Content generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a content generation method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a target visual angle in response to a user operation, and enabling the target visual angle to be used for representing an observation visual angle in a target state; image media are obtained, a content generation model is called to process the image media based on the target view angle, view angle special effect content is generated, the view angle special effect content has a special effect video picture, and the special effect video picture is used for displaying the visual effect of observing the image media based on the target view angle. According to the invention, the target visual angle representing the observation visual angle of the target observation object is determined, the target visual angle is taken as input, the image generation model is called to process the image media, and the visual angle special effect content is generated, so that video generation based on visual angle dimension is realized, and the quality of the generated video is improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the technical field of artificial intelligence content generation, and in particular, to a content generation method, device, electronic device, and storage medium. Background Art

[0002] Currently, interactive image generation based on artificial intelligence (AI) technology has become an increasingly popular way of content creation. Users can generate corresponding videos by inputting descriptive words and using the capabilities of artificial intelligence models, which greatly improves the efficiency of content creation.

[0003] In the prior art, video generation technology based on AI models requires users to describe the content of video images through complex descriptive words to generate corresponding videos. However, the design of description words requires users to have high model operation experience, and it is difficult for general users to quickly achieve reasonable and accurate description word input.

[0004] Therefore, the solutions for producing special effects videos based on AI technology in the prior art have the problems of low video generation efficiency and video quality that is difficult to meet user expectations. Summary of the invention

[0005] The embodiments of the present disclosure provide a content generation method, device, electronic device, and storage medium to overcome the problems of low video generation efficiency and difficulty in meeting user expectations for video quality.

[0006] In a first aspect, an embodiment of the present disclosure provides a content generation method, including:

[0007] In response to user operation, a target perspective is determined, and the target perspective is used to characterize the observation perspective under the target state; image media is acquired, and a content generation model is called to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to display the visual effect of observing the image media based on the target perspective.

[0008] In a second aspect, an embodiment of the present disclosure provides a content generation device, including:

[0009] An interaction module, configured to determine a target viewing angle in response to a user operation, wherein the target viewing angle is used to characterize an observation viewing angle in a target state;

[0010] A generation module is used to obtain image media and call a content generation model to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to display the visual effect of observing the image media based on the target perspective.

[0011] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0012] The memory stores computer-executable instructions;

[0013] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the content generation method described in the first aspect and various possible designs of the first aspect.

[0014] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the content generation method described in the first aspect and various possible designs of the first aspect is implemented.

[0015] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the content generation method described in the first aspect and various possible designs of the first aspect.

[0016] The content generation method, device, electronic device and storage medium provided in this embodiment determine the target perspective in response to user operation, and the target perspective is used to characterize the observation perspective under the target state; obtain image media, and call the content generation model to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to show the visual effect of observing the image media based on the target perspective. In response to user operation, a target perspective that characterizes the observation perspective of the target observation object is determined, and then, with the target perspective as input, the image generation model is called to process the image media to generate perspective special effects content, and the perspective special effects content includes the visual effect of observing the image media based on the observation perspective of the target observation object, thereby realizing video generation based on the perspective dimension. This process does not require the user to input overly complex descriptive words, so it can effectively improve the efficiency of video generation. At the same time, the generated perspective special effects content is a video generated by the content generation model based on its own understanding of the observation perspective of the target observation object, so the content consistency of the video is better, the authenticity is higher, and the quality of the generated video is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 An application scenario diagram of the content generation method provided by the embodiment of the present disclosure;

[0019] Figure 2 A flow chart of a content generation method provided in an embodiment of the present disclosure Figure 1 ;

[0020] Figure 3 A schematic diagram of a first page provided in an embodiment of the present disclosure;

[0021] Figure 4 for Figure 2 A flowchart of a specific implementation method of step S101 in the illustrated embodiment;

[0022] Figure 5 A schematic diagram of a special effects content page provided by an embodiment of the present disclosure;

[0023] Figure 6 for Figure 2 A flowchart of another specific implementation of step S101 in the illustrated embodiment;

[0024] Figure 7 A schematic diagram of a second page provided in an embodiment of the present disclosure;

[0025] Figure 8 for Figure 6 A flowchart of a specific implementation method of step S1013 in the illustrated embodiment;

[0026] Fig. 9 A schematic diagram of generating perspective special effect content provided by an embodiment of the present disclosure;

[0027] Fig.10 A flow chart of a content generation method provided in an embodiment of the present disclosure Figure 2 ;

[0028] Fig.11 A structural block diagram of a content generation device provided in an embodiment of the present disclosure

[0029] Fig.12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure;

[0030] Fig.13 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0032] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] The application scenarios of the embodiments of the present disclosure are explained below:

[0034] The content generation method provided by the embodiment of the present disclosure can be applied to applications (APP, Application) with video generation and video production functions, such as short video applications, video editing applications, etc. More specifically, it can be applied to application scenarios of AI model-based image generation video, adding special effects to videos, and video continuation (video generation video). The execution subject of this embodiment can be a terminal device running the above-mentioned application with video generation function, or a server deploying the server corresponding to the above-mentioned application, or other electronic devices with similar functions. Among them, when the execution subject is a terminal device, the terminal device executes the method provided by this embodiment by running the above-mentioned application; when the execution subject is a server, the server of the above-mentioned application with video generation function can be partially or completely run on the server, and the method provided by this embodiment is executed on the server side, and the terminal device runs the client of the application, and the communication between the server and the terminal device is based on the server-client, so that the terminal device can obtain the execution result of the method provided by this embodiment and display it as needed.

