Visual media generation method and device, electronic equipment and storage medium

Abstract

The invention relates to a visual media generation method and device, electronic equipment and a storage medium, and the method comprises the steps: displaying a random style control on a preset generation page, responding to a visual media generation instruction triggered based on the random style control, and displaying a plurality of generated visual media corresponding to a plurality of visual styles. The multiple visual styles are randomly determined by the current platform. According to the embodiment of the invention, the interaction convenience and interaction efficiency in the visual media generation process can be greatly improved, the interaction experience can be greatly improved, the clear accuracy and diversity of visual style description can be effectively ensured, and the diversity and generation effect of the visual media can be effectively improved.

Description

Technical Field

[0001] This disclosure relates to the field of computer vision technology, and in particular to a method, apparatus, electronic device and storage medium for generating visual media. Background Technology

[0002] With the development of AIGC (Artificial Intelligence Generated Content) technology, AIGC generation tools have also been widely used. Among related technologies, AIGC generation tools cover generative models such as diffusion models. These models can transform text descriptions or reference inputs into visual media outputs. However, many users, especially novices in the AIGC field, often find it difficult to clearly and accurately describe their desired visual style or do not understand the specific style effects supported by the platform. They often spend a lot of time editing the generated description information, resulting in poor interactive efficiency in the visual media generation process. Furthermore, the inability to clearly and accurately describe the generated description information often leads to poor visual media effects such as images and videos. Summary of the Invention This disclosure provides a visual media generation method, apparatus, electronic device, and storage medium to at least solve the technical problems of poor interactive efficiency and poor image and video generation effects in the visual media generation process in related technologies. The technical solution of this disclosure is as follows: According to a first aspect of the present disclosure, a visual media generation method is provided, comprising: Display randomly styled controls on the preset generated page; In response to a visual media generation instruction triggered by the random style control, multiple generated visual media are displayed. These multiple visual media correspond to multiple visual styles, which are randomly determined by the current platform.

[0003] In an optional embodiment, the multiple visual styles are randomly determined based on the interest visual styles corresponding to the current account. The interest visual styles are determined based on the historical style interaction information corresponding to the current account and / or the high-frequency style description information corresponding to the current platform, using a preset visual style recognition model. The historical style interaction information is used to indicate the interactive operations performed by the current account for at least one visual style within a preset historical time period.

[0004] In an optional embodiment, displaying random style controls on a preset generated page includes: The random style control is displayed in the style selection area of ​​the preset generation page.

[0005] In an optional embodiment, the step of displaying multiple generated visual media in response to a visual media generation instruction triggered based on the random style control includes: In response to a selection instruction for the random style control, random style description information is displayed in a preset area of ​​the preset generation page, where the preset area is the input area for media generation description information. When the random style description information is displayed in the preset area, the multiple visual media are displayed in response to the visual media generation instruction.

[0006] In an optional embodiment, the method further includes: In response to an information input command, the currently generated description information is displayed in a preset area of ​​the preset generation page, where the preset area is the input area for media generation description information; The multiple visual media generated by the display include: Display the multiple visual media generated based on the currently generated description information and the multiple visual styles.

[0007] In an optional embodiment, the method further includes: In response to the first parameter setting instruction, the first current parameter is displayed on the preset generation page. The first current parameter is used to indicate the degree of influence of the current generation description information and the corresponding visual style on each visual media during the generation of each visual media. The display of the multiple visual media generated based on the currently generated description information and the multiple visual styles includes: Display the multiple visual media generated based on the currently generated description information, the multiple visual styles, and the first current parameter.

[0008] In an optional embodiment, the currently generated description information includes a current reference image; the plurality of visual media are images of the plurality of visual styles corresponding to the current reference image; the plurality of visual media for displaying the generated images include: The multiple visual media are displayed based on preset style templates.

[0009] In an optional embodiment, the multiple visual styles are multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; the method further includes: Display style description information for the various custom styles; In response to storage instructions for multiple custom styles, style description information for the multiple custom styles is stored.

[0010] In an optional embodiment, the method further includes: In response to a preset sharing command, the various custom styles and / or the various visual media corresponding to the various custom styles are shared with the user account on the current platform.

[0011] In an optional embodiment, the multiple visual styles are multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; the method further includes: In response to the style customization command corresponding to the first visual media, display the custom style description information of the visual style corresponding to the first visual media; In response to a storage instruction for the custom style description information, the first visual media and the custom style description information are stored; Wherein, the first visual medium is any one of the multiple visual media.

[0012] In an optional embodiment, prior to displaying the generated multiple visual media, the method further includes: In response to the second parameter setting instruction, a second current parameter is displayed on the preset generation page. The second current parameter is used to indicate the degree of difference in visual style among the multiple visual media. The various visual styles are randomly determined based on the second current parameter.

[0013] In an optional embodiment, the random style control is initially in an unselected state; the display of multiple generated visual media in response to a visual media generation instruction triggered based on the random style control includes: In response to the selection instruction for the random style control, the random style control in the preset generated page is updated from a non-selected state to a selected state; When the random style control is selected, the multiple visual media are displayed in response to the visual media generation instruction.

[0014] In an optional embodiment, displaying random style controls on a preset generated page includes: In response to a page display instruction, a preset generated page including preset prompt information is displayed. The preset prompt information is used to prompt that visual media is generated using a randomly determined style, and the preset prompt information includes the random style control.

[0015] In an optional embodiment, the method further includes: Before or during the presentation of the multiple visual media, display style description information corresponding to each of the multiple visual styles.

[0016] In an optional embodiment, the generated visual media includes: Display the multiple visual media and preset production instructions; The preset production instruction information is used to instruct media content production based on at least one of the plurality of visual media.

[0017] In an optional embodiment, the plurality of visual media correspond to different visual styles, and the method further includes: In response to a first synthesis instruction for at least two of the plurality of visual media, a first synthesized visual media corresponding to the at least two visual media is displayed, wherein the visual style corresponding to the first synthesized visual media is a mixed style of the visual styles corresponding to the at least two visual media. or, In response to a second composition instruction for a visual style corresponding to at least two of the plurality of visual media, a second composite visual media corresponding to at least two visual styles is displayed, wherein the at least two visual styles are the visual styles corresponding to the at least two visual media.

[0018] In an optional embodiment, the generated visual media includes: Display a second visual medium and its corresponding style description information, wherein the second visual medium is any one of the plurality of visual media; In response to a visual media switching command, the second visual media and its corresponding style description information are switched to a third visual media and its corresponding style description information, wherein the third visual media is any visual media other than the second visual media among the plurality of visual media.

[0019] In an optional embodiment, the generated visual media includes: The aforementioned visual media are presented in a blind box style; In response to a media viewing command, display the visual media corresponding to the media viewing command; Wherein, the visual media corresponding to the media viewing instruction is at least one of the plurality of visual media.

[0020] According to a second aspect of the present disclosure, a visual media generation apparatus is provided, comprising: The control display module is configured to display random style controls on a preset generation page. The random style controls in the selected state are used to indicate that the corresponding visual style is randomly determined during the visual media generation process. The visual media display module is configured to execute a visual media generation instruction triggered based on the random style control, and display multiple generated visual media, which correspond to multiple visual styles, and the multiple visual styles are randomly determined by the current platform.

[0021] In an optional embodiment, the multiple visual styles are randomly determined based on the interest visual styles corresponding to the current account. The interest visual styles are determined based on the historical style interaction information corresponding to the current account and / or the high-frequency style description information corresponding to the current platform, using a preset visual style recognition model. The historical style interaction information is used to indicate the interactive operations performed by the current account for at least one visual style within a preset historical time period.

