Comment processing method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to a comment processing method and device, an electronic device and a storage medium. The method comprises displaying a plurality of preset image generation portals on a comment editing panel of a target comment object; wherein the plurality of preset image generation portals are used to trigger different preset image generation networks to generate a comment image corresponding to the target comment object. The present disclosure can realize the application of artificial intelligence image generation in the comment process, enrich the artificial intelligence image generation function in the comment process, and improve the novelty and interest of the comment method. By displaying a plurality of preset image generation portals on the comment editing panel, the convenience of users in using the artificial intelligence image generation function is greatly improved, and the users can conveniently use the artificial intelligence image generation function in the comment editing process. At the same time, the users can be effectively stimulated to interact with the comment, the interactivity is improved, and the users can better understand the target comment object with better comment information.

Description

Technical Field

[0001] This disclosure relates to the field of Internet technology, and in particular to a comment processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of internet technology and the widespread use of mobile devices, watching short videos and other multimedia content and purchasing goods using mobile devices has become a part of people's daily lives. Users often leave comments on the multimedia content they watch or the goods they buy.

[0003] In related technologies, users can only edit comment information by uploading pre-taken images or common emojis, in addition to editing the comment text. This results in a lack of novelty and fun in the commenting methods, failing to effectively stimulate user interaction and leading to poor interactivity. Summary of the Invention

[0004] This disclosure provides a comment processing method, apparatus, electronic device, and storage medium to at least address the technical problems in related technologies, such as the lack of novelty and interest in comment methods, the inability to effectively stimulate user interaction in comments, and the resulting poor interactivity. The technical solution of this disclosure is as follows: According to a first aspect of the present disclosure, a comment processing method is provided, comprising: The comment editing panel for the target commenter displays multiple preset image entry points; The multiple preset raw image entry points are used to trigger the generation of comment images corresponding to the target comment object based on different preset image generation networks. Each preset raw image entry point is used to trigger the generation of a corresponding comment image based on the preset image generation network corresponding to each preset raw image entry point.

[0005] In one optional embodiment, the plurality of preset raw image entry points include at least two of the following: text-based raw image entry point, image-based raw image entry point, graffiti-based raw image entry point, and text-based image entry point.

[0006] In an optional embodiment, displaying multiple preset raw image entry points in the comment editing panel of the target comment object includes: In response to a comment trigger command for the target comment object, the comment editing panel, including the various preset raw image entry points, is displayed.

[0007] In an optional embodiment, the method further includes: In response to a comment trigger command for the target comment object, an initial comment editing panel is displayed, which displays raw image entry trigger information; The method of displaying multiple preset raw image entry points in the comment editing panel of the target commenter includes: In response to the raw image entry display instruction triggered based on the raw image entry trigger information, the initial comment editing panel is updated to display the comment editing panel with the multiple preset raw image entries.

[0008] In an optional embodiment, the method further includes: When the generation of a target comment image corresponding to the target comment object is triggered based on the target raw image entry, the target comment image is displayed in the comment editing panel. The target raw image entry is any one of the multiple preset raw image entries. The target comment image is generated based on the preset image generation network corresponding to the target raw image entry. In response to a comment posting instruction, comment information, including the target comment image, is displayed in the comment display area corresponding to the target comment object.

[0009] In an optional embodiment, when the generation of the target comment image corresponding to the target comment object is triggered based on the target raw image entry, displaying the target comment image in the comment editing panel includes: In response to a raw image trigger command triggered based on the target raw image entry, raw image editing operation information is displayed; When the image description information is edited based on the raw image editing operation information and the raw image confirmation command is triggered, at least one generated image is displayed. The at least one generated image is an image generated based on the image description information and the preset image generation network corresponding to the target raw image entry. In response to an image confirmation command for the target comment image, the target comment image is displayed in the comment editing panel, wherein the target comment image is any one of the at least one generated image.

[0010] In an optional embodiment, when the target raw image entry is a text-based raw image entry, the image description information is edited text information; the preset image generation network corresponding to the target raw image entry is a text-based raw image network, and the at least one generated image is an image generated based on the edited text information and the text-based raw image network.

[0011] In an optional embodiment, when the target raw image entry is a graph-generated image entry, the image description information is a selected image; the preset image generation network corresponding to the target raw image entry is a graph-generated image network, and the at least one generated image is an image generated based on the selected image and the graph-generated image network.

[0012] In an optional embodiment, when the target raw image entry is a graffiti raw image entry, the image description information is an edited graffiti image; the preset image generation network corresponding to the target raw image entry is a graffiti raw image network, and the at least one generated image is an image generated based on the edited graffiti image and the graffiti raw image network.

[0013] In an optional embodiment, when the target image entry is a text-based image entry, the image description information is edited text-based information; the preset image generation network corresponding to the target image entry is a text-based image network, and the at least one generated image is an image generated based on the edited text-based information and the text-based image network.

[0014] In an optional embodiment, the at least one generated image includes a plurality of first generated images, which are generated images of a plurality of first preset styles; displaying the at least one generated image includes: Display the target generated image and the first style switching controls corresponding to each of the various first preset styles; The target generated image is a generated image of the first target style among the multiple first preset styles; any first style switching control is used to trigger the switching of the currently displayed generated image to the corresponding first preset style generated image.

[0015] In an optional embodiment, the at least one generated image includes an initial generated image; the image style of the initial generated image is a second target style among a plurality of second preset styles; displaying the at least one generated image includes: Display the initial generated image, style adjustment controls, first image update controls, and second style switching controls corresponding to each of the various second preset styles; The style adjustment control is used to adjust the intensity of the image style corresponding to the currently displayed generated image; the first image update control is used to trigger the update of the currently displayed generated image, and the image style of the currently displayed generated image is consistent with the image style of the updated generated image; any second style switching control is used to trigger the switching of the currently displayed generated image to the corresponding second preset style generated image, and the second style switching control corresponding to the first other style is also used to trigger the generation of the first other style generated image on the first trigger; the first other style is any second preset style other than the second target style among the multiple second preset styles.

[0016] In an optional embodiment, the at least one generated image includes multiple currently generated images of a third target style among multiple third preset styles, and displaying the at least one generated image includes: Display the multiple currently generated images and the third style switching controls corresponding to each of the multiple third preset styles; Wherein, any third style switching control is used to trigger the switching of multiple currently displayed generated images to multiple generated images of the corresponding third preset style; and the third style switching control corresponding to the second other style is also used to trigger the generation of multiple generated images of the second other style on the first trigger; the second other style is any third preset style other than the third target style among the multiple third preset styles.

[0017] In an optional embodiment, the at least one generated image includes multiple second generated images, which are generated images in multiple fourth preset styles; displaying the at least one generated image includes: This demonstrates the various second generated images and second image update controls; The second image update control is used to trigger the update of the generated images of the various fourth preset styles currently displayed.

[0018] According to a second aspect of the present disclosure, a comment processing apparatus is provided, comprising: The preset raw image entry display module is configured to display multiple preset raw image entries in the comment editing panel of the target comment object; The multiple preset raw image entry points are used to trigger the generation of comment images corresponding to the target comment object based on different preset image generation networks. Each preset raw image entry point is used to trigger the generation of a corresponding comment image based on the preset image generation network corresponding to each preset raw image entry point.

[0019] In one optional embodiment, the plurality of preset raw image entry points include at least two of the following: text-based raw image entry point, image-based raw image entry point, graffiti-based raw image entry point, and text-based image entry point.

