display unit is configured to execute the following: displaying the plurality of style classification labels corresponding to the first style library on the multimedia generation page. The style reference picture display unit is configured to execute the following: displaying at least one style reference picture under the target style classification label; the target style classification label is one of the plurality of style classification labels.

[0019] In a possible implementation, the first multimedia generation mode includes a text-to-image mode, and the first style information includes style display entry information. The style display module includes: The second display unit is configured to execute the following: displaying the style display entry information corresponding to the first style library on the multimedia generation page. The apparatus further includes: The style reference picture display module is configured to execute the following: in response to triggering of the style display entry information, displaying at least one style reference picture in the first style library on the multimedia generation page.

[0020] In a possible implementation, the first multimedia generation manner includes an image conversion manner, a video generation manner, or a reference image generation manner, and the first style information includes at least one style reference image in the first style library; and the style display module includes: A third display unit, configured to display at least one style reference image in the first style library on the multimedia generation page.

[0021] In a possible implementation, the first multimedia generation manner is the reference image generation manner, and the reference image generation manner includes a multi-image reference generation manner; and the device further includes: A reference type display module, configured to display a reference image display area corresponding to each of a plurality of reference image types on the multimedia generation page; and the plurality of reference image types include a style reference image type. The style display module is further configured to display at least one style reference image in the first style library on the multimedia generation page in response to triggering of the reference image display area corresponding to the style reference image type.

[0022] In a possible implementation, the first multimedia generation manner is the reference image generation manner or the video generation manner, and the device further includes: A role information display module, configured to display a role reference display area and a role library control; A role reference image display module, configured to display a plurality of role reference images in a role library corresponding to the role library control in response to triggering of the role library control; A role reference image selection module, configured to display a target role reference image in the role reference display area in a case where the target role reference image is selected from the plurality of role reference images; and the target role reference image is used to control a role in multimedia resource generation.

[0023] In a possible implementation, the style display module includes: A fourth display unit, configured to display at least one style reference image in the first style library in a first style display style configured for the first style library; The at least one style reference image in the first style library is selected from a plurality of style reference images in the first style library based on a first style recommendation strategy configured for the first style library; the plurality of style reference images include a plurality of preset style reference images preconfigured for the first style library, and / or a plurality of style reference images each corresponding to a style dynamically matched for a target account in the first multimedia generation manner; and the target account is an account corresponding to the display multimedia generation page.

[0024] In a possible implementation, the first style recommendation strategy of the first style library configuration comprises at least one of the following: recommending based on historical usage style information of the target account in the first multimedia generation manner; or recommending long-tail styles with a statistical interaction frequency less than an interaction frequency threshold.

[0025] In a possible implementation, the multimedia generation page further displays a style description area; and the apparatus further comprises: a style description backfill module configured to perform, in response to selection of a first style reference image, automatic display of first style description text corresponding to the first style reference image in the style description area, and display of the first style reference image and at least one first associated style reference image associated with the first style reference image at associated positions of the first style description text; The at least one first associated style reference image is used to select and switch the style of the generated multimedia resource, and the first style reference image is one of the at least one style reference image.

[0026] In a possible implementation, the apparatus further comprises: a style reference image switching module configured to perform, in response to selection of a second style reference image in the at least one first associated style reference image, automatic switching of the style description area to display second style description text corresponding to the second style reference image, and display of the second style reference image and at least one first associated style reference image associated with the second style reference image at associated positions of the second style description text.

[0027] In a possible implementation, the first style display style comprises at least two style display styles corresponding to respective display sizes; and the style display module comprises: a fifth display unit configured to perform display of at least one style reference image in the first style library in a style display style corresponding to a target display size in the first style display style, the target display size being a display size matched by a target terminal, and the target terminal being a terminal that displays the multimedia generation page.

[0028] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the method according to any one of the first aspect.

[0029] According to a fourth aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, when instructions in the computer readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method according to any one of the first aspect of the embodiments of the present disclosure. According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, comprising computer instructions, when the computer instructions are executed by a processor, the computer is enabled to perform the method according to any one of the first aspect of the embodiments of the present disclosure.

[0030] The embodiments of the present disclosure at least have the following beneficial effects: By displaying a multimedia generation page, a plurality of multimedia generation controls are displayed in the multimedia generation page; the plurality of multimedia generation controls correspond to a plurality of multimedia generation modes; in a case where a first multimedia generation control in the plurality of multimedia generation controls is in a selected state, first style information corresponding to a first style library configured in a first multimedia generation mode is displayed on the multimedia generation page; the first multimedia generation mode is a multimedia generation mode corresponding to the first multimedia generation control in the plurality of multimedia generation modes. Different style libraries are configured in different multimedia generation modes, and users can independently select different multimedia generation modes to make the style information in the style library configured in the corresponding multimedia generation mode be presented, so that different generation scenarios (i.e. multimedia generation modes) have their corresponding style libraries, and the style libraries of different generation scenarios are visualized, so that the style expression can be more intuitively expressed in a finer granularity based on different generation scenarios, the style expression can be more adapted to different generation scenarios, so that the style expression in each generation scenario can be more accurate, thereby effectively improving the efficiency and generation quality of multimedia resources in each generation scenario. And, different multimedia generation modes can be flexibly selected on the multimedia generation page to switch the display of the corresponding style library, so that the style display is more flexible and rich, and the style interaction rate in the generated multimedia resources can be improved in terms of visual effect and style use convenience, thereby improving the utilization rate of the displayed resources.

[0031] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0032] The accompanying drawings incorporated in and forming a part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure without imposing undue limitations on the disclosure.

[0033] Figure 1 is a schematic diagram of an application environment according to an exemplary embodiment.

[0034] Figure 2 is a flow chart of an interaction method of a multimedia generation page according to an exemplary embodiment.

[0035] Figure 3 is a style display and interaction schematic diagram of a multimedia generation page in a text-to-image scenario according to an exemplary embodiment.

[0036] Figure 4 is a style display schematic diagram of a multimedia generation page in an image-to-drawing scenario according to an exemplary embodiment.

[0037] Figure 5 is a display schematic diagram of style description text backfilling according to an exemplary embodiment.