[0022] In an optional embodiment, the control display module is specifically configured to display the random style control in the style selection area of ​​the preset generated page.

[0023] In an optional embodiment, the visual media display module includes: The random style description information display unit is configured to execute a random style description information display in a preset area of ​​the preset generation page in response to a selection instruction for the random style control, wherein the preset area is an input area for media generation description information; The first visual media display unit is configured to display the multiple visual media in response to the visual media generation instruction when the random style description information is displayed in the preset area.

[0024] In an optional embodiment, the apparatus further includes: The currently generated description information display module is configured to respond to information input instructions and display the currently generated description information in a preset area of ​​the preset generation page, wherein the preset area is the input area for media generated description information; The visual media display module includes: The second visual media display unit is configured to perform the display of the multiple visual media generated based on the currently generated description information and the multiple visual styles.

[0025] In an optional embodiment, the apparatus further includes: The first current parameter display module is configured to execute a first parameter setting instruction and display the first current parameter on the preset generation page. The first current parameter is used to indicate the degree of influence of the current generation description information and the corresponding visual style on each visual media during the generation of each visual media. The second visual media display unit includes: The third visual media display unit is configured to perform the display of multiple visual media generated based on the currently generated description information, the multiple visual styles, and the first current parameter.

[0026] In an optional embodiment, the currently generated description information includes a current reference image; the plurality of visual media are images of the plurality of visual styles corresponding to the current reference image; the visual media display module includes: The fourth visual media display unit is configured to display the multiple visual media based on a preset style template.

[0027] In an optional embodiment, the multiple visual styles are based on multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; the device further includes: The first style description information display module is configured to display the style description information of the various custom styles; The first storage module is configured to execute storage instructions in response to multiple custom styles, and to store style description information for the multiple custom styles.

[0028] In an optional embodiment, the apparatus further includes: The sharing module is configured to execute a preset sharing command to share the various custom styles and / or the various visual media corresponding to the various custom styles to the user account in the current platform.

[0029] In an optional embodiment, the multiple visual styles are based on multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; the device further includes: The second style description information display module is configured to execute a style customization instruction corresponding to the first visual media and display the custom style description information corresponding to the visual style of the first visual media. The second storage module is configured to execute a storage instruction in response to the custom style description information, and store the first visual media and the custom style description information. Wherein, the first visual medium is any one of the multiple visual media.

[0030] In an optional embodiment, the apparatus further includes: The second current parameter display module is configured to, in response to the second parameter setting instruction, display the second current parameter on the preset generation page before the multiple visual media generated by the display are executed. The second current parameter is used to indicate the degree of difference in visual style among the multiple visual media. The various visual styles are randomly determined based on the second current parameter.

[0031] In an optional embodiment, the random style control is initially in an unselected state; the visual media display module includes: The state update unit is configured to execute a response to a selection instruction for the random style control, updating the random style control in the preset generated page from a non-selected state to a selected state. The fifth visual media display unit is configured to display the multiple visual media in response to the visual media generation instruction when the random style control is selected.

[0032] In an optional embodiment, the control display module includes: The preset generated page display unit is configured to execute a page display instruction to display the preset generated page including preset prompt information. The preset prompt information is used to prompt that visual media is generated in a way that randomly determines the style, and the preset prompt information includes the random style control.

[0033] In an optional embodiment, the apparatus further includes: The third style description information display module is configured to display the style description information corresponding to each of the multiple visual styles before or during the display of the multiple visual media.

[0034] In an optional embodiment, the visual media display module includes: The sixth visual media display unit is configured to display the multiple visual media and preset production instruction information; The preset production instruction information is used to instruct media content production based on at least one of the plurality of visual media.

[0035] In an optional embodiment, the plurality of visual media correspond to different visual styles, and the device further includes: The first composite visual media display module is configured to execute a first composite instruction in response to at least two of the plurality of visual media, and display a first composite visual media corresponding to the at least two visual media, wherein the visual style corresponding to the first composite visual media is a mixed style of the visual styles corresponding to the at least two visual media. or, The second composite visual media display module is configured to execute a second composite instruction in response to a visual style corresponding to at least two of the plurality of visual media, and display the second composite visual media corresponding to at least two visual styles, wherein the at least two visual styles are the visual styles corresponding to the at least two visual media.

[0036] In an optional embodiment, the visual media display module includes: The seventh visual media display unit is configured to display a second visual media and style description information corresponding to the second visual media, wherein the second visual media is any one of the plurality of visual media; The visual media switching unit is configured to execute a visual media switching instruction to switch the second visual media and the style description information corresponding to the second visual media to a third visual media and the style description information corresponding to the third visual media, wherein the third visual media is any visual media other than the second visual media among the plurality of visual media.

[0037] In an optional embodiment, the visual media display module includes: The eighth visual media display unit is configured to present the multiple visual media in a blind box style; The ninth visual media display unit is configured to respond to a media viewing instruction and display the visual media corresponding to the media viewing instruction. Wherein, the visual media corresponding to the media viewing instruction is at least one of the plurality of visual media.

[0038] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method as described in any one of the first aspects above.

[0039] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform any one of the methods described in the visual media generation methods of the present disclosure. According to a fifth aspect of the present disclosure, a computer program product including instructions is provided that, when run on a computer, causes the computer to perform the method as described in any one of the first aspects above.

[0040] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: By setting a random style control on the preset generation page, and triggering a visual media generation command based on this random style control, multiple visual media based on various visual styles randomly determined by the current platform are automatically generated. During the visual media generation process, the random style control can automatically and randomly determine multiple visual styles, which greatly improves the convenience and efficiency of interaction during the visual media generation process, and thus greatly enhances the interactive experience. Furthermore, the ability to generate multiple visual media from multiple visual styles randomly determined by the platform can effectively ensure the clarity, accuracy, and diversity of visual style descriptions, thereby effectively improving the diversity and generation effect of visual media.

[0041] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0043] Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment; Figure 2 This is a flowchart illustrating a visual media generation method according to an exemplary embodiment; Figure 3 This is a schematic diagram of a page displaying a preset generated page with random generation controls, according to an exemplary embodiment. Figure 4 This is a schematic diagram of a preset generated page displaying preset prompt information, according to an exemplary embodiment; Figure 5 This is a schematic diagram of a preset generated page that displays random style controls in a style selection area, according to an exemplary embodiment. Figure 6 This is a schematic diagram illustrating a random style control before and after selection, according to an exemplary embodiment; Figure 7 This is a schematic diagram illustrating the page changes of a preset generated page before and after a selection instruction for a random style control is triggered, according to an exemplary embodiment. Figure 8 This is a schematic diagram illustrating the page changes of a preset generated page before and after triggering a selection instruction for a random style control, according to an exemplary embodiment. Figure 9 This is a schematic diagram of a preset generated page according to an exemplary embodiment; Figure 10This is a schematic diagram of another preset generated page according to an exemplary embodiment; Figure 11 This is a block diagram illustrating a visual media generation apparatus according to an exemplary embodiment; Figure 12 This is a block diagram illustrating an electronic device for generating visual media according to an exemplary embodiment. Detailed Implementation

[0044] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0045] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0046] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0047] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment, which may include a terminal 100 and a server 200.

[0048] In an optional embodiment, terminal 100 can be used to provide services such as visual media generation to any user. Specifically, terminal 100 can be, but is not limited to, electronic devices such as smartphones, desktop computers, tablets, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices, or software running on the aforementioned electronic devices, such as applications. Optionally, the operating system running on the electronic device can be, but is not limited to, Android, iOS, Linux, Windows, etc.