[0020] In an optional embodiment, the preset raw image entry display module includes: The first display unit is configured to execute a comment trigger command in response to the target comment object, and display the comment editing panel including the multiple preset raw image entry points.

[0021] In an optional embodiment, the apparatus further includes: The initial comment editing panel display module is configured to execute a comment trigger command in response to the target comment object and display the initial comment editing panel, which displays raw image entry trigger information; The preset raw image entry display module includes: The second display unit is configured to execute a raw image entry display instruction triggered based on the raw image entry trigger information, and update the initial comment editing panel to display the comment editing panel with the multiple preset raw image entries.

[0022] In an optional embodiment, the apparatus further includes: The target comment image display module is configured to display the target comment image in the comment editing panel when the generation of the target comment image corresponding to the target comment object is triggered based on the target raw image entry. The target raw image entry is any one of the multiple preset raw image entries. The target comment image is generated based on the preset image generation network corresponding to the target raw image entry. The comment information display module is configured to respond to a comment posting command by displaying comment information, including the target comment image, in the comment display area corresponding to the target comment object.

[0023] In an optional embodiment, the target comment image display module includes: The raw image editing operation information display unit is configured to execute a raw image triggering command triggered based on the target raw image entry and display raw image editing operation information; The generated image display unit is configured to display at least one generated image when the image description information is edited based on the raw image editing operation information and a raw image confirmation instruction is triggered. The at least one generated image is an image generated based on the image description information and a preset image generation network corresponding to the target raw image entry. The target comment image display unit is configured to display the target comment image in the comment editing panel in response to an image confirmation command for the target comment image, wherein the target comment image is any one of the at least one generated image.

[0024] In an optional embodiment, when the target raw image entry is a text-based raw image entry, the image description information is edited text information; the preset image generation network corresponding to the target raw image entry is a text-based raw image network, and the at least one generated image is an image generated based on the edited text information and the text-based raw image network.

[0025] In an optional embodiment, when the target raw image entry is a graph-generated image entry, the image description information is a selected image; the preset image generation network corresponding to the target raw image entry is a graph-generated image network, and the at least one generated image is an image generated based on the selected image and the graph-generated image network.

[0026] In an optional embodiment, when the target raw image entry is a graffiti raw image entry, the image description information is an edited graffiti image; the preset image generation network corresponding to the target raw image entry is a graffiti raw image network, and the at least one generated image is an image generated based on the edited graffiti image and the graffiti raw image network.

[0027] In an optional embodiment, when the target image entry is a text-based image entry, the image description information is edited text-based information; the preset image generation network corresponding to the target image entry is a text-based image network, and the at least one generated image is an image generated based on the edited text-based information and the text-based image network.

[0028] In an optional embodiment, the at least one generated image includes multiple first generated images, which are generated images of multiple first preset styles; the generated image display unit is specifically configured to perform: Display the target generated image and the first style switching controls corresponding to each of the various first preset styles; The target generated image is a generated image of the first target style among the multiple first preset styles; any first style switching control is used to trigger the switching of the currently displayed generated image to the corresponding first preset style generated image.

[0029] In an optional embodiment, the at least one generated image includes an initial generated image; the image style of the initial generated image is a second target style among multiple second preset styles; the generated image display unit is specifically configured to perform: Display the initial generated image, style adjustment controls, first image update controls, and second style switching controls corresponding to each of the various second preset styles; The style adjustment control is used to adjust the intensity of the image style corresponding to the currently displayed generated image; the first image update control is used to trigger the update of the currently displayed generated image, and the image style of the currently displayed generated image is consistent with the image style of the updated generated image; any second style switching control is used to trigger the switching of the currently displayed generated image to the corresponding second preset style generated image, and the second style switching control corresponding to the first other style is also used to trigger the generation of the first other style generated image on the first trigger; the first other style is any second preset style other than the second target style among the multiple second preset styles.

[0030] In an optional embodiment, the at least one generated image includes multiple currently generated images of a third target style from a plurality of third preset styles, and the generated image display unit is specifically configured to perform: Display the multiple currently generated images and the third style switching controls corresponding to each of the multiple third preset styles; Wherein, any third style switching control is used to trigger the switching of multiple currently displayed generated images to multiple generated images of the corresponding third preset style; and the third style switching control corresponding to the second other style is also used to trigger the generation of multiple generated images of the second other style on the first trigger; the second other style is any third preset style other than the third target style among the multiple third preset styles.

[0031] In an optional embodiment, the at least one generated image includes multiple second generated images, which are generated images of multiple fourth preset styles; the generated image display unit is specifically configured to perform: This demonstrates the various second generated images and second image update controls; The second image update control is used to trigger the update of the generated images of the various fourth preset styles currently displayed.

[0032] 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.

[0033] 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 of the comment processing methods described in the embodiments 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.

[0034] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: The comment editing panel of the target comment object displays multiple preset raw image entry points to trigger the generation of comment images corresponding to the target comment object based on different preset image generation networks. This can realize the application of AI-generated images in the commenting process, enhance the novelty and fun of the commenting method, enrich the AI-generated image function in the commenting process, and greatly improve the convenience of users to access various AI-generated image functions by displaying multiple preset raw image entry points in the comment editing panel. This allows users to conveniently use various AI-generated image functions during the comment editing process, and can also effectively stimulate user interaction in the comment, improve interactivity, and further help users better understand the target comment object by combining better comment information.

[0035] 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

[0036] 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.

[0037] Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment; Figure 2 This is a flowchart illustrating a comment processing method according to an exemplary embodiment; Figure 3 This is a schematic diagram illustrating a comment editing panel according to an exemplary embodiment; Figure 4 This is a schematic diagram illustrating another comment editing panel according to an exemplary embodiment; Figure 5 This is a schematic diagram illustrating an initial comment editing panel according to an exemplary embodiment; Figure 6 This is a schematic diagram illustrating a process of generating at least one generated image based on a text image entry according to an exemplary embodiment; Figure 7 This is a schematic diagram illustrating a process of generating at least one generated image based on an image-generated image entry according to an exemplary embodiment; Figure 8 This is a schematic diagram illustrating a process of generating at least one generated image based on a graffiti-style image entry, according to an exemplary embodiment. Figure 9 This is a schematic diagram of a page display page that generates at least one image, provided according to an exemplary embodiment; Figure 10 This is a schematic diagram of a page display page for generating at least one image, provided according to an exemplary embodiment. Figure 11 This is a schematic diagram of a page display page for generating at least one image, provided according to an exemplary embodiment. Figure 12 This is a schematic diagram illustrating the posting of comment information based on a target comment image generated by triggering a text-based image entry, as provided in an exemplary embodiment. Figure 13 This is a schematic diagram illustrating the posting of comment information based on a target comment image triggered by an image-generated entry point, as provided in an exemplary embodiment. Figure 14This is a schematic diagram illustrating the posting of comment information based on a target comment image generated by a graffiti-style image entry point, as provided in an exemplary embodiment. Figure 15 This is a block diagram of a comment processing apparatus according to an exemplary embodiment; Figure 16 This is a block diagram illustrating an electronic device for comment processing according to an exemplary embodiment. Detailed Implementation

[0038] 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.

[0039] 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.

[0040] 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.

[0041] AI (Artificial Intelligence) technology is a comprehensive discipline involving a wide range of fields, encompassing both hardware and software technologies. The solutions provided in this application involve software-level technologies, specifically AIGC (Artificial Intelligence Generated Content) technology, i.e., content production technology based on artificial intelligence, as illustrated by the following embodiments: 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.