[0035] Among them, in some embodiments, the terminal device or server can implement the video generation method provided by the embodiment of the present disclosure by running various computer executable instructions or computer programs. For example, computer executable instructions can be program-level commands, machine instructions or software instructions. The computer program can be a native program or software module in the operating system; it can be a local application, that is, a program that needs to be installed in the operating system to run, or it can be a small program embedded in any APP, that is, a program that runs based on a browser environment. In summary, the above-mentioned computer executable instructions can be instructions in any form, and the above-mentioned computer program can be an application, module or plug-in in any form, and the specific implementation form can be configured as needed. Furthermore, in the process of implementing the video generation method provided by the embodiment of the present disclosure, the video generation device can execute the method by running a computer executable instruction or computer program set locally, or it can execute the method by calling a computer executable instruction or computer program set in an external server. In some embodiments, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud storage, cloud communications, cloud databases, cloud computing, cloud functions, network services, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms. Among them, cloud services can be interactive processing services for terminal devices to call.

[0036] Figure 1 This is an application scenario diagram of the content generation method provided by the embodiment of the present disclosure, referring to Figure 1As shown in , taking a terminal device as an example, a target application with a video generation function is running on one side of the terminal device. Afterwards, the user can input the image media and description words to be processed by operating the target application, wherein, for example, the image media is a picture, and the description words are the content description of the special effects video to be generated. Afterwards, based on the image media and the description words, the terminal device calls a content generation model based on artificial intelligence content generation (AIGC) technology to generate a special effects video or special effects picture that combines the picture content and the content described by the description words. For example, as shown in the figure, the image media is a portrait photo P1, and the content of the description words is "let the person in the picture wear glasses", then based on the image media and the description words, a special effects video V1 is generated, and the content of the special effects video is the process of the "person" in the above-mentioned portrait photo implementing the action of putting on glasses. The above example is the process of generating a video based on the model. In another possible application scenario, the image media input by the user can also be a video to be processed. After the terminal device calls the content generation model based on the video to be processed and the descriptive words, it generates a special effects video that combines the video content of the video to be processed and the content described by the descriptive words, which is the process of video generation based on the model.

[0037] In the prior art, in the above-mentioned application scenarios of video generation based on AIGC technology, users are usually required to describe the video content through complex descriptive words to generate corresponding videos. For example, users need to describe the picture style of the video, the way the content changes, etc. However, the design of description words requires users to have a high level of model operation experience. It is difficult for general users to quickly input reasonable and accurate description words, which leads to low video generation efficiency and video quality that is difficult to meet user expectations.

[0038] The embodiments of the present disclosure provide a content generation method to solve the above problems.

[0039] refer to Figure 2 , Figure 2 A flow chart of a content generation method provided in an embodiment of the present disclosure Figure 1 The method of this embodiment can be applied in a terminal device. The content generation method includes:

[0040] Step S101: In response to a user operation, a target viewing angle is determined, where the target viewing angle is used to characterize an observation viewing angle in a target state.

[0041] Step S102: Acquire image media, and call a content generation model to process the image media based on a target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to display the visual effect of observing the image media based on the target perspective.

[0042] For example, reference Figure 1 In the application scenario diagram shown, the terminal device runs a target application, such as a video editing APP, and displays an interactive interface through the target application, and receives user operations input by the user through the interactive interface, wherein the specific implementation of the user operation is implemented by the design of the interactive interface of the target application. In a possible implementation, the interactive interface of the target application includes a first page, and the user operation includes a selection operation for the first page. Before step S101, it also includes:

[0043] Step S100A: Display a first page, in which special effect components corresponding to at least two observation perspectives are displayed.

[0044] Accordingly, a specific implementation of step S101 includes: in response to a selection operation on a target special effect component in the first page, determining an observation angle corresponding to the target special effect component as a target angle.

[0045] Exemplarily, the first page may be the homepage of the perspective special effect, in which a plurality of special effect components are provided, each of which corresponds to an observation perspective, so as to realize observation perspectives in different states for the user to choose. In a possible implementation, the target perspective includes the observation perspective of the target observation object, and the special effect video screen is used to display the visual effect of observing the image media based on the observation perspective of the target observation object. Figure 3 A schematic diagram of a first page provided in an embodiment of the present disclosure, referring to Figure 3As shown, exemplarily, the first page is provided with special effect component #1, special effect component #2 and special effect component #3, among which the observation perspective corresponding to special effect component #1 is "the perspective of a person who has eaten poisonous mushrooms", the observation perspective of special effect component #2 is "the perspective of an alien", and the observation perspective of special effect component #3 is "the perspective of a fly". The title of each special effect component is the name of the corresponding observation object and the fixed description "the world in the eyes", that is, the title of special effect component #1 is "the world in the eyes of a person who has eaten poisonous mushrooms"; the title of special effect component #2 is "the world in the eyes of an alien"; and the title of special effect component #3 is "the world in the eyes of a fly". Among them, the state corresponding to the observation perspective refers to the characteristics of the observation perspective, so the target perspective can be the observation perspective of the target observation object, such as "the perspective of a person who has eaten poisonous mushrooms". It can also be a perspective that does not limit the target observation object but only limits the observation state, such as "the perspective of eating poisonous mushrooms". Taking the observation angle corresponding to special effect component #1 as an example, the state corresponding to the observation angle is the state of "eating poisonous mushrooms", and its observation angle is the "perspective of a person". After combination, it serves as the target perspective, that is, the "perspective of a person who has eaten poisonous mushrooms". Further, when the user applies a selection operation to the first page, for example, selecting "special effect component #1" in the first page as the target special effect component, the terminal device uses the target perspective corresponding to "special effect component #1", that is, "perspective of a person who has eaten poisonous mushrooms", as the target perspective used in subsequent steps according to the selection operation.