[0049] In an optional embodiment, server 200 can provide background services to terminal 100. Optionally, server 200 can combine a pre-trained preset generative model to generate corresponding visual media. Specifically, server 200 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0050] In addition, it should be noted that, Figure 1 The example shown is merely one application environment provided by this disclosure. In practical applications, other application environments may also be included, such as more terminals.

[0051] In the embodiments described in this specification, the terminal 100 and the server 200 can be directly or indirectly connected through wired or wireless communication, and this disclosure does not impose any restrictions.

[0052] Figure 2 This is a flowchart illustrating a visual media generation method according to an exemplary embodiment. This method can be applied to a terminal, such as... Figure 2 As shown, the method may include the following steps: In step S201, random style controls are displayed on the preset generation page.

[0053] In one specific embodiment, the preset generation page can be a page used for visual media generation processing. Visual media can be media that conveys information visually; optionally, visual media can include static media such as images and / or static media such as videos. Specifically, the aforementioned random style control can be used to trigger the random determination of a corresponding visual style during the visual media generation process. Specifically, a visual style can refer to the overall visual characteristics with consistency and recognizability formed by the combination and presentation of visual elements (such as color, shape, lines, composition, fonts, etc.), exemplified by anime style, retro style, and two-dimensional style. Specifically, the display position of the random style control on the preset generation page can be set according to actual application requirements. For example, as shown... Figure 3 As shown, Figure 3 This is a schematic diagram of a preset generated page displaying randomly generated controls, according to an exemplary embodiment, wherein the control corresponding to 301 can be a random style control.

[0054] In an optional embodiment, displaying random style controls on a preset generated page may include: In response to a page display instruction, a preset generated page including preset prompts is displayed. These preset prompts can be used to prompt that visual media is generated using a randomly determined style, and the preset prompts include a random style control.

[0055] In one specific embodiment, the page display instruction can be an instruction to trigger the display of a preset generated page; specifically, the preset prompt information can be used to prompt the generation of visual media using a randomly determined style; for example, the preset prompt information can include text prompt information for prompting the generation of visual media using a randomly determined style, and optionally, it can also include a confirmation control and a cancellation control, the confirmation control being a random style control; optionally, if a touch operation such as clicking the confirmation control is performed, it can be determined that the visual style is randomly determined during the generation of visual media; optionally, if a touch operation such as clicking the cancellation control is performed, triggering the corresponding cancellation instruction, then the corresponding visual style will not be randomly determined during the generation of visual media.

[0056] In practical applications, the preset generated page can provide functions such as generating images from text, images from images, and images from text, as well as generating videos from text, images, and images from text. Optionally, in the initial state, i.e., in response to the page display command, the preset generated page can display a certain preset function interface by default, and other function interfaces can be triggered to be displayed on the preset generated page by switching tabs corresponding to other function interfaces. Accordingly, users can switch between different function interfaces according to their actual needs.

[0057] In a specific embodiment, such as Figure 4 As shown, Figure 4 This is a schematic diagram illustrating a preset generated page displaying preset prompt information, according to an exemplary embodiment; specifically, in conjunction with... Figure 4 The preset generated page shown can be a preset prompt message for page 401, and the "confirmation control" in the preset prompt message can be a random style control.

[0058] In the above embodiments, in response to the page display instruction, when displaying the preset generation page, a preset prompt message is displayed to prompt the user to generate visual media using a randomly determined style. This can actively invite users to experience the function of generating visual media with a random style. The preset prompt message includes a random style control, which allows the platform to automatically and randomly determine the visual style during the visual media generation process, without requiring the user to set the visual style themselves. This effectively ensures the generation effect of the visual media and also improves the convenience and efficiency of user interaction during the visual media generation process.

[0059] In an optional embodiment, displaying random style controls on a preset generated page may include: Random style controls are displayed in the style selection area of ​​the preset generation page.

[0060] In one specific embodiment, the style selection area can be a pre-generated page area used to display the visual styles to be selected. Optionally, the style selection area can also display style description information corresponding to at least one visual style to be selected.

[0061] In a specific embodiment, such as Figure 5 As shown, Figure 5 This is a schematic diagram of a preset generated page that displays random style controls in a style selection area, according to an exemplary embodiment; specifically, in conjunction with... Figure 5 The preset generated page shown can be configured with random style controls for the 501 error.

[0062] In the above embodiments, a random style control is displayed in the style selection area of ​​the preset generation page. The random style can be used as a visual style to be selected. In addition to providing users with a visual style reference, the random style can also be combined to enhance the sense of surprise in the visual media generation process.

[0063] In step S203, in response to the visual media generation instruction triggered by the random style control, multiple generated visual media are displayed. The multiple visual media correspond to multiple visual styles, which are randomly determined by the current platform.

[0064] In an optional embodiment, the random style control may be initially in an unselected state; the multiple visual media generated in response to the visual media generation instruction triggered based on the random style control may include: In response to the selection command for the random style control, update the random style control in the preset generated page from the unselected state to the selected state; With the random style control selected, multiple visual media are displayed in response to visual media generation instructions.

[0065] In one specific embodiment, the selection instruction for the random style control can be an instruction to select the random style control. Optionally, the selection instruction for the random style control can be triggered by touch operations such as clicking or long-pressing a random style control that is not in a selected state. The random style control in the selected state can be used to indicate that the corresponding visual style is randomly determined during the visual media generation process.

[0066] In a specific embodiment, such as Figure 6 As shown, Figure 6 This is a schematic diagram illustrating the selection of a random style control before and after selection, according to an exemplary embodiment; specifically, in conjunction with... Figure 6As shown in the preset generated page (a), the control corresponding to 601 can be a random-style control in an unselected state; optionally, when a selection command for a random-style control is triggered, combined with... Figure 6 As shown in the preset generated page (b), the control corresponding to 602 can be a randomly styled control that is selected.

[0067] In the above embodiments, a random style control that is not selected is first displayed on the preset generation page. Then, by triggering a selection command for the random style control, the random style control is selected so that the platform can automatically and randomly determine the visual style during the generation of visual media. This not only improves the convenience and efficiency of setting random styles, but also effectively ensures the clarity, accuracy and diversity of visual style descriptions, thereby effectively improving the generation effect of visual media.

[0068] In an optional embodiment, the above-mentioned response to a visual media generation instruction triggered based on a random style control, displaying multiple generated visual media may include: In response to the selection command for the random style control, random style description information is displayed in the preset area of ​​the preset generation page. The preset area is the input area for media generation description information. When a preset area displays descriptions with a random style, multiple visual media are displayed in response to visual media generation instructions.

[0069] In one specific embodiment, the aforementioned preset area can be an input area for media generation description information, and the random style description information can be information describing a random style. For example, the random style description information can be "random style". The preset area displaying the random style description information can be used to indicate that the corresponding visual style is randomly determined during the visual media generation process. Optionally, when a selection instruction is triggered, the random style control can be updated from a non-selected state to a selected state, or the display of the random style control can be canceled.

[0070] In one specific embodiment, taking the random style control displayed in the style selection area, and the random style control updating from a non-selected state to a selected state when a selection command is triggered as an example, such as... Figure 7 As shown, Figure 7 This is a schematic diagram illustrating the page changes of a preset generated page before and after triggering a selection instruction for a random style control, according to an exemplary embodiment; specifically, in conjunction with... Figure 7 The preset generated page shown in section a, where the control corresponding to 701 can be a random-style control in an unselected state, can optionally be combined with a selection command for the random-style control when triggered. Figure 7In the preset generated page shown in b, the control corresponding to 702 can be a random style control that is selected; and the area corresponding to 703 can be a preset area that displays random style description information.