[0042] In an optional embodiment, terminal 100 can be used to provide business services such as comments 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.

[0043] In an optional embodiment, server 200 can provide background services to terminal 100. Specifically, server 200 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0044] 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.

[0045] 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.

[0046] Figure 2 This is a flowchart illustrating a comment processing method according to an exemplary embodiment, which can be applied to a terminal, such as... Figure 2 As shown, the method may include: In step S201, multiple preset raw image entry points are displayed in the comment editing panel of the target comment object; In one specific embodiment, the target comment object can be the object that needs to be commented on. Specifically, the target comment object can be multimedia content such as videos and images, or it can be downloaded applications, purchased goods, etc.

[0047] In one specific embodiment, the aforementioned multiple preset raw image entry points are used to trigger the generation of comment images corresponding to the target comment object based on different preset image generation networks. Specifically, each preset raw image entry point can be used to trigger the generation of a corresponding comment image based on the preset image generation network corresponding to that preset raw image entry point. In one specific embodiment, the comment editing panel (comment publisher) can be used to edit comment information; specifically, the comment editing panel can also display operation information for editing comment information, such as information input boxes, voice input controls, keyboards, and emoji input controls.

[0048] In an optional embodiment, the above-mentioned multiple preset raw image entry points may include at least two of the following: text-based raw image entry point, image-based raw image entry point, graffiti-based raw image entry point, and text-based image entry point.

[0049] In one specific embodiment, the preset image generation network corresponding to the text-based image entry can be a text-based image network. Specifically, the text-based image network can be used to generate images based on text information. Optionally, the text-based image network can be obtained by training a first preset generative network to generate images based on sample text information and the corresponding annotations. Correspondingly, the text-based image entry can be used to trigger the generation of comment images based on the text-based image network.

[0050] In one specific embodiment, the preset image generation network corresponding to the image-generated image entry can be an image-generated image network; specifically, the image-generated image network can be used to generate images based on images; optionally, the image-generated image network can be obtained by training a second preset generative network to generate images based on sample images and their corresponding annotations. Accordingly, the image-generated image entry can be used to trigger the generation of comment images based on the image-generated image network.

[0051] In one specific embodiment, the preset image generation network corresponding to the graffiti image entry point can be a graffiti image generation network. Specifically, the graffiti image generation network can be used to generate images based on graffiti images. Optionally, the graffiti image generation network can be obtained by training a third preset generative network to generate images based on sample graffiti images and their corresponding annotations. Correspondingly, the graffiti image entry point can be used to trigger the generation of comment images based on the graffiti image generation network.

[0052] In one specific embodiment, the preset image generation network corresponding to the image-text-generated image entry point can be an image-text-generated image network. Specifically, the image-text-generated image network can be used to generate images based on image and text information, which may include image and text information. Optionally, the image-text-generated image network can be obtained by training a fourth preset generative network to generate images based on sample image and text information and the corresponding annotations. Correspondingly, the image-text-generated image entry point can be used to trigger the generation of comment images based on the image-text-generated image network.

[0053] Furthermore, it should be noted that the first preset generative network, the second preset generative network, the third preset generative network, and the fourth preset generative network can be pre-set generative artificial intelligence networks. The specific network structure of each network can be set according to the actual application. Optionally, taking generative adversarial networks as an example, the corresponding text-to-image network, image-to-image network, graffiti-to-image network, and image-to-text network can be generators trained in the corresponding generative adversarial networks.

[0054] In the above embodiments, by providing at least two types of image generation entry points—text-to-image, image-to-image, doodle-to-image, and text-to-image—in the comment editing panel, users can conveniently use the AI-generated image function during the comment editing process, while greatly enhancing the diversity of the AI-generated image function.

[0055] In an optional embodiment, the aforementioned multiple preset raw image entry points can be displayed simultaneously when the comment editing panel is triggered; correspondingly, the display of multiple preset raw image entry points in the comment editing panel of the target comment object may include: In response to a comment trigger command targeting the object of the comment, a comment editing panel with multiple preset raw image entry points is displayed.

[0056] In one specific embodiment, the comment trigger command can be a command that triggers the display of the comment editing panel, allowing the user to edit comment information using the panel. Specifically, the comment trigger command can be triggered by clicking or long-pressing the comment trigger control corresponding to the target comment object.

[0057] In another alternative embodiment, the above method may further include: In response to a comment trigger command targeting the object of the comment, the initial comment editing panel is displayed, which shows the entry trigger information for the raw image. Accordingly, the various preset raw image entry points displayed in the comment editing panel of the target comment object may include: In response to the command to display raw image entry based on raw image entry trigger information, the initial comment editing panel is updated to display a comment editing panel with multiple preset raw image entry points.

[0058] In one specific embodiment, the above-mentioned raw image entry trigger information can be used to trigger the display of various preset raw image entries; optionally, the above-mentioned raw image entry display instruction can be triggered by clicking, long-pressing the raw image entry trigger information, or other operations.

[0059] In one specific embodiment, taking the target comment object as multimedia content, and the aforementioned preset raw image entry points including text-based raw image entry points, image-based raw image entry points, and graffiti-based raw image entry points as an example, such as... Figure 3 As shown, Figure 3 This is a schematic diagram illustrating a comment editing panel according to an exemplary embodiment. The information displayed in area 301 can be the comment editing panel itself, and the information displayed in area 302 can be various preset image entry points.

[0060] In another specific embodiment, taking the target comment object as multimedia content, and the aforementioned multiple preset raw image entry points including text-based raw image entry points, image-based raw image entry points, and graffiti-based raw image entry points as an example, such as... Figure 4 As shown, Figure 4 This is a schematic diagram illustrating another comment editing panel according to an exemplary embodiment. The information displayed in area 401 can be the comment editing panel, and the information displayed in area 402 can be various preset image entry points.

[0061] In a specific embodiment, taking multimedia content as the target comment object as an example, such as... Figure 5 As shown, Figure 5 This is a schematic diagram illustrating an initial comment editing panel according to an exemplary embodiment. The information displayed in area 501 can be the initial comment editing panel, and the information displayed in area 502 can be the raw image entry trigger information.

[0062] In the above embodiments, by simultaneously displaying multiple preset raw image entry points when triggering the display of the comment editing panel, or by first displaying raw image entry trigger information for triggering the display of multiple preset raw image entry points when triggering the comment trigger command, and then combining the raw image entry trigger information to trigger multiple preset raw image entry points, the diversity of users reached by multiple AI raw image function trigger entry points can be improved on the basis of enriching AI raw image functions.

[0063] In an optional embodiment, the above method further includes: When the generation of the target comment image corresponding to the target comment object is triggered based on the target raw image entry, the target comment image is displayed in the comment editing panel; In response to a comment posting command, comment information, including the target comment image, is displayed in the comment display area corresponding to the target comment object.

[0064] In one specific embodiment, the target raw image entry point can be any of a variety of preset raw image entry points; the target comment image can be generated based on a preset image generation network corresponding to the target raw image entry point.

[0065] In an optional embodiment, when the generation of the target comment image corresponding to the target comment object is triggered based on the target raw image entry, displaying the target comment image in the comment editing panel may include: In response to a raw image trigger command triggered based on the target raw image entry, display raw image editing operation information; When the image description information is edited based on the raw image editing operation information and the raw image confirmation command is triggered, at least one generated image is displayed. The at least one generated image is an image generated based on the image description information and the preset image generation network corresponding to the target raw image entry. In response to an image confirmation command for a target comment image, the target comment image is displayed in the comment editing panel. The target comment image is any one of at least one generated image.