[0038] Figure 6 is a style display schematic diagram of a multimedia generation page in a single-image reference text-to-image scenario according to an exemplary embodiment.

[0039] Figure 7 is a style display schematic diagram of a multimedia generation page in a video generation scenario according to an exemplary embodiment.

[0040] Figure 8 is a style display schematic diagram of a multimedia generation page in a multi-image reference text-to-image scenario according to an exemplary embodiment.

[0041] Figure 9 is a style display schematic diagram of a multimedia generation page in a text-to-image scenario in a mobile terminal scenario according to an exemplary embodiment.

[0042] Figure 10 is a style display schematic diagram of a multimedia generation page in an image-to-drawing scenario in a mobile terminal scenario according to an exemplary embodiment.

[0043] Figure 11 is a block diagram of an interaction device of a multimedia generation page according to an exemplary embodiment.

[0044] Figure 12 is a block diagram of an electronic device for interaction of a multimedia generation page according to an exemplary embodiment.

[0045] Figure 13 is a block diagram of an electronic device for interaction of a multimedia generation page based on an exemplary embodiment. DETAILED DESCRIPTION

[0046] In order for ordinary personnel in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings.

[0047] It should be noted that the terms "first", "second", and the like in the description and claims of the present disclosure and above-described accompanying drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0048] Artificial intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology and machine learning / deep learning and other directions.

[0049] In recent years, with the research and progress of artificial intelligence technology, artificial intelligence technology has been widely applied in many fields. The scheme provided in the embodiments of the present application relates to computer vision technology (such as image generation or video generation), which is specifically described through the following embodiments.

[0050] Please refer to Figure 1 , Figure 1 is a schematic diagram of an application environment according to an exemplary embodiment, as shown in Figure 1 , the application environment can include a server 01 and a terminal 02.

[0051] In an optional embodiment, the terminal 02 can be used for the interactive method of the multimedia generation page. Specifically, the terminal 02 can include but is not limited to smart phones, desktop computers, tablet computers, notebook computers, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart wearable devices and the like. Optionally, the operating system running on the electronic device can include but is not limited to Android system, IOS system, linux, windows and the like.

[0052] In an optional embodiment, the server 01 can be used for background support of the interaction of the multimedia generation page, for example, providing different multimedia generation modes respectively corresponding to style libraries, selecting a style reference picture for display recommendation from the style library based on a style recommendation strategy corresponding to each style library, and the like. Specifically, the server 01 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and basic cloud computing services such as big data and artificial intelligence platforms.

[0053] In addition, it should be noted that, Figure 1 The above-mentioned only shows one application environment of the multimedia generation page interaction method provided by the present disclosure.

[0054] In the embodiments of the present disclosure, the server 01 and the terminal 02 can be directly or indirectly connected through wired or wireless communication, which is not limited in the present application.

[0055] It should be noted that the following figures show a possible sequence of steps, which actually does not have to be strictly followed. Some steps can be executed in parallel without mutual dependence. The user information (including but not limited to user device information, user personal information, user behavior information, etc.) and data (including but not limited to data for display, training data, etc.) involved in the present disclosure are all information and data authorized by the user or authorized by all parties.

[0056] Figure 2 is a flowchart of a multimedia generation page interaction method according to an exemplary embodiment. As shown in Figure 2 may include the following steps.

[0057] In step S201, a multimedia generation page is displayed, and the multimedia generation page displays a plurality of multimedia generation controls.

[0058] In the embodiments of the present disclosure, the multimedia generation page can refer to an interactive page for generating multimedia resources. For example Figures 3-10 The present disclosure does not limit this. The multimedia resources can include images, videos, and the like, and the present disclosure does not limit this.

[0059] The plurality of multimedia generation controls can correspond to a plurality of multimedia generation modes, for triggering the corresponding multimedia generation controls and switching to the corresponding multimedia generation mode. Exemplarily, the multimedia generation mode can be an image generation mode, and based on this, the plurality of multimedia generation modes can be as followsFigure 3 As shown in 31, the generation methods may include, but are not limited to, text-based images, reference-based images, and image transfer. Text-based images can refer to methods of generating images based on text; reference-based images can refer to methods of generating images based on one or more images, such as single-image reference or multi-image reference; and image transfer can refer to methods of style conversion of images.

[0060] In one possible implementation, access to a multimedia generation page can be triggered in the target application, and in response to this trigger, the multimedia generation page (e.g., an image generation page) can be displayed, for example... Figure 3 As shown in the image above. For example, this multimedia generation page can display various multimedia generation controls, such as... Figure 3 As shown in 31, the selected control is the image generation control corresponding to "Text-to-Image".

[0061] As an example, refer to Figure 3 As shown in the image above, the multimedia generation page can be divided into two areas. The left area can be used for interactive generation of multimedia resources, while the right area can be used to display historically generated multimedia resources, or to display the currently generated target multimedia resource after triggering "Generate Now", such as displaying the currently generated target image.

[0062] In step S203, when the first multimedia generation control among the various multimedia generation controls is selected, the first style information corresponding to the first style library configured under the first multimedia generation method is displayed on the multimedia generation page.

[0063] In the embodiments described in this specification, the first multimedia generation control can be any one of a variety of multimedia generation controls. The selected state can be the default state on the multimedia generation page or selected by the user, and this disclosure does not limit this.

[0064] The first multimedia generation method (e.g., the first image generation method) is the multimedia generation method that corresponds to the first multimedia generation control among multiple multimedia generation methods. For example... Figure 3 As shown in the image above, the first multimedia generation control is a "text-to-image" multimedia generation control that is in the selected state. Correspondingly, the first multimedia generation method can be the text-to-image method.