[0071] In another specific embodiment, taking the example of a random style control displayed in the style selection area, and the random style control being dedisplayed when a selection command is triggered, as follows: Figure 8 As shown, Figure 8 This is a schematic diagram illustrating page changes before and after triggering a selection instruction for a random style control, according to an exemplary embodiment; specifically, in conjunction with... Figure 8 The preset generated page shown in section a has a control corresponding to 801 that can be a random style control. Optionally, when a selection command for a random style control is triggered, it can be combined with... Figure 8 The preset generated page shown in b can display random style description information in preset area 802, and the random style control can be hidden. Optionally, it can be combined with... Figure 8 As can be seen, when the random style control is de-displayed, the style description information corresponding to at least one (or multiple) candidate visual styles in the selectable style area can also be de-displayed.

[0072] In the above embodiments, when a selection instruction for a random style control displayed on a preset generation page is triggered, random style description information is displayed in the input area of ​​media generation description information on the preset generation page. This allows users to more intuitively and clearly perceive that the visual style of the visual media to be generated has been determined by the platform's random style selection method, thereby improving the user's interactive experience.

[0073] In one specific embodiment, the visual media generation instruction can be an instruction to generate visual media. A visual media generation instruction triggered by a random style control can be a visual media generation instruction triggered when the random style is determined to be the visual style during the visual media generation process (i.e., the corresponding visual style is randomly determined). Optionally, the preset generation page can display preset generation controls (controls used to trigger the visual media generation instruction). Optionally, the aforementioned visual media generation instruction can be triggered through touch operations such as clicking or long-pressing the preset generation control. For example, Figure 6 The control corresponding to 603 can be a preset generated control.

[0074] In another alternative embodiment, the corresponding visual media generation instruction can also be triggered directly by randomly generating controls. For example, while clicking or long-pressing the randomly generated control to trigger the selection instruction for the randomly generated control, the visual media generation instruction can be automatically triggered.

[0075] In one specific embodiment, the aforementioned multiple visual media correspond to multiple visual styles, and these multiple visual media can correspond to different visual styles. Specifically, each visual media can correspond to at least one visual style. The aforementioned multiple visual styles are randomly determined by the current platform. Optionally, the current platform can be the platform currently providing visual media generation services. Optionally, the current platform can randomly determine multiple visual styles from a preset visual style library. Specifically, the preset visual style library can include a large number (multiple) preset visual styles. Specifically, the preset visual styles in the preset visual style library can be set according to actual conditions.

[0076] In an optional embodiment, the above-mentioned multiple visual styles are randomly determined based on the interest visual style corresponding to the current account. The interest visual style is determined by style recognition based on the historical style interaction information corresponding to the current account and / or the high-frequency style description information corresponding to the current platform using a preset visual style recognition model. The historical style interaction information is used to indicate the interaction operation performed by the current account for at least one visual style within a preset historical time period.

[0077] In a specific embodiment, the preset historical time period can be set according to the actual application. The aforementioned interactive operations may include style selection operations for corresponding visual styles, download operations for visual media for corresponding visual styles, sharing operations for visual media for corresponding visual styles, positive feedback operations (e.g., liking) for visual media for corresponding visual styles, negative feedback operations (e.g., disliking) for visual media for corresponding visual styles, and rating operations for visual media for corresponding visual styles. Specifically, the historical style interaction information can be the operation record information of the corresponding interactive operations; the high-frequency style description information corresponding to the current platform can be the high-frequency description information related to the visual style in the generated description information entered by the user account in the current platform (e.g., generated description information that appears more than a preset number of times within a specified time period).

[0078] In one specific embodiment, the historical style interaction information corresponding to the current account and / or the high-frequency style description information corresponding to the current platform can be input into a preset visual style recognition model for visual style recognition processing to obtain the interest visual style corresponding to the current account; optionally, the interest visual style corresponding to the current account may include at least one visual style that the current account is interested in; optionally, in the process of randomly determining multiple visual styles based on the interest visual style corresponding to the current account, multiple visual styles associated with the interest visual style can be randomly matched from a preset visual style library; optionally, if the number of styles included in the interest visual style is greater than the number of styles corresponding to multiple visual styles, multiple visual styles can also be randomly selected from the interest visual style.

[0079] In one specific embodiment, the preset visual style recognition model can be an artificial intelligence model used for visual style recognition.

[0080] In the above embodiments, based on the preset visual style recognition model, the historical style interaction information corresponding to the current account and / or the high-frequency style description information corresponding to the current platform are used to identify the interest visual style corresponding to the current account. In combination with the interest visual style, multiple visual styles are randomly determined to generate multiple visual media. This can improve the randomness and surprise of the generated visual media, while also better meeting user needs and enhancing the personalization of the visual media.

[0081] In an optional embodiment, visual style recommendation processing can also be combined with interest-based visual styles. Optionally, style description information of interest-based visual styles can be displayed in the style selection area for users to choose from.

[0082] In one specific embodiment, multiple visual media can be displayed on a preset generated page or on a new page.

[0083] In an optional embodiment, the above method may further include: Before or when displaying multiple visual media, display style descriptions for each of the various visual styles.

[0084] In one specific embodiment, the display of multiple visual media may be performed before the generation of multiple visual media, or when the random style control is selected. For example, the style description information corresponding to each of the multiple visual styles can be presented in any form such as text or graphics. Optionally, the style description information corresponding to each of the multiple visual styles can be displayed in a preset area, the location of the visual media generation progress bar, or other areas. Optionally, when displaying multiple visual media, the style description information corresponding to each of the multiple visual styles can be displayed together with the corresponding visual media.

[0085] In the above embodiments, displaying style description information corresponding to each of the various visual styles before displaying multiple visual media can inform users of the visual style of the generated visual media in advance, helping users to quickly understand the style of the generated visual media. When displaying multiple visual media, displaying style description information corresponding to each of the various visual styles can create a blind box-like sense of surprise, and can also help users understand the visual style more intuitively by combining the multiple visual media displayed together.

[0086] In one specific embodiment, style description information of multiple randomly determined visual styles can be input into a preset generation model for visual media generation processing to obtain multiple visual media. Specifically, the number of multiple visual media generated can be set according to actual application requirements. Specifically, the preset generation model is a generative model used to generate visual media.

[0087] In an optional embodiment, the above method may further include: In response to the information input command, the currently generated description information is displayed in the preset area of ​​the preset generation page. The preset area is the input area for the media generation description information. Accordingly, the visual media generated by the above display include: Display multiple visual media generated based on the currently generated descriptive information and various visual styles.

[0088] In one specific embodiment, the information input instruction can be an instruction to generate descriptive information from the input; specifically, the currently generated descriptive information can be information describing the visual media to be generated from the current input. Optionally, the information format of the currently generated descriptive information can include at least any of text or images.

[0089] In one specific embodiment, style description information of multiple randomly determined visual styles and current generated description information can be input into a preset generation model for visual media generation processing to obtain multiple visual media.

[0090] In the above embodiments, in response to the information input command, the currently generated description information is displayed in the input area of ​​the media generation description information in the preset generation page. Thus, when the visual media generation command is triggered, multiple visual media can be generated based on the currently generated description information and multiple randomly determined visual styles. This can quickly generate high-quality visual media by combining multiple randomly determined visual styles, while also meeting the user's needs for independent creation and enhancing the personalization of the generated visual media.