[0066] In one specific embodiment, the preset raw image entry point can be an operable control; correspondingly, the above-mentioned raw image triggering command can be triggered by interactive operations targeting the target raw image entry point, such as clicking the target raw image entry point, long-pressing the target raw image entry point, etc.; optionally, the details viewing command can also be triggered according to the interactive operation of triggering the raw image triggering command indicated in the target raw image entry point. For example, if the target raw image entry point is a text raw image entry point, and the text raw image entry point includes the interactive instruction information "shake the device to use AI text raw image", then the raw image triggering command corresponding to the text raw image entry point can be triggered by the interactive operation of shaking the device; optionally, the above-mentioned raw image triggering command can also be triggered by operating an external device, etc., in conjunction with the interactive operation of triggering the raw image triggering command indicated in the target raw image entry point.

[0067] In one specific embodiment, the raw image editing operation information can be operation information used to edit image description information; specifically, the image description information can be information describing the image to be generated, i.e., the input information of the corresponding preset image generation network. Optionally, the raw image editing operation information can be displayed in the comment editing panel, or it can be displayed on a new page. Correspondingly, at least one generated image can be displayed in the comment editing panel, or it can be displayed on a new page.

[0068] In an optional embodiment, when the target raw image entry is a text-based raw image entry, the image description information can be edited text information; the preset image generation network corresponding to the target raw image entry can be a text-based raw image network, and the at least one generated image can be an image generated based on the edited text information and the text-based raw image network.

[0069] In a specific embodiment, when the target image entry point is a text-based image entry point, the image editing operation information can be text editing operation information. Optionally, the text editing operation information can include a text input box, and correspondingly, the edited text information can include text information input based on the text input box. Optionally, the text editing operation information can also include image theme selection information, image action selection information, and image environment selection information. Specifically, the image theme selection information can include multiple selectable theme information, which can be set according to the actual application; the image action selection information can include multiple selectable action information, which can be set according to the actual application; the image environment selection information can include multiple selectable environment information, which can be set according to the actual application. Correspondingly, the edited text information can also include selected theme information, selected action information, and selected environment information.

[0070] In one specific embodiment, the edited text information can be input into a text-to-image network for image generation processing to obtain at least one generated image as described above.

[0071] In the above embodiments, when the target raw image entry is a text-based raw image entry, by editing the text information and using the edited text information as input to the text-based raw image network for image generation processing, the application of artificial intelligence text-based raw images in the comment process can be realized, thereby enhancing the richness and interest of comment information, and effectively stimulating user interaction in comments, thus improving interactivity.

[0072] In a specific embodiment, when the target image entry is a graph-generated image entry, the image description information is the selected image; the preset image generation network corresponding to the target image entry is a graph-generated image network, and at least one generated image can be an image generated based on the selected image and the graph-generated image network.

[0073] In a specific embodiment, when the above-mentioned target raw image entry is a raw image entry, the raw image editing operation information can be image selection operation information. Optionally, the image selection operation information can include an image source selection control and the image corresponding to the current image source. Specifically, the currently selectable image can be selected by combining the image source selection control. Furthermore, the image can be selected by clicking on any image among the currently selectable images.

[0074] In one specific embodiment, the selected image can be input into a graph-generated image network for image generation processing to obtain at least one generated image as described above.

[0075] In the above embodiments, when the target raw image entry is a graph-generated image entry, by selecting an image and using the selected image as the input of the graph-generated image network for image generation processing, the application of artificial intelligence graph-generated images in the comment process can be realized, thereby enhancing the richness and interest of comment information, and effectively stimulating user interaction in comments, thus improving interactivity.

[0076] In an optional embodiment, when the target raw image entry is a graffiti raw image entry, the image description information is an edited graffiti image; the preset image generation network corresponding to the target raw image entry is a graffiti raw image network, and at least one generated image can be an image generated based on the edited graffiti image and the graffiti raw image network.

[0077] In a specific embodiment, when the target raw image entry is a doodle raw image entry, the raw image editing operation information can be doodle operation information. Optionally, the doodle operation information can be operation information for creating doodle images, such as drawing board, paintbrush, etc.

[0078] In one specific embodiment, the edited graffiti image can be input into the graffiti image generation network for image generation processing to obtain at least one of the above-mentioned generated images.

[0079] In the above embodiments, when the target raw image entry is a graffiti raw image entry, by editing the graffiti image and using the edited graffiti image as input to the graffiti raw image network for image generation processing, the application of artificial intelligence graffiti raw images in the comment process can be realized, thereby enhancing the richness and interest of comment information, and effectively stimulating user interaction in comments, thus improving interactivity.

[0080] In an optional embodiment, when the target image entry is a text-based image entry, the image description information is edited text-based information; the preset image generation network corresponding to the target image entry is a text-based image network, and at least one generated image is an image generated based on the edited text-based information and the text-based image network.

[0081] In a specific embodiment, when the target image entry point is a text-based image entry point, the image editing operation information may include text editing operation information and image editing operation information; the edited text-based information may include edited text information and edited images; specifically, the detailed breakdown of the text editing operation information and the edited text information can be found in the relevant steps above, and will not be repeated here.

[0082] In one specific embodiment, the image editing operation information may include doodle operation information and / or image selection operation information. Correspondingly, the edited image may include an edited doodle image and / or a selected image. Specifically, the details of the doodle operation information, image selection operation information, edited doodle image, and selected image can be found in the relevant steps described above, and will not be repeated here.

[0083] In one specific embodiment, the edited text and image information can be input into a text-to-image network for image generation processing to obtain at least one generated image as described above.

[0084] In the above embodiments, when the target image entry point is a text-based image entry point, by editing the text-based information and using the edited text-based information as input to the text-based image network for image generation processing, the application of artificial intelligence text-based image generation in the comment process can be realized, thereby enhancing the richness and interest of comment information, and effectively stimulating user interaction in comments, thus improving interactivity.

[0085] In one specific embodiment, when the image description information is edited based on the raw image editing operation information and a raw image confirmation instruction is triggered, the terminal can send an image generation request carrying the image description information to the server. Correspondingly, the server can combine the image description information and the corresponding preset image generation network to generate at least one generated image and return it to the terminal so that the terminal can display at least one generated image.

[0086] In one specific embodiment, combined with Figure 3 In the corresponding embodiment, it is assumed that the target raw image entry point is the "AI Text-to-Image" control (Text-to-Image Entry Point), such as Figure 6 As shown, Figure 6 This is a schematic diagram illustrating a process for generating at least one generated image based on a text-based image entry point, according to an exemplary embodiment. Figure 6 The image shown in section 'a' displays information about text editing operations. Further, combined with... Figure 6 Image b shows a text editing operation information display page displaying the edited text information "A young girl elegantly eats watermelon". Further, if the "Generate" control in the text editing operation information triggers a confirmation command for generating an image, as shown... Figure 6 Image c shows the generation page on the terminal side during the process of generating at least one generated image based on the text-to-image model and the edited text information; furthermore, after at least one generated image has been generated, such as... Figure 6 The image shown in section d is a display page that shows at least one generated image based on a text-based image model and edited text information.