[0046] Furthermore, in a possible implementation, the selection operation includes a first selection operation and a second selection operation, that is, the selection operation is composed of two operation steps, the first selection operation and the second selection operation. Accordingly, Figure 4 As shown, the specific implementation of step S101 includes:

[0047] Step S1011: In response to the second selection operation on the target special effect component, a special effect content page corresponding to the target special effect component is displayed, the special effect content page displays at least two special effect videos generated based on the observation angle corresponding to the target special effect component, and a confirmation component is set in the special effect content page.

[0048] Step S1012: In response to the first selection operation on the confirmation component, the observation angle corresponding to the target special effect component is determined as the target angle.

[0049] Exemplarily, after the first page is displayed, first, in response to the second selection operation for the target special effect component, the special effect content page corresponding to the target special effect component is displayed, and multiple special effect videos are displayed in the special effect content page. Specifically, the special effect content page displays multiple first frames of special effect videos, video covers and other pictures, and by further clicking on the above pictures, the clicked special effect video can be played. The special effect video is a special effect video generated based on the observation angle corresponding to the target special effect component selected by the second selection operation.

[0050] Figure 5 A schematic diagram of a special effects content page provided by an embodiment of the present disclosure, such as Figure 5 As shown, reference Figure 3 In the illustrated embodiment, after the user applies a second selection operation (e.g., a click operation) and triggers special effect component #3, the user enters a special effect content page corresponding to special effect component #3, and the special effect content page displays a special effect video generated based on the observation angle corresponding to the target special effect component, such as special effect video A, special effect video B, special effect video C, special effect video D, etc. shown in the figure. Optionally, social information corresponding to each special effect video is also displayed, such as the name of the posting user (represented by User_1, User_2, etc. in the figure), the number of likes, the number of reposts, etc. Furthermore, the above-mentioned special effects video is a special effects video generated by the user based on the observation angle corresponding to the target special effects component, wherein, more specifically, the observation angle corresponding to the special effects component #3 is, for example, the "fly's perspective". For example, as shown in the figure, the special effects video (the special effects video screen, i.e., the screen of a certain frame in the special effects video) generated based on the observation angle simulates the "fly's perspective" (the "hexagon" is used in the figure to simulate the "compound eye" effect of the fly) to present the image media uploaded by the user, so that the special effects video (the special effects video screen) can show the visual effect of observing the image media based on the "fly's perspective". Afterwards, the user clicks (the first selection operation) the confirmation component set in the special effects content page to determine the observation angle corresponding to the target special effects component as the target perspective, i.e., the "fly's perspective". In this embodiment, after triggering the target special effect component, the corresponding special effect content page is first displayed, and the various visual effects of the special effect video generated by the observation perspective corresponding to the target special effect component are displayed through the special effect content page, thereby realizing the aggregation of user-created content, improving information display efficiency, and enabling users to match the target perspective of interest more quickly.

[0051] In the steps of this embodiment, an implementation scheme for determining the target viewing angle is provided, that is, generated viewing angles are provided for users to choose, and based on the user's choice, a target viewing angle is determined from the above-mentioned generated viewing angles. This process does not require the user to input description words, thereby improving interaction efficiency, reducing user operation requirements, and improving the efficiency of special effect video generation.

[0052] Furthermore, in a possible implementation, a preview area is provided in the special effect component, and during or after the execution of step S100A, the following is further included:

[0053] In the preview area of ​​each special effect component on the first page, the recommended special effect video corresponding to the special effect component is displayed, wherein the recommended special effect video is a video determined by sorting the video attributes of each special effect video among the special effect videos generated based on the observation perspective corresponding to the special effect component; the video attributes include the video generation time and / or the video access popularity.

[0054] Among them, reference Figure 4 , Figure 5 In the illustrated embodiment, the preview area is an area for displaying the special effect video (special effect video screen) in the special effect content page corresponding to the special effect component. Through the preview area, the user can observe the content in the special effect content page without entering the special effect content page, thereby improving the interaction efficiency. Among them, the preview area displays the recommended special effect video corresponding to the special effect component, that is, the recommended special effect video in the special effect content page. The recommended special effect video is, for example, the top N special effect videos in the special effect content page after sorting based on video attributes, wherein the video attribute is, for example, the video generation time, that is, the most recently generated N special effect videos in the special effect content page are displayed in the preview area; or, the attribute is, for example, the video access heat, which is determined by one or more of the number of visits, forwarding, and collections, that is, the N special effect videos with the highest access heat in the special effect content page are displayed in the preview area.

[0055] In this embodiment, by configuring the preview area of ​​the special effect component, the special effect component can display the recommended special effect video in the special effect content page through the preview area, thereby further improving the interaction efficiency.

[0056] In another possible implementation, the user operation includes an input operation, which is an operation for inputting text, that is, the user determines the target perspective by inputting a description text, thereby realizing the generation of special effects video based on the target perspective, that is, content generation. Specifically, before step S101, it also includes:

[0057] Step S100B: Display the second page, where a text input component is provided.