[0091] In an optional embodiment, the above method may further include: In response to the first parameter setting command, the first current parameter is displayed on the preset generation page; Accordingly, the aforementioned display of multiple visual media generated based on the currently generated descriptive information and various visual styles may include: Display multiple visual media generated based on the currently generated description information, various visual styles, and the first current parameter.

[0092] In one specific embodiment, the first parameter setting instruction can be an instruction to set a first current parameter; specifically, the first current parameter can be set by direct input or by selecting the first current parameter from multiple selectable parameters. Specifically, the aforementioned first current parameter can be used to indicate the degree of influence of the currently generated description information and corresponding visual style on each visual media during the generation of each visual media.

[0093] In one specific embodiment, style description information of multiple randomly determined visual styles, current generation description information, and first current parameters can be input into a preset generation model for visual media generation processing to obtain multiple visual media.

[0094] In the above embodiments, during the visual media generation process, by setting a first current parameter to indicate the degree of influence of the current generation description information and corresponding visual style on the visual media during the generation of each visual media, the visual media generation effect can be controlled more flexibly, thereby better ensuring the generation effect of the visual media.

[0095] In an optional embodiment, the currently generated description information may include the current reference image; the aforementioned multiple visual media are images of various visual styles corresponding to the current reference image; correspondingly, the multiple visual media displayed include: Display multiple visual media based on preset style templates.

[0096] In one specific embodiment, the preset style template can be a template for the presentation styles of multiple visual media, which can be set according to actual application needs. For example, the preset style template can be a preset splicing template for multiple images, such as a multi-grid splicing template, a horizontal long image template, a vertical image template, etc. For example, the preset style template can be a preset frame-breaking composition template containing multiple images. For example, the preset style template can be a poster style template containing multiple images, etc.

[0097] In the above embodiments, in the scenario of generating multiple images with various visual styles by combining images, displaying multiple images with various visual styles by combining preset style templates can better enhance the visual presentation of the generated images with various visual styles.

[0098] In an optional embodiment, the aforementioned multiple visual styles can be multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; correspondingly, the above method may further include: Displays style descriptions for various custom styles; In response to storage commands for various custom styles, store style description information for various custom styles.

[0099] In one specific embodiment, style description information of multiple custom styles can be displayed before or when multiple visual media are displayed. Optionally, the style description information of multiple custom styles can be displayed on a preset generated page or on a new page.

[0100] In one specific embodiment, the preset generation model, in addition to outputting multiple visual media, can also output style description information corresponding to a custom style for each visual media. Specifically, the style description information for any custom style can be information describing that custom style; specifically, the style description information can be presented in at least one of the following forms: text, image, or graphic-text combination; specifically, the style description information can include at least one of the following: a style name or a style template image. The style template image can be a template image reflecting the corresponding visual style. Optionally, while displaying the style description information for multiple custom styles, a corresponding storage control can be displayed. Correspondingly, storage instructions for multiple custom styles can be triggered by combining this storage control. Specifically, the server can store the style description information for multiple custom styles.

[0101] In the above embodiments, when the multiple visual styles corresponding to the generated multiple visual images are multiple preset visual styles determined by random determination and multiple custom styles determined by the currently generated description information, the style description information of multiple custom styles can be displayed, and in response to the storage instruction for multiple custom styles, the style description information of multiple custom styles can be stored for subsequent use, thereby improving the diversity of visual styles of visual media within the platform.

[0102] In an optional embodiment, the visual style of the visual media pair can also be customized by the user; correspondingly, the above method may further include: In response to style customization instructions for the first visual media, display the custom style description information for the visual style of the first visual media. In response to a storage instruction for custom style description information, store the first visual media and the custom style description information.

[0103] In one specific embodiment, the custom style description information corresponding to the visual style of the first visual media can be displayed on a preset generation page or on a new page.

[0104] In one specific embodiment, the aforementioned first visual media can be any media content from a plurality of visual media. Specifically, the custom style description information corresponding to the first visual media can be custom description information for the visual style corresponding to that first visual media, such as, for example, the corresponding style name, etc. The automatic style customization instruction can be an instruction for editing the custom style description information.

[0105] In one specific embodiment, while displaying the custom style description information corresponding to the visual style of the first visual media, a corresponding storage control can be displayed. Accordingly, this storage control can be used to trigger a storage instruction for the custom style description information. Specifically, the storage instruction for the custom style description information can be an instruction to store the custom style description information and the corresponding first visual media. The first visual media can be used as a style template image for the corresponding custom style. Specifically, the server can store the custom style description information and the corresponding first visual media.

[0106] In the above embodiments, when the multiple visual styles corresponding to the generated multiple visual images are based on multiple preset visual styles determined by random determination and multiple custom styles determined by the currently generated description information, the user can customize the visual style of the visual media pair. This can realize the iterative update of the visual style within the platform and store the corresponding custom style description information and visual media for subsequent use. This can enrich the visual style of the visual media within the platform and also enhance the user's autonomy and the personalization of the visual style.

[0107] In an optional embodiment, the above method may further include: In response to preset sharing commands, share multiple custom styles and / or multiple visual media corresponding to multiple custom styles to user accounts on the current platform.

[0108] In one specific embodiment, the preset sharing instruction can be an instruction to share multiple custom styles and / or the aforementioned multiple visual media corresponding to multiple custom styles to a user account on the current platform. Optionally, while displaying the style description information of multiple visual media and multiple custom styles, a corresponding sharing control can be displayed. Accordingly, multiple custom styles and / or multiple visual media corresponding to multiple custom styles can be triggered based on the corresponding sharing control. Specifically, sharing multiple custom styles can mean sharing the style description information of multiple custom styles.

[0109] In one specific embodiment, the user account in the current platform can be a user account specified by the current account in the current platform, or it can be any user account in the current platform.

[0110] In the above embodiments, in response to a preset sharing instruction, multiple custom styles and / or multiple visual media corresponding to multiple custom styles are shared with user accounts on the current platform. This can enrich the visual styles of visual media on the platform, while also improving the user's interactive experience and the interactivity between users on the platform.

[0111] In an optional embodiment, the method may further include the following before displaying the generated multiple visual media: In response to the second parameter setting command, the second current parameter is displayed on the preset generation page; In one specific embodiment, the second parameter setting instruction can be an instruction to set a second current parameter; specifically, the second current parameter can be set by directly inputting it or by selecting a second previous parameter from multiple selectable parameters.

[0112] In one specific embodiment, the aforementioned second current parameter is used to indicate the degree of difference in visual styles among multiple visual media. Accordingly, in the process of randomly determining multiple visual styles, the second current parameter can be incorporated, meaning that multiple visual styles are randomly determined based on the second current parameter. Optionally, the similarity between any two visual styles in a preset visual style library can be determined. Accordingly, multiple visual styles where the similarity between any two visual styles is less than a preset similarity threshold can be randomly selected in conjunction with the second current parameter. Optionally, the preset similarity threshold can be set in conjunction with the second current parameter. Optionally, the larger the second current parameter (the greater the difference), the smaller the preset similarity threshold; conversely, the smaller the second current parameter (the smaller the difference), the larger the preset similarity threshold.

[0113] In the above embodiments, during the process of generating visual media using random styles, by setting a second current parameter to indicate the degree of visual style differences among multiple visual media, the differences among the generated multiple visual media can be flexibly controlled, thereby better meeting the different visual media generation needs of users.

[0114] In an optional embodiment, the multiple visual media generated as shown above may include: Displays multiple visual media and preset production instructions; In one specific embodiment, preset production instructions are used to instruct media content creation based on at least one of a plurality of visual media. Optionally, the preset production instructions may include text prompts instructing media content creation based on at least one of a plurality of visual media, and may also include operation controls that trigger media content creation based on at least one of a plurality of visual media. Specifically, users can combine at least one of a plurality of visual media to perform further media content creation processing such as image-to-video conversion and video secondary creation, according to actual application needs.