[0087] In another specific embodiment, combined with Figure 3 In the corresponding embodiment, it is assumed that the target raw image entry point is the "AI Raw Image" control (Raw Image Entry Point), such as Figure 7 As shown, Figure 7 This is a schematic diagram illustrating a process for generating at least one generated image based on an image-generated entry point, according to an exemplary embodiment. Figure 7 Image 'a' shows the page displaying information about the image selection process. Further, assuming the image of a girl eating watermelon is selected and the raw image confirmation command is triggered, as shown... Figure 7 Figure b shows the generation page on the terminal side during the process of generating at least one generated image based on the graph-generated image model and the selected image; furthermore, after at least one generated image has been generated, such as... Figure 7 The image shown in d is a display page that shows at least one generated image based on a graph-generated image model and a selected image.

[0088] In another specific embodiment, combined with Figure 3In the corresponding embodiment, it is assumed that the target raw image entry point is the "AI Doodle Raw Image" control (Doodle Raw Image Entry Point), such as Figure 8 As shown, Figure 8 This is a schematic diagram illustrating a process for generating at least one generated image based on a graffiti-style image entry point, according to an exemplary embodiment. Figure 8 The image shown in section 'a' displays information about the drawing process. Further, combined with... Figure 8 Figure b shows the graffiti operation information display page with the edited graffiti image. Further, if the "Generate" control in the graffiti operation information triggers the image confirmation command, as shown... Figure 8 Image c shows the generation page on the terminal side during the process of generating at least one generated image based on the graffiti raw image model and the edited graffiti image; furthermore, after at least one generated image has been generated, such as Figure 8 As shown in d, this is a display page that shows at least one generated image based on an edited graffiti image and a graffiti raw image model.

[0089] In one specific embodiment, multiple images with different image styles can be generated at once. Accordingly, the at least one generated image mentioned above can include multiple first generated images, which are generated images with multiple first preset styles. Correspondingly, displaying at least one generated image can include: Displays the target generated image and the corresponding first style switching controls for various first preset styles; In one specific embodiment, the target generated image can be a generated image of a first target style among multiple first preset styles; any first style switching control is used to trigger the switching of the currently displayed generated image to the corresponding first preset style generated image. Specifically, the first target style can be the default image style that is preferentially displayed. Accordingly, in the initial state, the currently displayed generated image is the target generated image. The multiple first preset styles can be multiple pre-set image styles, which can be set according to actual applications, such as including anime style, traditional Chinese style, neoclassical style, optimized style, colorful style, etc.

[0090] In one specific embodiment, the currently displayed generated image can be switched to the corresponding first preset style generated image by clicking any first style switching control, or the display of other first preset style generated images can be switched by sliding the currently displayed generated image.

[0091] In one specific embodiment, the target raw image entry point is used as the raw image entry point, and the first target style is a two-dimensional style, combined with the above. Figure 7As can be seen, the image corresponding to 701 is the target generated image, and the control corresponding to 702 can be multiple first style switching controls corresponding to various first preset styles. Optionally, combined with... Figure 7 As can be seen, at least one generated image display page can also display an original image switching control (the switching control corresponding to the selected image), a comment image confirmation control ("OK" control), a comparison confirmation control, etc. Correspondingly, the currently displayed generated image can be switched to the selected image by combining the original image switching control, or the display of the selected image can be triggered by sliding operations on the currently displayed generated image. The comparison confirmation control can be in a selected state or a deselected state. When selected, after selecting an image for commenting from the generated images and triggering the comment posting command, the comment information can include the selected generated image (target comment image) and the corresponding original image (selected image); conversely, when deselected, after selecting an image for commenting from the generated images and triggering the comment posting command, the comment information does not include the original image corresponding to the selected generated image.

[0092] In the above embodiments, by generating multiple images with different image styles at once and combining them with the corresponding switching controls for each image style, users can easily select images of different styles as comment images according to their needs, thereby increasing the diversity of comment image selection.

[0093] In an optional embodiment, a single image of a certain image style can be generated. Accordingly, the at least one generated image may include an initial generated image; the image style of the initial generated image is a second target style among a plurality of second preset styles; displaying at least one generated image may include: Displays the initial generated image, style adjustment controls, first image update controls, and second style switching controls corresponding to various second preset styles; In one specific embodiment, the style adjustment control can be used to adjust the intensity of the image style corresponding to the currently displayed generated image; the first image update control can be used to trigger the update of the currently displayed generated image, and the image style of the currently displayed generated image is consistent with the image style of the updated generated image, that is, the first image update control can be combined to switch to display a generated image consistent with the current image style; specifically, any second style switching control can be used to trigger the switching of the currently displayed generated image to the corresponding second preset style, and the second style switching control corresponding to the first other style is also used to trigger the generation of the first other style generated image on the first trigger; the first other style is any second preset style other than the second target style among multiple second preset styles. The second target style can be the default preferred image style. Correspondingly, in the initial state, the currently displayed generated image can be the initial generated image. Multiple second preset styles can be multiple pre-set image styles, which can be set according to actual applications, such as including anime style, traditional Chinese style, neoclassical style, optimized style, etc.

[0094] In one specific embodiment, the target raw image entry point is used as the raw image entry point, and the first target style is a two-dimensional style, such as... Figure 9 As shown, Figure 9 This is a schematic diagram of a page displaying at least one generated image according to an exemplary embodiment; wherein, the image corresponding to 901 is an initial generated image, the control corresponding to 902 can be a style adjustment control, the control corresponding to 903 can be a first image update control, and the control corresponding to 904 can be multiple second style switching controls corresponding to various second preset styles. The second style switching control can display preset images with corresponding image styles; optionally, combined with Figure 9 As can be seen, at least one image display page can also display original image switching controls (switching controls corresponding to the selected image), comment image confirmation controls ("OK" controls), comparison confirmation controls, etc.

[0095] In the above embodiments, by first generating a single image of a certain image style, and then displaying style adjustment controls, a first image update control, and second style switching controls corresponding to various second preset styles on the generated image display page, it is convenient to adjust the intensity of the style, and different images of the same style can also be generated. At the same time, by combining the switching controls corresponding to various different image styles, it is convenient for users to select different style images and different images of the same style as comment images according to their needs, which greatly improves the flexibility of selecting different generated images of different styles.

[0096] In an optional embodiment, multiple images of a certain image style can be generated in a single instance; correspondingly, the at least one generated image may include multiple currently generated images of a third target style from a variety of third preset styles, and displaying at least one generated image may include: Displays multiple currently generated images and corresponding third-style switching controls for various third-preset styles; In one specific embodiment, any third style switching control is used to trigger the switching of multiple currently displayed generated images to multiple generated images of the corresponding third preset style; and the third style switching control corresponding to the second other style is also used to trigger the generation of multiple generated images of the second other style on the first triggering; the second other style is any third preset style other than the third target style among multiple third preset styles. The third target style can be the default preferred image style. Accordingly, in the initial state, the multiple generated images currently displayed are multiple currently generated images of the third target style. The multiple third preset styles can be multiple preset image styles, which can be set according to actual applications, such as including anime style, traditional Chinese style, neoclassical style, optimized style, colorful style, etc.

[0097] In one specific embodiment, the target raw image entry point is used as the raw image entry point, and the first target style is a two-dimensional style, such as... Figure 10 As shown, Figure 10 This is a schematic diagram of a page displaying at least one generated image according to an exemplary embodiment; wherein, the image corresponding to 1001 is multiple currently generated images, and the control corresponding to 1002 can be multiple third-style switching controls corresponding to various third preset styles. The third-style switching control can display preset images with corresponding image styles; optionally, combined with Figure 10 As can be seen, at least one image-generating display page can also display image optimization controls. Figure 10 The image includes controls such as "Optimize this image", "OK" control for commenting on the image, and "Compare" control. Correspondingly, the image optimization control can be combined to trigger the optimization process of the corresponding generated image and update the corresponding generated image to the optimized image.