[0065] The style categories (one or more styles) in the first style library configured under the first multimedia generation manner can be preset or dynamically constructed. For example, the preset style categories can be obtained by counting the styles used by a large number of users under the first multimedia generation manner, for example, counting the style categories with top N (N can be an integer greater than or equal to 1) usage frequencies under the first multimedia generation manner as the style categories in the first style library. The dynamically constructed style categories can be obtained by counting the styles used by the target account under the first multimedia generation manner, which conforms to the style preference of the target account under the first multimedia generation manner. Alternatively, the dynamically constructed style categories can be obtained by adding styles that have not been used by the target account to the styles preferred by the target account under the first multimedia generation manner, which can meet the style preference and explore new styles, thereby effectively improving the style interaction rate. Here, the target account can be the account corresponding to the multimedia generation page (or the account logged in the website or application corresponding to the multimedia generation page). Alternatively, the style categories in the first style library can be the preset style categories combined with the dynamically constructed style categories, which are not limited in the present disclosure. The style can refer to the image style, and it can be understood that the style in the generated video can refer to the image style of the image frame of the generated video. The image style can refer to the stable and identifiable artistic characteristics or forms conveyed by visual elements (such as color, line, composition, texture, etc.), for example, can include animation, sketch, etc. styles, which are not limited in the present disclosure.

[0066] In one example, the style categories in the first style library can be represented in the form of style reference pictures. Based on this, the first style library configured under the first multimedia generation manner can include a plurality of style reference pictures, which can include a plurality of preset style reference pictures pre-configured for the first style library, and / or a plurality of style reference pictures respectively corresponding to the dynamically matched styles for the target account under the first multimedia generation manner. That is, the style reference pictures in the first style library configured under the first multimedia generation manner can be preset, dynamically constructed, or a combination of preset and dynamically constructed, which are not limited in the present disclosure. The style selection preference demand of the user under different generation scenarios can be met, and the style presentation can effectively match different generation scenarios.

[0067] Accordingly, the first style information corresponding to the first style library can refer to information that visualizes all or part of the style categories in the first style library, such as including but not limited to style reference images, style display entry information, etc. Correspondingly, the form of the first style information can include but is not limited to images, text, buttons, etc. In the case of partial style categories, the style categories can be recommended and filtered based on the style recommendation strategy of the first style library; this disclosure does not limit the style recommendation strategy. In the case of all style categories, style reference images corresponding to each style category in the first style library can be displayed (if the corresponding display area is insufficient, it can be switched by sliding or automatically rotated, etc.). The style display entry information can be used to guide the viewing of all or part of the style categories and can be regarded as the entry point for the visualization of the first style library. Style information can be used to indicate the style of the generated multimedia resources, and style reference images can be used to indicate the style of the generated multimedia resources through images; that is, a style reference image can refer to an image that can represent a certain style and can serve as a reference image for a certain style.

[0068] It should be noted that the first style library configured under the first multimedia generation method, and the related content of the first style information corresponding to the first style library, can be understood as any one of multiple multimedia generation methods. Therefore, the second multimedia generation method is also applicable to the related settings, display, and interaction of the first multimedia generation method, which will not be elaborated further. Based on this, the style libraries (including the first style library and the second style library) configured for different multimedia generation methods can include at least one of the following differences: different style types, different display styles, and different style recommendation strategies. For example, the style recommendation strategy can refer to the recommendation strategy for style types in the style library when displaying style types in the style library. Thus, the style information (including first style information and second style information) corresponding to different style libraries can have at least one of the following differences: different style types and different display styles. This allows the style types to be differentiated and adapted to different generation scenarios.

[0069] In one possible implementation, when the first multimedia generation control among multiple multimedia generation controls is selected, the multimedia generation page can display the first style information corresponding to the first style library configured under the first multimedia generation method. For example... Figure 3 The style shown in Figure 32 displays the entry information, or as shown in Figure 32. Figure 4 The style reference image and corresponding style description text are shown in section 41. As an example, the display format of the first style information may include, but is not limited to, pop-ups, overlays, or changing the layout of the multimedia generation page to display it in a specific area of ​​the multimedia generation page (e.g., ...). Figure 3 (As shown in the figure below), this disclosure does not limit it.

[0070] Optionally, in response to the target style selected based on the first style information, a generated target multimedia resource is displayed, the style of which can be the selected target style. For example, a target style can be selected based on the first style information, and a multimedia generation instruction can be triggered, such as clicking... Figure 4 The "Generate Immediately" option triggers a multimedia generation instruction. Accordingly, in response to this instruction, the generated target multimedia resource can be displayed. This target multimedia resource can be generated by a multimedia generation model (e.g., an image generation model or a video generation model) based on a target style and other relevant information. This "other relevant information" can be information required for generating multimedia resources in various generation scenarios. For example, in a text-to-image scenario, this information could include descriptive text; or in an image transfer scenario, it could include the original image to be transferred. This disclosure does not limit these possibilities. The multimedia generation model can be pre-trained, applicable to multiple generation scenarios, or have its own corresponding multimedia generation model for each generation scenario, such as a text-to-image mode or an image transfer model. This disclosure does not limit these possibilities.

[0071] For example, it is possible to Figure 4 Drag the original image and select Figure 4 As shown in Figure 41, for one of the styles, clicking "Generate Now" will display the target multimedia resource to be generated in the right-hand area of ​​the multimedia generation page, such as the target generated image. Optionally, the dragged-out original image and the selected style (e.g., cartoon style) can be input into a pre-trained image generation model for image generation processing to obtain a cartoon-style target generated image. The image style of the target generated image is cartoon style, and the content of the target generated image can be consistent with the content of the dragged-out original image. Because the selected target style is more accurate, the style representation in the input of the image generation model is more accurate, thus resulting in a higher quality target generated image.

[0072] The multimedia generation page is displayed, and a plurality of multimedia generation controls are displayed in the multimedia generation page. The plurality of multimedia generation controls correspond to a plurality of multimedia generation modes. When a first multimedia generation control in the plurality of multimedia generation controls is in a selected state, first style information corresponding to a first style library configured in a first multimedia generation mode is displayed in the multimedia generation page. The first multimedia generation mode is a multimedia generation mode corresponding to the first multimedia generation control in the plurality of multimedia generation modes. Different style libraries are configured in different multimedia generation modes, and a user can independently select different multimedia generation modes to make style information in the style library configured in the corresponding multimedia generation mode be presented. In this way, different generation scenarios (i.e., multimedia generation modes) have corresponding style libraries, and the style libraries of different generation scenarios are visualized, so that the style expression can be more suitable for different generation scenarios, the style expression can be more finely expressed based on different generation scenarios, and the style expression in each generation scenario can be more accurate, thereby effectively improving the efficiency and generation quality of multimedia resources in each generation scenario. In addition, different multimedia generation modes can be flexibly selected in the multimedia generation page to switch the display of the corresponding style library, so that the style display is more flexible and rich, and the style interaction rate in the generated multimedia resources can be improved in terms of visual effect and style use convenience, thereby improving the utilization rate of the displayed resources.