[0115] In the above embodiments, while displaying multiple generated visual media, preset production instruction information is also displayed to instruct the production of media content based on at least one of the multiple visual media. This can improve the convenience of users in creating media content and also better enrich the media content within the platform.

[0116] In an optional embodiment, multiple visual media correspond to different visual styles, and the above method may further include: In response to a first composition instruction for at least two visual media among a plurality of visual media, display the first composite visual media corresponding to the at least two visual media; or, In response to a second composition instruction for at least two visual media corresponding to visual styles among a plurality of visual media, display the second composite visual media corresponding to at least two visual styles.

[0117] In one specific embodiment, the first compositing instruction can be an instruction to compose at least two visual media among multiple visual media. Optionally, while displaying multiple visual media, corresponding compositing controls can be displayed. Optionally, when at least two visual media are selected, the first compositing instruction can be triggered by touch operations such as clicking or long-pressing the corresponding compositing controls, and the first synthesized visual media corresponding to the at least two visual media can be displayed. Specifically, the first synthesized visual media can be visual media synthesized based on at least two visual media. Optionally, at least two visual media can be input into a preset media compositing model to obtain the first synthesized visual media. Correspondingly, the visual style corresponding to the first synthesized visual media is a mixed style of the visual styles corresponding to the at least two visual media. Specifically, the preset media compositing model can be an artificial intelligence model used for media compositing.

[0118] In one specific embodiment, the second compositing instruction can be an instruction to compose visual media corresponding to at least two visual media out of multiple visual media. Optionally, while displaying multiple visual media, corresponding compositing controls can be displayed. Optionally, when at least two visual media are selected, the second compositing instruction can be triggered by touch operations such as clicking or long-pressing the corresponding compositing controls, and the second composite visual media corresponding to at least two visual styles can be displayed. Specifically, the at least two visual styles are the visual styles corresponding to at least two visual media. Optionally, the style description information of the at least two visual styles can be input into a preset generation model to obtain the second composite visual media.

[0119] In the above embodiments, by synthesizing at least two visual media from multiple visual media, or by synthesizing the visual styles corresponding to at least two visual media, a corresponding hybrid style of synthesized visual media is obtained. This can enrich the visual media within the platform and also enhance the diversity of the corresponding styles of the visual media within the platform.

[0120] In an optional embodiment, the multiple visual media generated as shown above may include: Display the style description information corresponding to the second visual media; In response to the visual media switching command, the style description information corresponding to the second visual media and the second visual media is switched to the style description information corresponding to the third visual media.

[0121] In one specific embodiment, the second visual media can be any one of multiple visual media; the style description information corresponding to the second visual media can be the style description information of the visual style corresponding to the second visual media; specifically, the third visual media can be any visual media other than the second visual media among the multiple visual media. The visual media switching instruction can be an instruction to switch the currently displayed visual media and its corresponding style description information; optionally, the visual media switching instruction can be triggered by touch operations such as double-clicking or swiping.

[0122] In one specific embodiment, taking multiple visual media as multiple images as an example, such as... Figure 9 As shown, Figure 9 This is a schematic diagram of a preset generated page according to an exemplary embodiment; wherein, the image corresponding to 901 can be a second visual media, and the information corresponding to 902 can be style description information corresponding to the second visual media; optionally, a visual media switching command can be triggered by a left-right swipe touch operation to switch the second visual media and the style description information corresponding to the second visual media to a third visual media and the style description information corresponding to the third visual media.

[0123] In the above embodiments, during the display of multiple visual media, each visual media and its corresponding style description information are gradually displayed by switching them one by one. This can create an atmosphere of continuous unveiling, enhance the interactivity and fun of the visual media presentation process, and also better enhance the sense of surprise in the unveiling of the visual media and its corresponding visual style.

[0124] In an optional embodiment, the multiple visual media generated as shown above may include: Presenting multiple visual media in a blind box style; In response to a media viewing command, display the visual media corresponding to the media viewing command; In one specific embodiment, the multiple visual media presented in the blind box style can be multiple visual media presented as blind boxes; the visual media corresponding to the media viewing instruction is at least one of the multiple visual media, and correspondingly, the media viewing instruction can be a viewing instruction for at least one visual media; optionally, the display of a visual media can be triggered by clicking the touch operation of the blind box corresponding to a certain visual media, or the display of multiple visual media can be triggered with one click by a preset activation control (used to trigger the display of multiple visual media). Optionally, while displaying the visual media, corresponding style description information can also be displayed.

[0125] In a specific embodiment, such as Figure 10 As shown, Figure 10 This is a schematic diagram of another preset generated page according to an exemplary embodiment; wherein, the blind box corresponding to 1001 can be multiple visual media presented in the style of blind boxes; and the control corresponding to 1002 can be a preset opening control.

[0126] In the above embodiments, multiple visual media are presented in a blind box style, and media viewing instructions are displayed. The visual media corresponding to the media viewing instructions are displayed, which can enhance the interactive fun during the presentation of visual media, and also better enhance the sense of surprise when the visual media is revealed.

[0127] In an alternative embodiment, users can also directly input the corresponding generation description information according to their actual needs to generate visual media with a custom style.

[0128] Furthermore, it should be noted that the "multiple" in the embodiments of this application can be at least two, and the "multiple" can be at least two. The instructions triggered by touch operations in the embodiments of this application can also be triggered by corresponding voice control operations, device movement operations, etc.

[0129] As can be seen from the technical solutions provided in the embodiments of this specification above, this specification sets a random style control on the preset generation page, and automatically generates multiple visual media based on multiple visual styles randomly determined by the current platform when a visual media generation instruction is triggered based on the random style control. In the process of visual media generation, multiple visual styles can be automatically and randomly determined by the random style control, which greatly improves the interactive convenience and efficiency in the process of visual media generation, and thus greatly improves the interactive experience. Moreover, multiple visual media can be generated by multiple visual styles randomly determined by the platform, which can also effectively ensure the clarity, accuracy and diversity of visual style descriptions, thereby effectively improving the diversity and generation effect of visual media.

[0130] Figure 11 This is a block diagram illustrating a visual media generation apparatus according to an exemplary embodiment. (Refer to...) Figure 11 The device includes: The control display module 1110 is configured to display random-style controls on a preset generated page; The visual media display module 1120 is configured to execute a visual media generation command triggered by a random style control, and display multiple generated visual media. The multiple visual media correspond to multiple visual styles, which are randomly determined by the current platform.

[0131] In an optional embodiment, multiple visual styles are randomly determined based on the interest visual styles corresponding to the current account. The interest visual styles are determined by style recognition based on the historical style interaction information corresponding to the current account and / or the high-frequency style description information corresponding to the current platform, using a preset visual style recognition model. The historical style interaction information is used to indicate the interaction operations performed by the current account for at least one visual style within a preset historical time period.

[0132] In an optional embodiment, the control display module 1110 is specifically configured to display random style controls in the style selection area of ​​a preset generated page.

[0133] In an optional embodiment, the visual media display module 1120 includes: The random style description information display unit is configured to respond to the selection command for the random style control and display random style description information in a preset area of ​​the preset generation page. The preset area is the input area for media generation description information. The first visual media display unit is configured to display multiple visual media in response to visual media generation instructions, provided that random style descriptive information is displayed in a preset area.