[0098] In the above embodiments, by generating multiple images of a certain image style in a single step, and displaying multiple currently generated images on the image display page, while simultaneously displaying the third style switching controls and style adjustment controls corresponding to various third preset styles, it is possible to combine the switching controls corresponding to various different image styles. This allows users to easily select different style images as comment images according to their needs, as well as different images of the same style, thereby improving the diversity of comment image selection.

[0099] In an optional embodiment, multiple preset styles of images can be generated, and the same multiple preset styles of images can be switched back and forth with one click; correspondingly, the above-mentioned at least one generated image may include multiple second generated images, and the multiple second generated images are generated images of multiple fourth preset styles; correspondingly, displaying at least one generated image includes: Displays various second-generation image and second-image update controls; In one specific embodiment, the second image update control is used to trigger the update of the generated images in the currently displayed multiple fourth preset styles. These multiple fourth preset styles can be pre-set image styles, which can be set according to actual applications, and may include, for example, anime style, traditional Chinese style, neoclassical style, optimized style, colorful style, etc.

[0100] In one specific embodiment, the target raw image entry point is used as the raw image entry point, and the first target style is a two-dimensional style, such as... Figure 11 As shown, Figure 11 This is a schematic diagram of a page displaying at least one generated image according to an exemplary embodiment; wherein the image corresponding to 1101 is a variety of second generated images, and the control corresponding to 1102 can be a second image update control.

[0101] In the above embodiments, by first generating images of multiple preset styles and then displaying a second image update control on the generated image display page, users can switch back to other images of the same multiple preset styles with one click. This makes it convenient for users to select images of different styles according to their needs, as well as different images of the same style as comment images, greatly improving the flexibility of selecting different generated images of different styles.

[0102] In one specific embodiment, a user can trigger an image confirmation command for a target comment image on at least one image-generating display page, so that the target comment image can be displayed in the comment editing panel. Specifically, with Figure 7 Taking C as an example, you can trigger an image confirmation command by clicking the "OK" control. Correspondingly, when the image confirmation command is triggered, the currently displayed generated image is the target comment image.

[0103] In the above embodiments, the raw image triggering command triggered by the target raw image entry is combined with the raw image editing operation information, and then the image description information can be edited in combination with the raw image editing operation information. When the raw image confirmation command is triggered, at least one generated image is displayed based on the image description information and the preset image generation network corresponding to the target raw image entry. When the user confirms that a certain generated image is the target comment image, the target comment image is displayed in the comment editing panel. This realizes the generation of comment images based on artificial intelligence during the commenting process, thereby improving the richness and interest of the comment information.

[0104] In one specific embodiment, with Figure 6 For example, in the corresponding implementation, assuming that in Figure 6 The page corresponding to 'd' triggered an image confirmation command for generating an anime-style image, such as... Figure 12 As shown, Figure 12 This is a schematic diagram illustrating the posting of comment information based on a target comment image generated by a text-based image entry point, as provided in an exemplary embodiment; wherein, Figure 12 Image a shows the comment editing panel displaying the target comment image; furthermore, in Figure 12 Once you've edited the text comment "Blonde magical girl! So cute!" in the comment editing panel shown in image a, you can trigger the comment posting command by clicking the "Send" control, etc. Correspondingly, such as... Figure 12 As shown in b, comment information, including the target comment image, can be displayed in the comment display area corresponding to the target comment object.

[0105] In one specific embodiment, with Figure 7 For example, in the corresponding implementation, assuming that in Figure 7 The page corresponding to 'c' triggered an image confirmation command for generating an anime-style image, such as... Figure 13 As shown, Figure 13 This is a schematic diagram illustrating the posting of comment information based on a target comment image generated by an image-generated entry point, as provided by an example; wherein, Figure 13 Image a shows the comment editing panel displaying the target comment image; furthermore, in Figure 13 Once you've edited the text comment "Blonde magical girl! So cute!" in the comment editing panel shown in image a, you can trigger the comment posting command by clicking the "Send" control, etc. Furthermore, as... Figure 13 The diagram shown in b illustrates the comment display area. Since the comparison confirmation control is selected, the image used for commenting is selected from the generated images. Accordingly, after the comment posting command is triggered, the comment information can include the target comment image and the corresponding original image (the selected image).

[0106] In one specific embodiment, with Figure 8 For example, in the corresponding implementation, assuming that in Figure 8 The page corresponding to 'd' triggered an image confirmation command for generating an anime-style image, such as... Figure 14 As shown, Figure 14 This is an illustrative diagram illustrating the posting of comment information based on a target comment image generated by a graffiti-style image entry point, provided by an example; wherein, Figure 14 Image a shows the comment editing panel displaying the target comment image; furthermore, in Figure 14After editing the text comment "The doodle is so interesting!" in the comment editing panel shown in Figure a, you can trigger the comment posting command by clicking the "Send" control, etc. Furthermore, as... Figure 14 The diagram shown in b illustrates the comment display area. Since the comparison confirmation control is selected, the image used for commenting is selected from the generated images. Accordingly, after the comment posting command is triggered, the comment information can include the target comment image and the corresponding original image (the selected image).

[0107] In the above embodiments, when the generation of the target comment image corresponding to the target comment object is triggered based on the target raw image entry, the target comment image generated by the preset image generation network corresponding to the target raw image entry is displayed in the comment editing panel. When the comment posting command is triggered, the comment information including the target comment image is displayed in the comment display area corresponding to the target comment object. This can realize the editing of comment information by combining the artificial intelligence raw image function during the comment editing process, thereby improving the richness and interest of the comment information.

[0108] In practical applications, to ensure a good user experience, a new feature is often rolled out to users gradually. Optionally, before the AI-powered image generation feature is rolled out to all users, a reservation tag for the feature can be displayed in the comments section. Users can then reserve the AI-powered image generation feature by clicking this reservation tag. Specifically, for example... Figure 14 The information shown as "AI Play Review Creation" can be the reservation tag for the AI-generated image function.

[0109] In an optional embodiment, the full-screen display of the target comment image can be triggered by clicking on the target comment image in the comment information; optionally, the full-screen display page of the target comment image can also display an appointment tag with the aforementioned AI-generated image function.

[0110] As can be seen from the technical solutions provided in the embodiments of this specification above, the comment editing panel of this specification displays multiple preset raw image entry points for triggering the generation of comment images corresponding to the target comment object based on different preset image generation networks. This can enrich the AI-generated image function in the commenting process, enhance the novelty and fun of the commenting method, and greatly improve the convenience of reaching users with multiple AI-generated image functions by displaying multiple preset raw image entry points in the comment editing panel. This allows users to conveniently use multiple AI-generated image functions during the comment editing process, effectively stimulates user interaction in the comments, enhances interactivity, and can also help users better understand the target comment object by combining better comment information.

[0111] Figure 15This is a block diagram illustrating a comment processing apparatus according to an exemplary embodiment. (Refer to...) Figure 15 The device includes: The preset raw image entry display module 1510 is configured to display multiple preset raw image entries in the comment editing panel of the target comment object; Among them, multiple preset raw image entry points are used to trigger the generation of comment images corresponding to the target comment object based on different preset image generation networks. Each preset raw image entry point is used to trigger the generation of a corresponding comment image based on the preset image generation network corresponding to each preset raw image entry point.