[0073] In a possible implementation, the user can independently switch different multimedia generation modes. Based on this, the method can further include: When a second multimedia generation control in the plurality of multimedia generation controls is in a selected state, the multimedia generation page is switched to display second style information corresponding to a second style library configured in a second multimedia generation mode. The second multimedia generation mode is a multimedia generation mode corresponding to the second multimedia generation control in the plurality of multimedia generation modes. Exemplarily, the second multimedia generation control can be different from the first multimedia generation control.

[0074] As an example, the first style information and the second style information can be different in at least one of the following: style category and display style. The display style can include, but is not limited to, a display area in the multimedia generation page, a display form, a display visual prominence, and the like, which are not limited in the present disclosure.

[0075] Optionally, the first style library and the second style library can be different in at least one of the following (which can be regarded as different generation scenarios corresponding to different style libraries): different style categories, different display styles (which can refer to the style of the style library when visually presented), and different style recommendation strategies. Illustratively, the style recommendation strategy can refer to the recommendation strategy for the style categories when displaying the style categories in the style library, that is, the strategy for recommending all style categories in the style library, which is used to filter the style categories presented to the user. For example, it can include but is not limited to recommending all style categories; or randomly recommending some style categories; or recommending based on historical usage style information (such as historical usage style frequency) of the target account under the corresponding multimedia generation mode, such as recommending styles with a historical usage style frequency higher than a preset frequency threshold; or recommending long-tail styles with a statistical interaction frequency less than an interaction frequency threshold, and the like, which are not limited in the present disclosure.

[0076] By triggering the selection of the second multimedia generation control, the display of the second style library is switched. Different style libraries have different display styles, so that when the generation scenario is switched, the visual prominence of the style library can be improved, and the style interaction rate can be effectively improved. Moreover, different style libraries have different style recommendation strategies and displayed style categories when displayed, which can be more suitable for different scenarios and facilitate the user to quickly locate the desired style.

[0077] Referring to Figure 3 the upper part of the figure or Figure 4 , in an optional implementation, the presentation of the style library can be directly a style reference picture in the style library, or can be an entry guide of the style library, which can flexibly meet the differentiated needs of different generation scenarios. Based on this, the first style information corresponding to the first style library can include at least one style reference picture in the first style library (such as Figure 4 41 shown in, for example Figure 3 34 shown in the lower part of the figure), or style display entry information (such as Figure 3 32 shown in) corresponding to the first style library. The at least one style reference picture in the first style library can be all or part of the style reference pictures in the first style library, and here the part of the style reference pictures can be obtained by filtering from the first style library based on the above-mentioned style recommendation strategy, which is not limited in the present disclosure.

[0078] Correspondingly, the first style information corresponding to the first style library configured in the multimedia generation page in the first multimedia generation mode described above can include: at least one style reference picture in the first style library is displayed in the multimedia generation page, such as Figures 4-7 shown; or, the style display entry information corresponding to the first style library is displayed in the multimedia generation page, such as Figure 3 32 shown in.

[0079] In one optional implementation, the first style information may include multiple style category labels and at least one style reference image under the target style category label, for example... Figure 3 As shown in the image below, in the context of text-based images, the following can be displayed: Figure 3 As shown in the image below. Based on this, the first style information corresponding to the first style library configured under the first multimedia generation method, as displayed on the multimedia generation page, can include: The multimedia generation page displays multiple style category tags corresponding to the first style library, such as... Figure 3 As shown in 33; It can display at least one style reference image under the target style category label; the target style category label can be one of multiple style category labels. For example, Figure 3 The multiple style category labels in the image below can include a "Featured" style category label, which can be a comprehensive recommendation across multiple style categories. The random style can be used to explore different styles to enhance style diversity in multimedia resource generation.

[0080] Optionally, it can be triggered Figure 3 The different style category tags shown in 33 allow you to easily view more granular style reference images under a specific style category tag.

[0081] By setting hierarchical styles, we can improve the efficiency of style selection and make style selection more granular, thus making style expression more precise and improving the efficiency and quality of multimedia resource generation.

[0082] Reference Figure 3 In one example, the first multimedia generation method may include a text-to-image method, and the first style information may include style display entry information. Based on this, the first style information corresponding to the first style library configured under the first multimedia generation method, as described above, can include: displaying the style display entry information corresponding to the first style library on the multimedia generation page, for example... Figure 3 As shown in 32.

[0083] Accordingly, the method may further include: in response to the triggering of style display entry information (e.g., click, double-click, etc.), displaying at least one style reference image from the first style library on the multimedia generation page. For example, clicking... Figure 3 The number 32 in the text triggers the display. Figure 3 At least one style reference diagram from the first style library shown in Figure 34.

[0084] By setting the first style information to include style display entry information in the text-to-image scenario, the characteristics of the text-to-image scenario focusing on text description can be adapted, the presentation of the style reference image is triggered by the user, and the experience demand in the text-to-image scenario is met.

[0085] With reference to Figures 4-6 In one possible implementation, the multimedia generation page can also display a style description area. For example, Figure 4 the input area below the "rewriting description" in Figure 5 , or Figure 6 the input area below the "creative description" in , which is not limited by the present disclosure. Accordingly, the method can further include: in response to the selection operation of the first style reference image, automatically displaying the first style description text corresponding to the first style reference image in the style description area, and displaying the first style reference image and at least one first associated style reference image associated with the first style reference image at the associated position (such as the surrounding position) of the first style description text.

[0086] wherein the at least one first associated style reference image is used to select and switch the style of the generated multimedia resource; and the first style reference image is one of the at least one style reference image, i.e., the selected one.

[0087] Further, the method can further include: in response to the selection operation of a second style reference image in the at least one first associated style reference image, automatically switching the style description area to display the second style description text corresponding to the second style reference image, and displaying the second style reference image and at least one first associated style reference image associated with the second style reference image at the associated position of the second style description text.