[0134] In an optional embodiment, the above-described apparatus further includes: The module for displaying the currently generated description information is configured to respond to information input commands and display the currently generated description information in a preset area of ​​the preset generation page. The preset area is the input area for media-generated description information. Visual media display module 1120 includes: The second visual media display unit is configured to perform the display of multiple visual media generated based on the currently generated descriptive information and various visual styles.

[0135] In an optional embodiment, the above-described apparatus further includes: The first current parameter display module is configured to execute a response to the first parameter setting instruction and display the first current parameter on the preset generation page. The first current parameter is used to indicate the current generation description information and corresponding visual style during the generation of each visual media, and the degree of influence on each visual media. The second visual media display unit includes: The third visual media display unit is configured to perform the display of multiple visual media generated based on the currently generated description information, multiple visual styles, and the first current parameter.

[0136] In an optional embodiment, the currently generated description information includes a current reference image; multiple visual media are images of various visual styles corresponding to the current reference image; the visual media display module 1120 includes: The fourth visual media display unit is configured to display multiple visual media based on a preset style template.

[0137] In an optional embodiment, the multiple visual styles are based on multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; the above apparatus further includes: The first style description information display module is configured to display style description information for various custom styles; The first storage module is configured to execute storage instructions in response to various custom styles, storing style description information for various custom styles.

[0138] In an optional embodiment, the above-described apparatus further includes: The sharing module is configured to execute a preset sharing command to share multiple custom styles and / or multiple visual media corresponding to multiple custom styles to user accounts on the current platform.

[0139] In an optional embodiment, the multiple visual styles are based on multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; the above apparatus further includes: The second style description information display module is configured to execute a style customization instruction corresponding to the first visual media and display the custom style description information corresponding to the visual style of the first visual media. The second storage module is configured to execute a storage instruction in response to custom style description information, and store the first visual media and the custom style description information. Among them, the first visual media refers to any one of the multiple visual media.

[0140] In an optional embodiment, the above-described apparatus further includes: The second current parameter display module is configured to, in response to the second parameter setting instruction, display the second current parameter on the preset generation page before displaying the multiple generated visual media. The second current parameter is used to indicate the degree of difference in visual style among the multiple visual media. Among them, multiple visual styles are randomly determined based on the second current parameter.

[0141] In an optional embodiment, the random style control is initially in an unselected state; the visual media display module 1120 includes: The state update unit is configured to execute a response to a selection instruction for a random style control, updating the random style control in the preset generated page from a non-selected state to a selected state. The fifth visual media display unit is configured to display multiple visual media in response to visual media generation instructions when the random style control is selected.

[0142] In an optional embodiment, the control display module 1110 includes: The preset generated page display unit is configured to execute a page display instruction and display a preset generated page including preset prompt information. The preset prompt information is used to prompt that visual media is generated in a way that randomly determines the style, and the preset prompt information includes a random style control.

[0143] In an optional embodiment, the above-described apparatus further includes: The third style description information display module is configured to display style description information corresponding to each of the various visual styles before or when displaying multiple visual media.

[0144] In an optional embodiment, the visual media display module 1120 includes: The sixth visual media display unit is configured to display multiple visual media and preset production instructions. Among them, the preset production instruction information is used to instruct media content production based on at least one of multiple visual media.

[0145] In an optional embodiment, multiple visual media correspond to different visual styles, and the device further includes: The first composite visual media display module is configured to execute a first composite instruction in response to at least two of the multiple visual media, and display the first composite visual media corresponding to the at least two visual media, wherein the visual style corresponding to the first composite visual media is a mixed style of the visual styles corresponding to the at least two visual media. or, The second composite visual media display module is configured to execute a second composite instruction in response to a visual style corresponding to at least two of the multiple visual media, and display the second composite visual media corresponding to at least two visual styles, wherein the at least two visual styles are the visual styles corresponding to at least two visual media.

[0146] In an optional embodiment, the visual media display module 1120 includes: The seventh visual media display unit is configured to display the style description information corresponding to the second visual media, where the second visual media is any one of multiple visual media. The visual media switching unit is configured to execute a visual media switching instruction to switch the style description information corresponding to the second visual media and the second visual media to the style description information corresponding to the third visual media, wherein the third visual media is any visual media other than the second visual media among a plurality of visual media.

[0147] In an optional embodiment, the visual media display module 1120 includes: The eighth visual media display unit is configured to present multiple visual media in a blind box style; The ninth visual media display unit is configured to respond to media viewing commands and display the visual media corresponding to the media viewing commands. The visual media corresponding to the media viewing command is at least one of multiple visual media.

[0148] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0149] Figure 12 This is a block diagram illustrating an electronic device for visual media generation according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 12As shown. This electronic device may include an RF (Radio Frequency) circuit 1210, a memory 1220 including one or more computer-readable storage media, an input unit 1230, a display unit 1240, a sensor 1250, an audio circuit 1260, a WiFi (Wireless Fidelity) module 1270, a processor 1280 including one or more processing cores, and a power supply 1290, among other components. Those skilled in the art will understand that... Figure 12 The terminal structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: RF circuit 1210 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and hands it over to one or more processors 1280 for processing; additionally, it transmits uplink data to the base station. Typically, RF circuit 1210 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, etc. Furthermore, RF circuit 1210 can also communicate wirelessly with networks and other terminals. Wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System for Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), etc.

[0150] The memory 1220 can be used to store software programs and modules. The processor 1280 executes various functional applications and data processing by running the software programs and modules stored in the memory 1220. The memory 1220 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for the functions, etc.; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 1220 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 1220 may also include a memory controller to provide access to the memory 1220 by the processor 1280 and the input unit 1230.

[0151] The input unit 1230 can be used to receive input numerical or character information, and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. Specifically, the input unit 1230 may include a touch-sensitive surface 1231 and other input devices 1232. The touch-sensitive surface 1231, also known as a touch display screen or touchpad, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch-sensitive surface 1231), and drive the corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface 1231 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 1280, and can receive and execute commands from the processor 1280. In addition, the touch-sensitive surface 1231 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides the touch-sensitive surface 1231, the input unit 1230 may also include other input devices 1232. Specifically, other input devices 1232 may include, but are not limited to, one or more of the following: a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick. The display unit 1240 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the terminal. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. The display unit 1240 may include a display panel 1241, which may optionally be configured as an LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or similar display panel 1241. Further, a touch-sensitive surface 1231 may cover the display panel 1241. When the touch-sensitive surface 1231 detects a touch operation on or near it, it transmits the information to the processor 1280 to determine the type of touch event. Subsequently, the processor 1280 provides corresponding visual output on the display panel 1241 according to the type of touch event. The touch-sensitive surface 1231 and the display panel 1241 can be two independent components to implement input and output functions. However, in some embodiments, the touch-sensitive surface 1231 and the display panel 1241 can be integrated to achieve both input and output functions.

[0152] The terminal may also include at least one sensor 1250, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 1241 according to the ambient light level, and the proximity sensor can turn off the display panel 1241 and / or the backlight when the terminal is moved to the ear. As a type of motion sensor, a gravity acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that identify the terminal's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometer, tapping), etc. Other sensors that may be configured on the terminal, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0153] Audio circuitry 1260, speaker 1261, and microphone 1262 provide an audio interface between the user and the terminal. Audio circuitry 1260 converts received audio data into electrical signals, which are then transmitted to speaker 1261, where they are converted into sound signals for output. Conversely, microphone 1262 converts collected sound signals into electrical signals, which are received by audio circuitry 1260, converted back into audio data, and then processed by processor 1280 before being transmitted via RF circuitry 1210 to, for example, another terminal, or output to memory 1220 for further processing. Audio circuitry 1260 may also include an earphone jack to facilitate communication between a peripheral headset and the terminal.