[0058] Accordingly, if Figure 6 As shown, in another possible implementation, the specific implementation of step S101 includes:

[0059] Step S1013: In response to the input operation on the text input component in the second page, a target text is generated, and the target text is used to determine the target observation object.

[0060] Step S1014: Determine the target perspective according to the target text.

[0061] Exemplarily, in another implementation, before step S101, the second page is first displayed, and the second page is a page for receiving text input by the user, and the user is guided to input relevant text by displaying adaptive prompt information in the second page, so that the terminal device can generate a target text according to the text input by the user. The target text can be the observation object of the target observation object of the target perspective. Figure 7 A schematic diagram of a second page provided in an embodiment of the present disclosure, referring to Figure 7 As shown, exemplarily, the second page can jump from the first page. For example, as shown in the figure, a "Create Perspective" control is set in the first page. After the user clicks the control, it jumps to the second page. The second page is configured with fixed prompt information, such as "I want to observe the world from _____'s perspective". After that, the user enters "alien", that is, the target text, in the text input component (for example, the underlined "_____" position shown in the figure) according to the above prompt information. After that, after the user clicks the confirmation component, the terminal device determines the corresponding target perspective according to the target text, which is "alien perspective". After that, the subsequent processing steps are performed based on the target perspective until the corresponding video or picture of the input image media observed from the perspective of an alien is generated, that is, the perspective special effect content.

[0062] Furthermore, in a possible implementation, the input operation includes a first trigger operation and a second trigger operation, and a random generation component for randomly generating a random object with complete semantics is configured in the second page. Accordingly, Figure 8 As shown, the specific implementation of step S1013 includes:

[0063] Step S1013 - 1 : In response to a first trigger operation on the random generation component of the second page, randomly generated text is displayed in the text input component of the second page, where the randomly generated text is used to represent a randomly generated observation object.

[0064] Step S1013 - 2 : In response to a second trigger operation on the second page, the randomly generated text is determined as the target text.

[0065] Exemplarily, after the user triggers the random generation component of the second page through the first trigger operation, the terminal device will display randomly generated text in the text input component of the second page. The randomly generated text is, for example, "elephant", "fly", "alien", etc. The randomly generated text can be words randomly selected from a pre-generated vocabulary for storing the names of the observed objects, or it can be words that can characterize the observed objects randomly generated by a large language model. Furthermore, the randomly generated text can be composed of at least two parts, wherein the first part is text that characterizes the object name of the observed object, such as "elephant", "fly, etc.", and the second part is restrictive text of the state of the standard observed object, such as "moving", "eating poisonous mushrooms". The specific generation method of the randomly generated text can be set as needed, and no specific limitation is made here. Afterwards, in response to the second trigger operation on the second page, refer to Figure 7 As shown in , the second trigger operation is, for example, a click operation on a "Confirm" button in the second page, the above-mentioned randomly generated text is determined as the target text, and subsequent steps are executed.

[0066] Furthermore, after the target viewing angle is obtained and determined through the interactive process of step S101, the terminal device further obtains image media, which may be pictures or videos. The image media may be stored locally on the terminal device or in the cloud, and obtained in response to the user's media selection operation. Furthermore, the image media may be a frame of picture or a segment of video, or may be multiple frames of pictures or multiple segments of video. When the image media is multiple frames of pictures or multiple segments of video, the terminal device may obtain the above-mentioned multiple frames of pictures or multiple segments of video from the local or cloud media library at one time, or may obtain the above-mentioned multiple frames of pictures or multiple segments of video in several times in response to multiple media selection operations of the user. The specific implementation method may be set as needed.

[0067] Afterwards, the terminal device processes the above-mentioned image media and target perspective by calling the content generation model, that is, taking the image media and target perspective as the input of the content generation model, and using the video generation capability of the video generation module to generate perspective special effects content with the perspective effect of observing the image media based on the observation perspective of the target observation object. Among them, the content generation model in this embodiment has semantic understanding ability, reasoning ability and video generation ability. It can understand the meaning of the input target perspective, and infer the visual effect of viewing the object under the target perspective, and generate the corresponding visual special effects video in combination with the image media based on the visual effect. The content generation model can be deployed locally on the terminal device or in the cloud. Specifically, the video generation module has the ability to understand the target perspective and add the visual effect of observing the target image based on the target perspective to the target image. When the image media is a video, the video generation module will add the above-mentioned perspective effect to at least one video frame in the video (usually all video frames or most video frames), and / or generate a new video frame with the above-mentioned perspective effect (i.e., video continuation), so that the processed video has the ability to express the observation perspective of the target observation object. When the image media is a picture, the video generation module will generate more pictures based on the picture to form a video (i.e., picture-generated video), and make the above-generated pictures have the visual effect of observing the picture based on the observation perspective of the target observation object, so that the processed video has the ability to express the observation perspective of the target observation object.

[0068] At the same time, the perspective special effects content generated based on the above steps has at least one of the following target features, target camera movement features, target lens angles, and target painting style features; wherein the target camera movement features are used to characterize the lens movement rules of the video screen of the perspective special effects content; the target lens angle characterizes the lens angle of the video screen of the perspective special effects content; the target painting style features characterize the picture style of the video screen of the perspective special effects content; the target features are determined based on the target state or target observation object corresponding to the target perspective.