[0088] Figure 5 For example, in the text-to-image scenario, the first style reference image shown in 51 in Figure 5 may be selected. Accordingly, the first style description text corresponding to the first style reference image can be automatically displayed in the style description area, such as "XX style" displayed in the input area below the "creative description". And the first style reference image (such as 52 in Figure 5 ) and at least one first associated style reference image (such as 53 in Figure 5 ) associated with the first style reference image can be displayed at the associated position of the first style description text. Further, the at least one first associated style reference image shown in 53 in Figure 5 may be selected to switch to other style categories, such as clicking Figure 5The second style reference image for "XXX style" shown in section 53 can automatically switch to displaying the second style description text (e.g., XXX style) corresponding to the second style reference image in the style description area. Accordingly, Figure 5 52 and 53 in the diagram are also switched accordingly based on this second style reference diagram.

[0089] Optionally, the associated positions of the first-style descriptive text can also be displayed as follows: Figure 5 Buttons 54 and 55 are shown in the image. Figure 5 The button shown in section 54 can be used to collapse and expand. Figure 5 52 and 53 in the middle. Figure 5 The button shown in section 55 can be used to delete the first-style description text or to close the window. Figure 4 The examples are 52 and 53.

[0090] By setting up a multimedia generation page that displays a style description area, when a style reference image is selected, the corresponding style description text can be filled in the style description area, and the corresponding style reference image and related style reference images will be displayed at the style description text filling position. This allows for style type adjustment in the style description area, making style type adjustment more convenient and efficient.

[0091] Reference Figure 6 , Figure 7 and Figure 4 In one example, the aforementioned first multimedia generation method may include an image transfer method, a video generation method, or a reference image method, and the aforementioned first style information may include at least one style reference image from a first style library. Based on this, displaying the first style information corresponding to the first style library configured under the first multimedia generation method on the multimedia generation page may include: displaying at least one style reference image from the first style library on the multimedia generation page, for example... Figure 6 41 in Figure 7 61 in Figure 7 As shown in 71. For example, Figure 6 It can provide a reference image scenario for a single image. Optionally, it can also be based on a trigger. Figure 7 62 or Figure 7 See number 72 in the image to view more style references. And refer to... Figure 7 Users can upload the first and last images and the last frame image for video generation; this disclosure does not impose any restrictions on these. It should be noted that... Figure 8 The multi-image reference in the image-generated video shown can refer to the generation of video by referencing multiple images, which can be image frames other than the first and last frames.

[0092] By visually displaying style reference images through image transfer, video generation, and reference image generation, the style application characteristics of these generation scenarios can be adapted to. By directly displaying style reference images, the generation efficiency of multimedia resources can be improved.

[0093] Reference Figure 8 In one example, the first multimedia generation method can be a reference image generation method, which includes a multi-image reference generation method. Based on this, the method may further include: displaying reference image display areas corresponding to various reference image types on the multimedia generation page; the various reference image types may include style reference image types, such as... Figure 8 As shown in 83. Exemplarily, various reference image types may also include a subject (e.g., a character), a scene, etc., and this disclosure does not limit this. The reference image display area corresponding to the subject can be as follows: Figure 8 As shown in 81, the reference image display area corresponding to the scene can be as follows: Figure 8 As shown in 82. Optionally, various reference map types may also include pose maps, normal maps, etc., which are not limited in this disclosure.

[0094] Accordingly, displaying at least one style reference image from the first style library on the multimedia generation page may include: responding to a trigger (e.g., a click, long press, etc.) of the reference image display area corresponding to the style reference image type, displaying at least one style reference image from the first style library on the multimedia generation page. For example, one can click... Figure 8 83 in the middle, to trigger the display Figure 6 84 in the first style library refers to at least one style reference image.

[0095] By setting up multiple reference images, including various reference image types, the control over the generated images from multiple reference images becomes more precise, and the combination becomes more flexible. Style reference images are aggregated into multiple reference image types, making the display and interaction more flexible and convenient.

[0096] Reference Figure 8 and Figure 6 In one optional implementation, the first multimedia generation method can be a reference image method or a video generation method. Based on this, the method may further include: displaying a character reference display area and a character library control. For example, the first multimedia generation control can be a reference image control, or it can be a control corresponding to a more detailed generation method in the reference image scenario, such as a control corresponding to a single image reference or a control corresponding to multiple image references. For example, Figure 6 When "Single Image Reference" is selected, the character reference display area can be shown (e.g., Figure 6 (as shown in 63) and character library controls (e.g.) Figure 9The character reference display area can be used to display the selected character reference picture; and the character library control can be used to trigger the display of the plurality of character reference pictures in the character library.

[0097] Further, in response to the triggering of the character library control, the plurality of character reference pictures in the character library corresponding to the character library control are displayed. The character reference picture can refer to a reference picture including a character.

[0098] In a case where a target character reference picture in the plurality of character reference pictures is selected, the target character reference picture is displayed in the character reference display area; and the target character reference picture can be used to generate a character control of the multimedia resource, i.e., to perform character control in the generation process of the multimedia resource, so as to realize the consistency of the character.

[0099] By displaying the character reference display area and the character library control, in response to the triggering of the character library control, the plurality of character reference pictures in the character library corresponding to the character library control are displayed, and in a case where a target character reference picture in the plurality of character reference pictures is selected, the target character reference picture is displayed in the character reference display area, so as to realize the consistency of the character in the reference picture generation scenario.

[0100] In a possible implementation, the above-mentioned display of at least one style reference picture in the first style library on the multimedia generation page can include: display of at least one style reference picture in the first style library in a first style display style configured by the first style library. The at least one style reference picture in the first style library is obtained by screening from a plurality of style reference pictures in the first style library based on a first style recommendation strategy configured by the first style library; the plurality of style reference pictures include a plurality of preset style reference pictures pre-configured for the first style library, and / or a plurality of style reference pictures respectively corresponding to a plurality of styles dynamically matched for a target account in the first multimedia generation mode; and the target account is an account corresponding to the display multimedia generation page. For details, refer to the above-mentioned corresponding content, which will not be described here.

[0101] By displaying at least one style reference picture in the first style library in a first style display style configured by the first style library, the presentation of the style library in different generation scenarios is more flexible and diverse, which can effectively improve the style interaction; and the style reference pictures in different style libraries are screened and displayed using the corresponding style recommendation strategy in the visual presentation, so that the style recommendation in different generation scenarios is more accurate, thereby improving the efficiency and quality of the multimedia resource generation based on the style.