[0112] In one optional embodiment, the multiple preset raw image entry points include at least two of the following: text-based raw image entry point, image-based raw image entry point, graffiti-based raw image entry point, and text-based image entry point.

[0113] In an optional embodiment, the preset raw image entry display module 1510 includes: The first display unit is configured to execute comment trigger commands in response to the target comment object, and display a comment editing panel that includes multiple preset raw image entry points.

[0114] In an optional embodiment, the above-described apparatus further includes: The initial comment editing panel display module is configured to execute a comment trigger command in response to the target comment object, and display the initial comment editing panel, which displays the raw image entry trigger information; The preset raw image entry display module 1510 includes: The second display unit is configured to execute a raw image entry display instruction triggered by raw image entry information, updating the initial comment editing panel to display a comment editing panel with multiple preset raw image entries.

[0115] In an optional embodiment, the above-described apparatus further includes: The target comment image display module is configured to display the target comment image in the comment editing panel when the generation of the target comment image corresponding to the target comment object is triggered based on the target raw image entry. The target raw image entry can be any of a variety of preset raw image entries; the target comment image is generated based on the preset image generation network corresponding to the target raw image entry. The comment information display module is configured to respond to a comment posting command by displaying comment information, including the target comment image, in the comment display area corresponding to the target comment object.

[0116] In an optional embodiment, the target comment image display module includes: The raw image editing operation information display unit is configured to execute a raw image trigger command triggered based on the target raw image entry and display raw image editing operation information; The generated image display unit is configured to display at least one generated image when the image description information is edited based on the raw image editing operation information and a raw image confirmation instruction is triggered. The at least one generated image is an image generated based on the image description information and a preset image generation network corresponding to the target raw image entry. The target comment image display unit is configured to display the target comment image in the comment editing panel in response to an image confirmation command for the target comment image, wherein the target comment image is any one of at least one generated image.

[0117] In an optional embodiment, when the target raw image entry is a text-based raw image entry, the image description information is edited text information; the preset image generation network corresponding to the target raw image entry is a text-based raw image network, and at least one generated image is an image generated based on the edited text information and the text-based raw image network.

[0118] In an optional embodiment, when the target image entry is a graph-generated image entry, the image description information is the selected image; the preset image generation network corresponding to the target image entry is a graph-generated image network, and at least one generated image is an image generated based on the selected image and the graph-generated image network.

[0119] In an optional embodiment, when the target raw image entry is a graffiti raw image entry, the image description information is an edited graffiti image; the preset image generation network corresponding to the target raw image entry is a graffiti raw image network, and at least one generated image is an image generated based on the edited graffiti image and the graffiti raw image network.

[0120] In an optional embodiment, when the target image entry is a text-based image entry, the image description information is edited text-based information; the preset image generation network corresponding to the target image entry is a text-based image network, and at least one generated image is an image generated based on the edited text-based information and the text-based image network.

[0121] In an optional embodiment, at least one generated image includes multiple first generated images, which are generated images of multiple first preset styles; the generated image display unit is specifically configured to perform: Displays the target generated image and the corresponding first style switching controls for various first preset styles; The target generated image is a generated image of the first target style among multiple first preset styles; any first style switching control is used to trigger the switching of the currently displayed generated image to the corresponding first preset style generated image.

[0122] In an optional embodiment, at least one generated image includes an initial generated image; the image style of the initial generated image is a second target style among multiple second preset styles; the generated image display unit is specifically configured to perform: Displays the initial generated image, style adjustment controls, first image update controls, and second style switching controls corresponding to various second preset styles; The style adjustment control is used to adjust the intensity of the image style corresponding to the currently displayed generated image; the first image update control is used to trigger the update of the currently displayed generated image, and the image style of the currently displayed generated image is consistent with the image style of the updated generated image; any second style switching control is used to trigger the switching of the currently displayed generated image to the corresponding second preset style generated image, and the second style switching control corresponding to the first other style is also used to trigger the generation of the first other style generated image on the first trigger; the first other style is any second preset style other than the second target style among a variety of second preset styles.

[0123] In an optional embodiment, at least one generated image includes multiple currently generated images of a third target style from a plurality of third preset styles, and the generated image display unit is specifically configured to perform: Displays multiple currently generated images and corresponding third-style switching controls for various third-preset styles; Among them, any third style switching control is used to trigger the switching of multiple currently displayed generated images to multiple generated images of the corresponding third preset style; and the third style switching control corresponding to the second other style is also used to trigger the generation of multiple generated images of the second other style on the first trigger; the second other style is any third preset style other than the third target style among multiple third preset styles.

[0124] In an optional embodiment, at least one generated image includes multiple second generated images, which are generated images in multiple fourth preset styles; the generated image display unit is specifically configured to perform: Displays various second-generation image and second-image update controls; The second image update control is used to trigger the update of the generated images of the various fourth preset styles currently displayed.

[0125] 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.

[0126] Figure 16 This is a block diagram illustrating an electronic device for comment processing according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 16 As shown. The terminal may include an RF (Radio Frequency) circuit 1610, a memory 1620 including one or more computer-readable storage media, an input unit 1630, a display unit 1640, a sensor 1650, an audio circuit 1660, a WiFi (Wireless Fidelity) module 1670, a processor 1680 including one or more processing cores, and a power supply 1690, etc. Those skilled in the art will understand that... Figure 16 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 1610 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 1680 for processing; additionally, it transmits uplink data to the base station. Typically, RF circuit 1610 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 1610 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.

[0127] The memory 1620 can be used to store software programs and modules. The processor 1680 executes various functional applications and data processing by running the software programs and modules stored in the memory 1620. The memory 1620 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 1620 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 1620 may also include a memory controller to provide access to the memory 1620 for the processor 1680 and the input unit 1630.

[0128] The input unit 1630 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 1630 may include a touch-sensitive surface 1631 and other input devices 1632. The touch-sensitive surface 1631, 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 1631), and drive the corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface 1631 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 1680, and can receive and execute commands from the processor 1680. In addition, the touch-sensitive surface 1631 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides the touch-sensitive surface 1631, the input unit 1630 may also include other input devices 1632. Specifically, other input devices 1632 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 1640 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 1640 may include a display panel 1641, which may optionally be configured as an LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or similar display panel. Further, a touch-sensitive surface 1631 may cover the display panel 1641. When the touch-sensitive surface 1631 detects a touch operation on or near it, it transmits the information to the processor 1680 to determine the type of touch event. Subsequently, the processor 1680 provides corresponding visual output on the display panel 1641 according to the type of touch event. The touch-sensitive surface 1631 and the display panel 1641 can be two independent components to implement input and output functions. However, in some embodiments, the touch-sensitive surface 1631 and the display panel 1641 can be integrated to achieve both input and output functions.

[0129] The terminal may also include at least one sensor 1650, 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 1641 according to the ambient light level, and the proximity sensor can turn off the display panel 1641 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.

[0130] Audio circuitry 1660, speaker 1661, and microphone 1662 provide an audio interface between the user and the terminal. Audio circuitry 1660 converts received audio data into electrical signals, which are then transmitted to speaker 1661, where they are converted into sound signals for output. Conversely, microphone 1662 collects sound signals, converts them into electrical signals, which are received by audio circuitry 1660, converted back into audio data, and then processed by processor 1680 before being transmitted via RF circuitry 1610 to, for example, another terminal, or output to memory 1620 for further processing. Audio circuitry 1660 may also include an earphone jack to facilitate communication between a peripheral headset and the terminal.