[0069] Fig. 9 A schematic diagram of generating perspective special effect content provided by an embodiment of the present disclosure, such as Fig. 9As shown, first, based on the interaction between the terminal device and the user, the terminal device obtains the image media and the target perspective, wherein the target perspective can be expressed in the form of text, and the target perspective is, for example, the text T1 shown in the figure. More specifically, the content of the text T1 is, for example, "the perspective of a fly", and the image media is, for example, the picture P1. Afterwards, the terminal device inputs the above-mentioned picture P1 and the text T1 into the content generation model. The video generation mode includes an inference sub-model and an image generation sub-model. After being processed by the inference sub-model and the image generation sub-model, the perspective special effect video V1 (i.e., the perspective special effect content) is output. Referring to the figure, first, the content features of the special effect video screen of the perspective special effect video V1 match the target perspective (i.e., "the perspective of a fly"), that is, the "perspective of a fly" is simulated to observe the content of the picture P1 (refer to the video screen P2 in the perspective special effect video V1 in the figure, the "hexagon" is used to express the visual effect of the fly's "compound eye"). Secondly, optionally, the perspective special effects video V1 may also have target style characteristics that match the target observation perspective, such as a "high contrast" style, to simulate and express the world in the eyes of the target perspective. Thirdly, optionally, during the playback of the perspective special effects video V1, the perspective special effects video V1 may also have target camera movement characteristics and target lens angles. For example, during the playback of the perspective special effects video V1, the perspective special effects video V1 presents a visual effect of rapid left and right shaking of the lens to simulate the behavioral characteristics of the target observation object; and observes the object from a bird's-eye view to simulate the observation point position of the target observation object. For example, when the observation point of the target observation object is relatively high (for example, the target observation object is an "elephant" and the target perspective is an "elephant's perspective"), the perspective special effects video V1 presents a visual effect of observing the object in the image P1 from a "bird's-eye view".

[0070] Of course, it is understandable that in other possible implementations, the image media can also be a video, such as video V0. Similar to the above process, after inputting the text T1 and video V0 into the content generation model, the content generation model will generate a corresponding perspective special effects video (i.e., perspective special effects content) after understanding and reasoning based on the content of the text T1. The specific implementation process will not be repeated here.

[0071] By inputting the target perspective into the content generation model, the content generation model can process the image media based on its own understanding of the target perspective, thereby generating self-consistent, streamlined and realistic perspective special effects content, and achieving control over multiple features such as video images and video lens movements. It is equivalent to a result-oriented AI video generation technology, which uses "perspective" to represent "special effects", thereby achieving the expression of complex video special effects. There is no need for users to control the picture change process of video generation, thereby improving video generation efficiency and video quality.

[0072] In this embodiment, by responding to user operations, a target perspective is determined, and the target perspective is used to characterize the observation perspective under the target state; image media is acquired, and a content generation model is called to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to show the visual effect of observing the image media based on the target perspective. By responding to user operations, a target perspective that characterizes the observation perspective of the target observation object is determined, and then, with the target perspective as input, the image generation model is called to process the image media to generate perspective special effects content, which includes the visual effect of observing the image media based on the observation perspective of the target observation object, thereby realizing video generation based on the perspective dimension. This process does not require the user to input overly complex descriptive words, so it can effectively improve the efficiency of video generation. At the same time, the generated perspective special effects content is a video generated by the content generation model based on its own understanding of the observation perspective of the target observation object, so the content consistency of the video is better, the authenticity is higher, and the quality of the generated video is improved.

[0073] refer to Fig.10 , Fig.10 A flow chart of a content generation method provided in an embodiment of the present disclosure Figure 2 In this embodiment Figure 2 On the basis of the illustrated embodiment, the interaction process is further refined, and the content generation method includes:

[0074] Step S201: displaying a second page, where a text input component is provided.

[0075] Step S202: In response to an input operation on a text input component in the second page, a target text is generated, and the target text is used to determine a target observation object.

[0076] Step S203: Generate a first prompt word according to the semantics of the target text, where the first prompt word is used to characterize the perspective feature of the observation perspective.

[0077] Step S204: Process the first prompt word through the pre-trained large language model to generate an observation object name, where the observation object name is used to indicate the observation object having the perspective feature of the observation perspective indicated by the first prompt word.

[0078] Step S205: Determine the target viewing angle according to the name of the observed object.

[0079] Exemplarily, the second page is a text input page, referring to Figure 2In the illustrated embodiment, the second page is introduced. After the terminal device displays the second page, the user inputs the target text by applying an input operation to the text input component in the second page, wherein the target text is information characterizing the characteristics of the target observation object. For example, the content of the target text is "a flying perspective that can see the distant horizon". At this time, the target text can characterize certain characteristics of the target observation object, but does not directly indicate a specific target observation object.

[0080] In this case, the terminal device performs semantic analysis on the target text by calling a large language model, and generates a corresponding first prompt word according to the semantics of the target text. The first prompt word is used to characterize the perspective feature of the observation perspective. For example, the first prompt word generated by the above target text is "having a high-altitude perspective, able to move quickly in the air, ...". After that, the first prompt word is processed by the pre-trained large language model to predict the observation object with the above perspective feature and generate the name of the observation object, such as "drone", "flying bird", etc. Then, the target perspective is determined, such as "drone perspective", "flying bird perspective", etc.

[0081] In this embodiment, the target file input by the user is processed in combination with a large language model to generate a target perspective recommended by the model, so that the user is not limited to using existing observation perspectives, or using common observation perspectives to generate perspective special effects content, thereby greatly improving the diversity and flexibility of observation perspectives, and improving video creation efficiency and interaction efficiency.