[0102] In a possible implementation, the first style recommendation strategy of the first style library configuration can include at least one of the following: recommending based on historical use style information (for example, historical use style frequency) of a target account in the first multimedia generation manner, for example, recommending a long-tail style with a statistical interaction frequency less than an interaction frequency threshold; or recommending a long-tail style with a statistical interaction frequency less than an interaction frequency threshold to realize exploration of new styles; and the target account is an account corresponding to the multimedia generation page. By recommending the historical use style behavior of the user in each generation scene, the style recommendation accuracy in each generation scene can be improved; or the long-tail style is recommended for exploration, the coverage of the style is wider, and the multimedia resource generation is more interesting.

[0103] In an optional implementation, the first style display style can include at least two display sizes each corresponding to a style display style. Based on this, the first style display style of the first style library configuration described above, displaying at least one style reference picture in the first style library, can include: displaying at least one style reference picture in the first style library in the style display style corresponding to the target display size in the first style display style; and the target display size is a display size matched by a target terminal, and the target terminal is a terminal displaying a multimedia generation page.

[0104] For example, the target terminal can include a mobile terminal with a small screen, a computer terminal with a large screen, or the like, and accordingly, the target display size can include, but is not limited to, a display size matched by a mobile terminal, a size of a web page in a computer terminal, and the like, which are not limited in the present disclosure.

[0105] For example, referring to Figure 10 and Figure 9 , for example, in a case where at least one style reference picture in the first style library needs to be displayed, the first style display style corresponding to the first style library can be determined. Further, the type of the target terminal can be determined, for example, as a mobile terminal, and the target display size matched by the mobile terminal can be determined from the display sizes corresponding to the first style display style, so that the style display style corresponding to the target display size can be determined. Thus, at least one style reference picture in the first style library can be displayed in the style display style corresponding to the target display size in the first style display style.

[0106] For example, taking a mobile terminal as an example, the style reference picture display in a text-to-image scene can be as shown in Figure 3 For comparison with Figure 3 (for example, Figure 9 is a web page in a computer terminal), the display size of the mobile terminal is smaller, and a display style that is more concise and convenient for touch operation can be set. For example, the style display entry information can be as shown in 91 in Figure 9 . At least one style reference picture in the first style library can be as shown inFigure 10 At least one style reference picture in the first style library can be displayed in a pop-up manner, and style description text can be displayed above the style reference picture to save display resources, etc. The present disclosure does not limit this. Alternatively, the reference Figure 10 In the image conversion scene, at least one style reference picture in the first style library can be displayed as shown in 101 of FIG. 1 1 1. Optionally, the "all" corresponding control in 101 can be triggered to view more style reference pictures. Figure 10 Figure 11

[0107] Optionally, at least one style reference picture displayed in a smaller display size can be displayed in a card manner, or can be displayed in a carousel manner, or can be displayed in a sliding manner, etc. This can not only save display resources, but also facilitate viewing more style reference pictures.

[0108] By displaying at least one style reference picture in the first style library in a style display style corresponding to a target display size in the first style display style, the display of the style reference picture is more flexible and diverse, and can effectively adapt to display resources of different display sizes, improve the style interaction experience in multimedia resource generation, and thus improve the generation and conversion of multimedia resources.

[0109] Figure 11 is a block diagram of an interactive device of a multimedia generation page according to an exemplary embodiment. Referring to Figure 12 The device can include: The page display module 1101 is configured to display a multimedia generation page, and the multimedia generation page displays a plurality of multimedia generation controls. The plurality of multimedia generation controls correspond to a plurality of multimedia generation modes. The style display module 1103 is configured to display first style information corresponding to a first style library configured in a first multimedia generation mode when a first multimedia generation control in the plurality of multimedia generation controls is in a selected state. The first multimedia generation mode is a multimedia generation mode corresponding to the first multimedia generation control in the plurality of multimedia generation modes.

[0110] ​​The multimedia generation page is displayed, and a plurality of multimedia generation controls are displayed in the multimedia generation page. The plurality of multimedia generation controls correspond to a plurality of multimedia generation modes. When a first multimedia generation control in the plurality of multimedia generation controls is in a selected state, first style information corresponding to a first style library configured in a first multimedia generation mode is displayed in the multimedia generation page. The first multimedia generation mode is a multimedia generation mode corresponding to the first multimedia generation control in the plurality of multimedia generation modes. Different style libraries are configured in different multimedia generation modes, and a user can independently select different multimedia generation modes to enable style information in a style library configured in a corresponding multimedia generation mode to be presented. In this way, different generation scenarios (i.e., multimedia generation modes) have respective corresponding style libraries. The style libraries that differentiate the generation scenarios are visualized, so that style expression can be more adapted to different generation scenarios. Style expression can be more finely expressed based on different generation scenarios, so that style expression in each generation scenario can be more accurate, thereby effectively improving the efficiency and generation quality of generated multimedia resources in each generation scenario. In addition, different multimedia generation modes can be flexibly selected in the multimedia generation page to switch the display of corresponding style libraries, so that style display is more flexible and rich. From the visual aspect and the convenience of style use, the style interaction rate in generated multimedia resources can be improved, thereby improving the utilization rate of displayed resources.

[0111] In a possible implementation, the apparatus further includes: The generation mode switching module is configured to perform, when a second multimedia generation control in the plurality of multimedia generation controls is in a selected state, switching the multimedia generation page to display second style information corresponding to a second style library configured in a second multimedia generation mode. The second multimedia generation mode is a multimedia generation mode corresponding to the second multimedia generation control in the plurality of multimedia generation modes. The first style information and the second style information are different in at least one of the following: style category and display style. The first style library and the second style library are different in at least one of the following: style category, display style, and style recommendation strategy.

[0112] In a possible implementation, the first style information corresponding to the first style library includes at least one style reference picture in the first style library or style display entry information corresponding to the first style library. The style display module 1103 can include: The first display unit is configured to perform displaying at least one style reference picture in the first style library in the multimedia generation page or displaying the style display entry information corresponding to the first style library in the multimedia generation page.