[0154] WiFi is a short-range wireless transmission technology. This terminal, through the WiFi module 1270, can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 12 WiFi module 1270 is shown, but it is understood that it is not an essential component of the terminal and can be omitted as needed without changing the nature of the invention.

[0155] The processor 1280 is the control center of the terminal, connecting various parts of the terminal through various interfaces and lines. It executes software programs and / or modules stored in the memory 1220, and calls data stored in the memory 1220 to perform various functions and process data, thereby enabling overall monitoring of the terminal. Optionally, the processor 1280 may include one or more processing cores; preferably, the processor 1280 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1280.

[0156] The terminal also includes a power supply 1290 (such as a battery) to power various components. Preferably, the power supply can be logically connected to the processor 1280 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 1290 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0157] Although not shown, the terminal may also include a camera, Bluetooth module, etc., which will not be described in detail here. Specifically, in this embodiment, the display unit of the terminal is a touch screen display, and the terminal also includes a memory and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors of the instructions in the method embodiment of the present invention.

[0158] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the visual media generation method as described in the embodiments of this disclosure.

[0159] In an exemplary embodiment, a computer-readable storage medium is also provided, wherein when the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the visual media generation method of the present disclosure embodiments. In an exemplary embodiment, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform the visual media generation method of the present disclosure embodiments.

[0160] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0161] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0162] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for generating visual media, characterized in that, include: Display randomly styled controls on the preset generated page; In response to a visual media generation instruction triggered by the random style control, multiple generated visual media are displayed. These multiple visual media correspond to multiple visual styles, which are randomly determined by the current platform.

2. The visual media generation method according to claim 1, characterized in that, The multiple visual styles are randomly determined based on the interest visual styles corresponding to the current account. The interest visual styles are determined based on the historical style interaction information corresponding to the current account and / or the high-frequency style description information corresponding to the current platform, using a preset visual style recognition model. The historical style interaction information is used to indicate the interactive operations performed by the current account for at least one visual style within a preset historical time period.

3. The visual media generation method according to claim 1, characterized in that, The step of displaying random style controls on the preset generation page includes: The random style control is displayed in the style selection area of ​​the preset generation page.

4. The visual media generation method according to claim 1, characterized in that, The response to the visual media generation instruction triggered based on the random style control, displaying multiple generated visual media includes: In response to a selection instruction for the random style control, random style description information is displayed in a preset area of ​​the preset generation page, where the preset area is the input area for media generation description information. When the random style description information is displayed in the preset area, the multiple visual media are displayed in response to the visual media generation instruction.

5. The visual media generation method according to claim 1, characterized in that, The method further includes: In response to an information input command, the currently generated description information is displayed in a preset area of ​​the preset generation page, where the preset area is the input area for media generation description information; The multiple visual media generated by the display include: Display the multiple visual media generated based on the currently generated description information and the multiple visual styles.

6. The visual media generation method according to claim 5, characterized in that, The method further includes: In response to the first parameter setting instruction, the first current parameter is displayed on the preset generation page. The first current parameter is used to indicate the degree of influence of the current generation description information and the corresponding visual style on each visual media during the generation of each visual media. The display of the multiple visual media generated based on the currently generated description information and the multiple visual styles includes: Display the multiple visual media generated based on the currently generated description information, the multiple visual styles, and the first current parameter.

7. The visual media generation method according to claim 5, characterized in that, The currently generated description information includes the current reference image; The plurality of visual media are images of the plurality of visual styles corresponding to the current reference image; The multiple visual media generated by the display include: The multiple visual media are displayed based on preset style templates.

8. The visual media generation method according to claim 5, characterized in that, The multiple visual styles are based on multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; the method further includes: Display style description information for the various custom styles; In response to storage instructions for multiple custom styles, style description information for the multiple custom styles is stored.

9. The visual media generation method according to claim 8, characterized in that, The method further includes: In response to a preset sharing command, the various custom styles and / or the various visual media corresponding to the various custom styles are shared with the user account on the current platform.

10. The visual media generation method according to claim 5, characterized in that, The multiple visual styles are based on multiple preset visual styles determined randomly and multiple custom styles determined by the currently generated description information; the method further includes: In response to the style customization command corresponding to the first visual media, display the custom style description information of the visual style corresponding to the first visual media; In response to a storage instruction for the custom style description information, the first visual media and the custom style description information are stored; Wherein, the first visual medium is any one of the multiple visual media.

11. The visual media generation method according to any one of claims 1 to 9, characterized in that, Prior to displaying the generated multiple visual media, the method further includes: In response to the second parameter setting instruction, a second current parameter is displayed on the preset generation page. The second current parameter is used to indicate the degree of difference in visual style among the multiple visual media. The various visual styles are randomly determined based on the second current parameter.

12. The visual media generation method according to any one of claims 1 to 9, characterized in that, The random style control is initially in an unselected state; the multiple visual media generated in response to the visual media generation instruction triggered based on the random style control include: In response to the selection instruction for the random style control, the random style control in the preset generated page is updated from a non-selected state to a selected state; When the random style control is selected, the multiple visual media are displayed in response to the visual media generation instruction.

13. The visual media generation method according to any one of claims 1 to 9, characterized in that, The step of displaying random style controls on the preset generation page includes: In response to a page display instruction, a preset generated page including preset prompt information is displayed. The preset prompt information is used to prompt that visual media is generated using a randomly determined style, and the preset prompt information includes the random style control.

14. The visual media generation method according to any one of claims 1 to 9, characterized in that, The method further includes: Before or during the presentation of the multiple visual media, display style description information corresponding to each of the multiple visual styles.

15. The visual media generation method according to any one of claims 1 to 9, characterized in that, The multiple visual media generated by the display include: Display the multiple visual media and preset production instructions; The preset production instruction information is used to instruct media content production based on at least one of the plurality of visual media.

16. The visual media generation method according to any one of claims 1 to 9, characterized in that, The multiple visual media correspond to different visual styles, and the method further includes: In response to a first synthesis instruction for at least two of the plurality of visual media, a first synthesized visual media corresponding to the at least two visual media is displayed, wherein the visual style corresponding to the first synthesized visual media is a mixed style of the visual styles corresponding to the at least two visual media. or, In response to a second composition instruction for a visual style corresponding to at least two of the plurality of visual media, a second composite visual media corresponding to at least two visual styles is displayed, wherein the at least two visual styles are the visual styles corresponding to the at least two visual media.

17. The visual media generation method according to any one of claims 1 to 9, characterized in that, The multiple visual media generated by the display include: Display a second visual medium and its corresponding style description information, wherein the second visual medium is any one of the plurality of visual media; In response to a visual media switching command, the second visual media and its corresponding style description information are switched to a third visual media and its corresponding style description information, wherein the third visual media is any visual media other than the second visual media among the plurality of visual media.

18. The visual media generation method according to any one of claims 1 to 9, characterized in that, The multiple visual media generated by the display include: The aforementioned visual media are presented in a blind box style; In response to a media viewing command, display the visual media corresponding to the media viewing command; Wherein, the visual media corresponding to the media viewing instruction is at least one of the plurality of visual media.

19. A visual media generation device, characterized in that, include: The control display module is configured to display randomly styled controls on a preset generated page; The visual media display module is configured to execute a visual media generation instruction triggered based on the random style control, and display multiple generated visual media, which correspond to multiple visual styles, and the multiple visual styles are randomly determined by the current platform.

20. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the visual media generation method as described in any one of claims 1 to 18.

21. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the visual media generation method as described in any one of claims 1 to 18.

Images