[0082] Step S206: Generate a second prompt word according to the target viewing angle, where the second prompt word is used to instruct the content generation model to generate a video based on the viewing angle of the target observation object.

[0083] Step S207: input the second prompt word and the image media into the content generation model to generate a special effect video.

[0084] Furthermore, after obtaining the target perspective, one possible implementation method is to directly input the target perspective (text) and media data into the content generation model, and use the content generation model's own reasoning ability and video generation ability to generate the corresponding perspective special effect content (i.e. Figure 2Implementation in the illustrated embodiment). In another possible implementation, the second prompt word can be first generated according to the target perspective, and then the second prompt word is input into the content generation model, and the video generation mode is guided to generate the corresponding video. In a possible implementation, the second prompt word can be a description text generated by analyzing the characteristics of the target observation object corresponding to the target perspective. For example, the target perspective is "the perspective of a fly", and the corresponding target observation object is "fly". After processing it based on the large language model, the corresponding description text is generated as "a flying insect, moving fast, irregular flight trajectory, with compound eyes, wide field of view...". Afterwards, based on the above description text, combined with the corresponding prompt word template, a second prompt word is generated to instruct the content generation model to infer the visual effect of the target perspective based on the content of the above description text, and then generate the corresponding special effects video. The scheme in this embodiment is equivalent to dividing the reasoning ability of the content generation model to the outside, using other language models as a supplement to the reasoning ability, thereby improving the performance of the content generation model, reducing the training cost of the content generation model, and ultimately achieving the purpose of improving the quality of the generated video.

[0085] Further, in one possible implementation, the second prompt word includes a first participle, and at least one of a second participle and a third participle, wherein the first participle is used to characterize the target observation object, the second participle is used to characterize the height and / or pitch angle of the observation point of the target observation object, and the third participle is used to characterize the movement law of the observation point of the target observation object and / or the movement law of the observation angle. For example, the content of the second prompt word is "a flying insect with compound eyes, moving at a height of less than 10 meters, and an irregular flight trajectory," wherein "a flying insect with compound eyes" is the first participle; "moving at a height of less than 10 meters" is the second participle; and "irregular flight trajectory" is the third participle. The second prompt word composed of one or more participles is input into the content generation model, thereby achieving the purpose of controlling the picture style of the video screen of the perspective special effect content (first participle), controlling the lens angle of the video screen of the perspective special effect content (second participle), and controlling the lens movement law of the video screen of the perspective special effect content (third participle), so that the generated perspective special effect content has the purpose of matching the target observation object with the target characteristics. The perspective special effects content can realize complex video special effects expression, and the process does not require the user to control the picture change process of the video generation, thereby improving the video generation efficiency and video quality. Among them, the specific content and expression of the target features are Figure 2 This has been introduced in the illustrated embodiment and will not be described again in detail here.

[0086] Corresponding to the content generation method of the above embodiment, Fig.11This is a structural block diagram of a content generation device provided in an embodiment of the present disclosure. The method described in the above embodiment can be executed by the content generation device, which can be implemented by software and / or hardware, and can be integrated in an electronic device with certain data processing functions. The electronic device can include but is not limited to a mobile terminal with big data processing capabilities, and a fixed terminal with big data processing capabilities such as a desktop computer and a supercomputer.

[0087] For the sake of convenience, only the parts related to the embodiments of the present disclosure are shown. Fig.11 , the content generating device 3 comprises:

[0088] An interaction module 31, for determining a target viewing angle in response to a user operation, where the target viewing angle is used to represent an observation viewing angle in a target state;

[0089] The generation module 32 is used to obtain image media, and call the content generation model to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has special effects video pictures, and the special effects video pictures are used to show the visual effects of observing the image media based on the target perspective.

[0090] According to one or more embodiments of the present disclosure, the user operation includes a selection operation, and the interaction module 31 is further used to: display a first page, on which special effect components corresponding to at least two observation perspectives are displayed; when the interaction module 31 determines the target perspective in response to the user operation, the interaction module 31 is specifically used to: in response to a selection operation on a target special effect component in the first page, determine the observation perspective corresponding to the target special effect component as the target perspective.

[0091] According to one or more embodiments of the present disclosure, the selection operation includes a first selection operation and a second selection operation. When the interactive module 31 determines the observation angle corresponding to the target special effect component as the target angle in response to the selection operation on the target special effect component in the first page, it is specifically used to: in response to the second selection operation on the target special effect component, display the special effect content page corresponding to the target special effect component, the special effect content page displays at least two special effect videos generated based on the observation angle corresponding to the target special effect component, and a confirmation component is provided in the special effect content page; in response to the first selection operation on the confirmation component, determine the observation angle corresponding to the target special effect component as the target angle.

[0092] According to one or more embodiments of the present disclosure, a preview area is provided in the special effect component, and the interactive module 31 is further used to: display the recommended special effect video corresponding to the special effect component in the preview area of ​​each special effect component in the first page; wherein the recommended special effect video is a video determined by sorting the video attributes of each special effect video among the special effect videos generated based on the observation perspective corresponding to the special effect component; the video attributes include the video generation time and / or the video access popularity.

[0093] According to one or more embodiments of the present disclosure, user operations include input operations; the interaction module 31 is also used to: display a second page, which is provided with a text input component; when the interaction module 31 determines the target perspective in response to the user operation, the interaction module 31 is specifically used to: generate a target text in response to the input operation on the text input component in the second page, and the target text is used to determine the target observation object; determine the target perspective based on the target text.