[0113] In a possible implementation, the first style information includes a plurality of style classification labels and at least one style reference picture under a target style classification label; the style display module 1103 can include: a style classification label display unit, configured to display the plurality of style classification labels corresponding to the first style library on the multimedia generation page; a style reference picture display unit, configured to display at least one style reference picture under the target style classification label; the target style classification label is one of the plurality of style classification labels.

[0114] In a possible implementation, the first multimedia generation manner includes a text-to-image manner, and the first style information includes style display entry information; the style display module 1103 can include: a second display unit, configured to display the style display entry information corresponding to the first style library on the multimedia generation page; The apparatus further includes: a style reference picture display module, configured to display at least one style reference picture in the first style library on the multimedia generation page in response to triggering of the style display entry information.

[0115] In a possible implementation, the first multimedia generation manner includes an image-to-image manner, a video generation manner, or a reference text-to-image manner, and the first style information includes at least one style reference picture in the first style library; the style display module 1103 can include: a third display unit, configured to display at least one style reference picture in the first style library on the multimedia generation page.

[0116] In a possible implementation, the first multimedia generation manner is the reference text-to-image manner, and the reference text-to-image manner includes a multi-image reference generation manner; the apparatus further includes: a reference type display module, configured to display a reference picture display area corresponding to each of a plurality of reference picture types on the multimedia generation page; the plurality of reference picture types include a style reference picture type; The style display module 1103 is further configured to display at least one style reference picture in the first style library on the multimedia generation page in response to triggering of the reference picture display area corresponding to the style reference picture type.

[0117] In a possible implementation, the first multimedia generation manner is the reference text-to-image manner or the video generation manner, and the apparatus further includes: The character information display module is configured to display the character reference display area and the character library control. The character reference picture display module is configured to display a plurality of character reference pictures in a character library corresponding to the character library control in response to triggering of the character library control. The character reference picture selection module is configured to display a target character reference picture in the plurality of character reference pictures in the character reference display area if the target character reference picture is selected; the target character reference picture is used to generate a character control of a multimedia resource.

[0118] In a possible implementation, the style display module 1103 can include: The fourth display unit is configured to display at least one style reference picture in the first style library in a first style display style configured for the first style library. The at least one style reference picture in the first style library is selected from a plurality of style reference pictures in the first style library based on a first style recommendation strategy configured for the first style library; the plurality of style reference pictures include a plurality of preset style reference pictures pre-configured for the first style library, and / or a plurality of style reference pictures respectively corresponding to a plurality of styles dynamically matched for a target account in the first multimedia generation mode; the target account is an account corresponding to the display multimedia generation page.

[0119] In a possible implementation, the first style recommendation strategy configured for the first style library includes at least one of the following: recommendation based on historical use style information of a target account in the first multimedia generation mode; or, recommendation of long-tail styles with a statistical interaction frequency less than an interaction frequency threshold.

[0120] In a possible implementation, the multimedia generation page further displays a style description area; and the apparatus further includes: The style description backfill module is configured to automatically display first style description text corresponding to the first style reference picture in the style description area in response to selection operation of the first style reference picture, and display the first style reference picture and at least one first associated style reference picture associated with the first style reference picture at an associated position of the first style description text. The at least one first associated style reference picture is used to select and switch a style of a generated multimedia resource; and the first style reference picture is one of the at least one style reference picture.

[0121] In a possible implementation, the apparatus further includes: The style reference picture switching module is configured to automatically switch the style description area to display second style description text corresponding to a second style reference picture in response to a selection operation of the second style reference picture in the at least one first associated style reference picture, and display the second style reference picture and at least one first associated style reference picture associated with the second style reference picture at an associated position of the second style description text.

[0122] In a possible implementation, the first style display style includes at least two style display styles corresponding to respective display sizes; and the style display module 1103 can include: A fifth display unit configured to display at least one style reference picture in the first style library in a style display style corresponding to a target display size in the first style display style; the target display size is a display size matched by a target terminal, and the target terminal is a terminal displaying the multimedia generation page.

[0123] As to the apparatus in the above-mentioned embodiments, the specific manners in which various modules perform operations have been described in details in the embodiments of the method, and thus will not be described in details here.

[0124] Figure 12 is a block diagram of an electronic device for interaction of a multimedia generation page according to an example embodiment. The electronic device can be a terminal, and its internal structure diagram can be as shown in Figure 12 The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the electronic device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a multimedia generation page interaction method. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the electronic device, or an external keyboard, touchpad or mouse, etc. Those skilled in the art can understand that Figure 13 The structure shown in the figure is only a block diagram of part of the structure related to the present disclosure, and does not constitute a limitation on the electronic device to which the present disclosure is applied. The specific electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] Figure 13 is a block diagram of an electronic device for multimedia generation page interaction based on an example embodiment. The electronic device can be a server, and its internal structure diagram can be as shown in Figure 13 The electronic device includes a processor, a memory and a network interface connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the electronic device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a multimedia generation page interaction method. Those skilled in the art can understand that ​ the structure shown in the above embodiment is only a block diagram of part of the structure related to the present disclosure, and does not constitute a limitation on the electronic device to which the present disclosure is applied. The specific electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an example embodiment, an electronic device is also provided, including a processor, a memory for storing instructions executable by the processor, and wherein the processor is configured to execute the instructions to implement the multimedia generation page interaction method in the embodiments of the present disclosure.

[0126] In an example embodiment, a computer readable storage medium is also provided, when the instructions in the computer readable storage medium are executed by the processor of the electronic device, the electronic device can execute the multimedia generation page interaction method in the embodiments of the present disclosure. The computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0127] In an example embodiment, a computer program product containing instructions is also provided, when it is run on a computer, the computer executes the multimedia generation page interaction method in the embodiments of the present disclosure.

[0128] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, databases, or other media in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0129] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure that are deemed to fall within the general principles of the disclosure and include commonly known or customary practice in the art. The specification and examples are to be considered exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

[0130] It should be understood that the present disclosure is not limited to the precise structures herein described and illustrated in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the claims that follow.