[0131] WiFi is a short-range wireless transmission technology. This terminal, through the WiFi module 1670, can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 16 WiFi module 1670 is shown, but it is understood that it is not a necessary component of the terminal and can be omitted as needed without changing the nature of the invention.

[0132] The processor 1680 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 1620, and calls data stored in the memory 1620 to perform various functions and process data, thereby providing overall monitoring of the terminal. Optionally, the processor 1680 may include one or more processing cores; preferably, the processor 1680 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1680.

[0133] The terminal also includes a power supply 1690 (such as a battery) to power various components. Preferably, the power supply can be logically connected to the processor 1680 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 1690 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.

[0134] 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 terminal's display unit 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.

[0135] 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 comment processing method as described in the embodiments of this disclosure.

[0136] 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 comment processing method of the present disclosure embodiments. In an exemplary embodiment, a computer program product including instructions is also provided, which, when run on a computer, causes the computer to perform the comment processing method of the present disclosure embodiments.

[0137] 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.

[0138] 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.

[0139] 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 comment processing method, characterized in that, include: The comment editing panel for the target commenter displays multiple preset image entry points; The multiple preset raw image entry points are used to trigger the generation of comment images corresponding to the target comment object based on different preset image generation networks. Each preset raw image entry point is used to trigger the generation of a corresponding comment image based on the preset image generation network corresponding to each preset raw image entry point.

2. The comment processing method according to claim 1, characterized in that, The various preset raw image entry points include at least two of the following: text-based raw image entry point, image-based raw image entry point, graffiti-based raw image entry point, and text-based image entry point.

3. The comment processing method according to claim 1, characterized in that, The method of displaying multiple preset raw image entry points in the comment editing panel of the target commenter includes: In response to a comment trigger command for the target comment object, the comment editing panel, including the various preset raw image entry points, is displayed.

4. The comment processing method according to claim 1, characterized in that, The method further includes: In response to a comment trigger command for the target comment object, an initial comment editing panel is displayed, which displays raw image entry trigger information; The method of displaying multiple preset raw image entry points in the comment editing panel of the target commenter includes: In response to the raw image entry display instruction triggered based on the raw image entry trigger information, the initial comment editing panel is updated to display the comment editing panel with the multiple preset raw image entries.

5. The comment processing method according to any one of claims 1 to 4, characterized in that, The method further includes: When the generation of a target comment image corresponding to the target comment object is triggered based on the target raw image entry, the target comment image is displayed in the comment editing panel. The target raw image entry is any one of the multiple preset raw image entries. The target comment image is generated based on the preset image generation network corresponding to the target raw image entry. In response to a comment posting instruction, comment information, including the target comment image, is displayed in the comment display area corresponding to the target comment object.

6. The comment processing method according to claim 5, characterized in that, When the generation of the target comment image corresponding to the target comment object is triggered based on the target raw image entry, displaying the target comment image in the comment editing panel includes: In response to a raw image trigger command triggered based on the target raw image entry, raw image editing operation information is displayed; When the image description information is edited based on the raw image editing operation information and the raw image confirmation command is triggered, at least one generated image is displayed. The at least one generated image is an image generated based on the image description information and the preset image generation network corresponding to the target raw image entry. In response to an image confirmation command for the target comment image, the target comment image is displayed in the comment editing panel, wherein the target comment image is any one of the at least one generated image.

7. The comment processing method according to claim 6, characterized in that, When the target raw image entry is a text-based raw image entry, the image description information is edited text information; the preset image generation network corresponding to the target raw image entry is a text-based raw image network, and the at least one generated image is an image generated based on the edited text information and the text-based raw image network.

8. The comment processing method according to claim 6, characterized in that, When the target raw image entry is a graph-generated image entry, the image description information is a selected image; the preset image generation network corresponding to the target raw image entry is a graph-generated image network, and the at least one generated image is an image generated based on the selected image and the graph-generated image network.

9. The comment processing method according to claim 6, characterized in that, When the target raw image entry is a graffiti raw image entry, the image description information is an edited graffiti image; the preset image generation network corresponding to the target raw image entry is a graffiti raw image network, and the at least one generated image is an image generated based on the edited graffiti image and the graffiti raw image network.

10. The comment processing method according to claim 6, characterized in that, When the target image entry is a text-based image entry, the image description information is edited text-based information; the preset image generation network corresponding to the target image entry is a text-based image generation network, and the at least one generated image is an image generated based on the edited text-based information and the text-based image generation network.

11. The comment processing method according to claim 6, characterized in that, The at least one generated image includes multiple first generated images, and the multiple first generated images are generated images of multiple first preset styles; The display of at least one generated image includes: Display the target generated image and the first style switching controls corresponding to each of the various first preset styles; The target generated image is a generated image of the first target style among the multiple first preset styles; any first style switching control is used to trigger the switching of the currently displayed generated image to the corresponding first preset style generated image.

12. The comment processing method according to claim 6, characterized in that, The at least one generated image includes an initial generated image; the image style of the initial generated image is a second target style among a plurality of second preset styles; The display of at least one generated image includes: Display the initial generated image, style adjustment controls, first image update controls, and second style switching controls corresponding to each of the various second preset styles; The style adjustment control is used to adjust the intensity of the image style corresponding to the currently displayed generated image; the first image update control is used to trigger the update of the currently displayed generated image, and the image style of the currently displayed generated image is consistent with the image style of the updated generated image; any second style switching control is used to trigger the switching of the currently displayed generated image to the corresponding second preset style generated image, and the second style switching control corresponding to the first other style is also used to trigger the generation of the first other style generated image on the first trigger; the first other style is any second preset style other than the second target style among the multiple second preset styles.

13. The comment processing method according to claim 6, characterized in that, The at least one generated image includes multiple currently generated images of a third target style from a variety of third preset styles, and displaying at least one generated image includes: Display the multiple currently generated images and the third style switching controls corresponding to each of the multiple third preset styles; Wherein, any third style switching control is used to trigger the switching of multiple currently displayed generated images to multiple generated images of the corresponding third preset style; and the third style switching control corresponding to the second other style is also used to trigger the generation of multiple generated images of the second other style on the first trigger; the second other style is any third preset style other than the third target style among the multiple third preset styles.

14. The comment processing method according to claim 6, characterized in that, The at least one generated image includes multiple second generated images, and the multiple second generated images are generated images of multiple fourth preset styles; The display of at least one generated image includes: This demonstrates the various second generated images and second image update controls; The second image update control is used to trigger the update of the generated images of the various fourth preset styles currently displayed.

15. A comment processing device, characterized in that, include: The preset raw image entry display module is configured to display multiple preset raw image entries in the comment editing panel of the target comment object; The multiple preset raw image entry points are used to trigger the generation of comment images corresponding to the target comment object based on different preset image generation networks. Each preset raw image entry point is used to trigger the generation of a corresponding comment image based on the preset image generation network corresponding to each preset raw image entry point.

16. 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 comment processing method as described in any one of claims 1 to 14.

17. 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 comment processing method as described in any one of claims 1 to 14.

18. A computer program product containing instructions, characterized in that, When the instructions are executed on a computer, the computer is able to perform the comment processing method as described in any one of claims 1 to 14.

Images