[0094] According to one or more embodiments of the present disclosure, when the interaction module 31 determines the target perspective based on the target text, it is specifically used to: generate a first prompt word based on the semantics of the target text, and the first prompt word is used to characterize the perspective characteristics of the observation perspective; process the first prompt word through a pre-trained large language model to generate an observation object name, and the observation object name is used to indicate the observation object having the perspective characteristics of the observation perspective indicated by the first prompt word; determine the target perspective based on the observation object name.

[0095] According to one or more embodiments of the present disclosure, the input operation includes a first trigger operation and a second trigger operation, a randomly generated component is configured in the second page, and the interaction module 31, when generating a target text in response to an input operation on the text input component in the second page, is specifically used to: in response to the first trigger operation on the randomly generated component of the second page, display the randomly generated text in the text input component of the second page, the randomly generated text is used to characterize the randomly generated observation object; in response to the second trigger operation on the second page, determine the randomly generated text as the target text.

[0096] According to one or more embodiments of the present disclosure, the perspective special effects content has at least one of the following target features: target camera movement features, target lens angles, and target painting style features; wherein the target camera movement features are used to characterize the lens movement patterns of the video images of the perspective special effects content; the target lens angles characterize the lens angles of the video images of the perspective special effects content; the target painting style features characterize the picture style of the video images of the perspective special effects content; the target features are determined based on the target state or target observation object corresponding to the target perspective.

[0097] According to one or more embodiments of the present disclosure, the generation module 32 is specifically used to: obtain a second prompt word corresponding to the target perspective, the second prompt word is used to instruct the content generation model to generate a video based on the observation perspective of the target observation object; input the second prompt word and image media into the content generation model to generate a special effects video.

[0098] According to one or more embodiments of the present disclosure, the second prompt word includes a first participle, and at least one of a second participle and a third participle, wherein the first participle is used to characterize the target observation object, the second participle is used to characterize the height and / or pitch angle of the observation point of the target observation object, and the third participle is used to characterize the movement law of the observation point of the target observation object and / or the movement law of the observation angle.

[0099] The interactive module 31 and the generating module 32 are connected. The content generating device 3 provided in this embodiment can execute the technical solution of the above method embodiment, and its implementation principle and technical effect are similar, which will not be described in detail in this embodiment.

[0100] Fig.12 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown in FIG. Fig.12 As shown, the electronic device 4 includes:

[0101] A processor 41, and a memory 42 communicatively connected to the processor 41;

[0102] The memory 42 stores computer executable instructions;

[0103] The processor 41 executes the computer execution instructions stored in the memory 42 to implement the following Figure 2-Figure 10 The content generation method in the illustrated embodiment.

[0104] Optionally, the processor 41 and the memory 42 are connected via a bus 43 .

[0105] For related instructions, please refer to Figure 2-Figure 10 The relevant descriptions and effects corresponding to the steps in the corresponding embodiments can be understood, and no further elaboration is made here.

[0106] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, which are used to implement the present invention when executed by a processor. Figure 2-Figure 10 The content generation provided by any one of the corresponding embodiments.

[0107] The present invention provides a computer program product, including a computer program. When the computer program is executed by a processor, the present invention is realized. Figure 2-Figure 10 The content generation method provided by any one of the corresponding embodiments.

[0108] In order to implement the above embodiment, the embodiment of the present disclosure also provides an electronic device.

[0109] refer to Fig.13 , which shows a schematic diagram of the structure of an electronic device 900 suitable for implementing the embodiment of the present disclosure, and the electronic device 900 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.13 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0110] like Fig.13 As shown, the electronic device 900 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 to a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0111] Typically, the following devices may be connected to the I / O interface 905: input devices 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 908 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.13 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0112] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 909, or installed from a storage device 908, or installed from a ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0113] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0114] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0115] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0116] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0117] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0118] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit or module does not, in some cases, constitute a limitation on the unit itself.

[0119] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0120] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0121] In a first aspect, according to one or more embodiments of the present disclosure, a content generation method is provided, including:

[0122] In response to user operation, a target perspective is determined, and the target perspective is used to characterize the observation perspective under the target state; image media is acquired, and a content generation model is called to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to display the visual effect of observing the image media based on the target perspective.

[0123] According to one or more embodiments of the present disclosure, the user operation includes a selection operation, and the method further includes: displaying a first page, wherein the first page displays special effect components corresponding to at least two observation perspectives; determining the target perspective in response to the user operation includes: in response to a selection operation on a target special effect component in the first page, determining the observation perspective corresponding to the target special effect component as the target perspective.

[0124] According to one or more embodiments of the present disclosure, the selection operation includes a first selection operation and a second selection operation, and the response to the selection operation on the target special effect component in the first page, the observation angle corresponding to the target special effect component is determined as the target angle, including: in response to the second selection operation on the target special effect component, a special effect content page corresponding to the target special effect component is displayed, the special effect content page displays at least two special effect videos generated based on the observation angle corresponding to the target special effect component, and a confirmation component is provided in the special effect content page; in response to the first selection operation on the confirmation component, the observation angle corresponding to the target special effect component is determined as the target angle.