Claims

1. An interactive method of generating a page of multimedia, characterized in that, The method comprises: displaying a multimedia generation page, and the multimedia generation page displays a plurality of multimedia generation controls; the plurality of multimedia generation controls correspond to a plurality of multimedia generation modes; when a first multimedia generation control in the plurality of multimedia generation controls is in a selected state, the multimedia generation page displays first style information corresponding to a first style library configured in a first multimedia generation mode; the first multimedia generation mode is a multimedia generation mode corresponding to the first multimedia generation control in the plurality of multimedia generation modes.

2. The method of claim 1, wherein, The method further comprises: when a second multimedia generation control in the plurality of multimedia generation controls is in a selected state, the multimedia generation page switches to display second style information corresponding to a second style library configured in a second multimedia generation mode; the second multimedia generation mode is a multimedia generation mode corresponding to the second multimedia generation control in the plurality of multimedia generation modes; wherein the first style information and the second style information are different in at least one of the following: style category, display style; the first style library and the second style library are different in at least one of the following: style category, display style, style recommendation strategy.

3. The method of claim 1, wherein, The first style information corresponding to the first style library includes at least one style reference picture in the first style library, or the first style information corresponding to the first style library includes style display entry information; The first style information corresponding to the first style library configured in the first multimedia generation mode in the multimedia generation page comprises: displaying at least one style reference picture in the first style library in the multimedia generation page; or, displaying the style display entry information corresponding to the first style library in the multimedia generation page.

4. The method of claim 1, wherein, The first style information includes a plurality of style classification tags and at least one style reference picture under a target style classification tag; the first style information corresponding to the first style library configured in the first multimedia generation mode in the multimedia generation page comprises: displaying the plurality of style classification tags corresponding to the first style library in the multimedia generation page; displaying at least one style reference picture under the target style classification tag; the target style classification tag is one of the plurality of style classification tags.

5. The method of claim 1, wherein, The first multimedia generation mode includes a text-to-image mode, and the first style information includes style display entry information; The first style information corresponding to the first style library configured in the first multimedia generation mode in the multimedia generation page comprises: displaying the style display entry information corresponding to the first style library in the multimedia generation page; The method further comprises: in response to triggering of the style display entry information, displaying at least one style reference picture in the first style library in the multimedia generation page.

6. The method of claim 1, wherein, The first multimedia generation mode includes an image conversion mode, a video generation mode, or a reference text-to-image mode, and the first style information includes at least one style reference picture in the first style library; The first style information corresponding to the first style library configured in the first multimedia generation mode of the multimedia generation page includes: The multimedia generation page displays at least one style reference picture in the first style library.

7. The method of claim 6, wherein, The first multimedia generation mode is the reference picture generation mode, and the reference picture generation mode includes a multi-picture reference generation mode; the method further includes: The multimedia generation page displays a reference picture display area corresponding to each of a plurality of reference picture types; the plurality of reference picture types include a style reference picture type; The multimedia generation page displays at least one style reference picture in the first style library, including: In response to triggering of the reference picture display area corresponding to the style reference picture type, the multimedia generation page displays at least one style reference picture in the first style library.

8. The method according to claim 6 or 7, characterized in that, The first multimedia generation mode is the reference picture generation mode or the generated video mode, and the method further includes: Displaying a character reference display area and a character library control; In response to triggering of the character library control, displaying a plurality of character reference pictures in a character library corresponding to the character library control; In a case where a target character reference picture in the plurality of character reference pictures is selected, displaying the target character reference picture in the character reference display area; the target character reference picture is used to generate a character control of a multimedia resource.

9. The method according to any one of claims 3, 5-7, characterized in that, The multimedia generation page displays at least one style reference picture in the first style library, including: Displaying at least one style reference picture in the first style library in a first style display style configured by the first style library; The at least one style reference picture in the first style library is selected from a plurality of style reference pictures in the first style library based on a first style recommendation strategy configured by the first style library; the plurality of style reference pictures include a plurality of preset style reference pictures pre-configured for the first style library, and / or a plurality of style reference pictures each corresponding to a style corresponding to a target account dynamically matched in the first multimedia generation mode; the target account is an account corresponding to the display multimedia generation page.

10. The method of claim 9, wherein, The first style recommendation strategy configured by the first style library includes at least one of the following: recommendation based on historical use style information of a target account in the first multimedia generation mode; or, recommendation of long-tail styles with a statistical interaction frequency less than an interaction frequency threshold.

11. The method according to any one of claims 3-7, characterized in that, The multimedia generation page further displays a style description area; the method further includes: In response to a selection operation of a first style reference picture, automatically displaying a first style description text corresponding to the first style reference picture in the style description area, and displaying the first style reference picture and at least one first associated style reference picture associated with the first style reference picture at an associated position of the first style description text; The at least one first associated style reference picture is used to select and switch the style of the generated multimedia resource; the first style reference picture is one of the at least one style reference picture.

12. The method of claim 11, wherein, The method further includes: In response to a selection operation of a second style reference picture in the at least one first associated style reference picture, the style description area is automatically switched to display second style description text corresponding to the second style reference picture, and the second style reference picture and at least one first associated style reference picture associated with the second style reference picture are displayed at an associated position of the second style description text.

13. The method of claim 9, wherein, The first style display mode includes at least two display sizes corresponding to style display modes; and the first style display mode configured by the first style library displays at least one style reference picture in the first style library, including: The first style display mode configured by the first style library displays at least one style reference picture in the first style library, including:

14. An interactive apparatus for generating a page of multimedia, characterized by The first style display mode configured by the first style library displays at least one style reference picture in the first style library, including: A page display module configured to display a multimedia generation page, the multimedia generation page displaying a plurality of multimedia generation controls; The plurality of multimedia generation controls correspond to a plurality of multimedia generation modes; A style display module configured to display first style information corresponding to a first style library configured by a first multimedia generation mode when a first multimedia generation control in the plurality of multimedia generation controls is in a selected state; the first multimedia generation mode is a multimedia generation mode corresponding to the first multimedia generation control in the plurality of multimedia generation modes.

15. An electronic device, comprising: A processor; A memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method of any one of claims 1-13. When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the method of any one of claims 1-13.

16. A computer-readable storage medium, characterized in that, Computer instructions, when executed by a processor, cause a computer to execute the method of any one of claims 1-13.

17. A computer program product, characterised in that, ​

Images