[0125] According to one or more embodiments of the present disclosure, a preview area is provided in the special effect component, and the method further includes: displaying a recommended special effect video corresponding to the special effect component in the preview area of ​​each special effect component in the first page; wherein the recommended special effect video is a video determined by sorting video attributes of each special effect video among the special effect videos generated based on the observation angle corresponding to the special effect component; the video attributes include video generation time and / or video access popularity.

[0126] According to one or more embodiments of the present disclosure, the user operation includes an input operation; the method also includes: displaying a second page, the second page being provided with a text input component; determining the target viewing angle in response to the user operation, includes: generating a target text in response to the input operation on the text input component within the second page, the target text being used to determine the target observation object; and determining the target viewing angle based on the target text.

[0127] According to one or more embodiments of the present disclosure, a target perspective is determined according to the target text, including: generating a first prompt word according to the semantics of the target text, the first prompt word being used to characterize the perspective characteristics of the observation perspective; processing the first prompt word through a pre-trained large language model to generate an observation object name, the observation object name being used to indicate an observation object having the perspective characteristics of the observation perspective indicated by the first prompt word; and determining the target perspective according to the observation object name.

[0128] According to one or more embodiments of the present disclosure, the input operation includes a first trigger operation and a second trigger operation, a random generation component is configured in the second page, and the target text is generated in response to the input operation on the text input component in the second page, including: in response to the first trigger operation on the random generation component of the second page, displaying the randomly generated text in the text input component of the second page, the randomly generated text is used to characterize the randomly generated observation object; in response to the second trigger operation on the second page, determining the randomly generated text as the target text.

[0129] According to one or more embodiments of the present disclosure, the perspective special effects content has at least one of the following target features: target camera movement features, target lens angles, and target painting style features; wherein the target camera movement features are used to characterize the lens movement rules of the video screen of the perspective special effects content; the target lens angle characterizes the lens angle of the video screen of the perspective special effects content; the target painting style features characterize the picture style of the video screen of the perspective special effects content; the target features are determined based on the target state or target observation object corresponding to the target perspective.

[0130] According to one or more embodiments of the present disclosure, a content generation model is called to process the image media based on the target perspective to generate perspective special effects content, including: obtaining a second prompt word corresponding to the target perspective, the second prompt word being used to instruct the content generation model to generate a video based on the observation perspective of the target observation object; and inputting the second prompt word and the image media into the content generation model to generate the special effects video.

[0131] According to one or more embodiments of the present disclosure, the second prompt word includes a first participle, and at least one of a second participle and a third participle, wherein the first participle is used to characterize the target observation object, the second participle is used to characterize the height and / or pitch angle of the observation point of the target observation object, and the third participle is used to characterize the movement law of the observation point of the target observation object and / or the movement law of the observation angle.

[0132] In a second aspect, according to one or more embodiments of the present disclosure, there is provided a content generating device, including:

[0133] An interaction module, configured to determine a target viewing angle in response to a user operation, wherein the target viewing angle is used to characterize an observation viewing angle in a target state;

[0134] A generation module is used to obtain image media and call a content generation model to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to display the visual effect of observing the image media based on the target perspective.

[0135] According to one or more embodiments of the present disclosure, the user operation includes a selection operation, and the interaction module is further used to: display a first page, in which special effect components corresponding to at least two observation perspectives are displayed; when the interaction module determines the target perspective in response to the user operation, the interaction module is specifically used to: in response to a selection operation on the target special effect component in the first page, determine the observation perspective corresponding to the target special effect component as the target perspective.

[0136] According to one or more embodiments of the present disclosure, the selection operation includes a first selection operation and a second selection operation. When the interactive module determines the observation angle corresponding to the target special effect component as the target angle in response to the selection operation on the target special effect component in the first page, it is specifically used to: in response to the second selection operation on the target special effect component, display a special effect content page corresponding to the target special effect component, the special effect content page displaying at least two special effect videos generated based on the observation angle corresponding to the target special effect component, and a confirmation component is provided in the special effect content page; in response to the first selection operation on the confirmation component, determine the observation angle corresponding to the target special effect component as the target angle.

[0137] According to one or more embodiments of the present disclosure, a preview area is provided in the special effect component, and the interactive module is further used to: display a recommended special effect video corresponding to the special effect component in the preview area of ​​each special effect component in the first page; wherein the recommended special effect video is a video determined by sorting the video attributes of each special effect video among the special effect videos generated based on the observation angle corresponding to the special effect component; the video attributes include the video generation time and / or the video access popularity.

[0138] According to one or more embodiments of the present disclosure, the user operation includes an input operation; the interaction module is further used to: display a second page, the second page is provided with a text input component; when the interaction module determines the target perspective in response to the user operation, the interaction module is specifically used to: generate a target text in response to the input operation on the text input component in the second page, the target text is used to determine the target observation object; determine the target perspective based on the target text.

[0139] According to one or more embodiments of the present disclosure, when the interaction module determines the target perspective based on the target text, it is specifically used to: generate a first prompt word based on the semantics of the target text, and the first prompt word is used to characterize the perspective characteristics of the observation perspective; process the first prompt word through a pre-trained large language model to generate an observation object name, and the observation object name is used to indicate the observation object having the perspective characteristics of the observation perspective indicated by the first prompt word; determine the target perspective based on the observation object name.

[0140] According to one or more embodiments of the present disclosure, the input operation includes a first trigger operation and a second trigger operation, a random generation component is configured in the second page, and when the interactive module generates a target text in response to an input operation on the text input component in the second page, it is specifically used to: in response to the first trigger operation on the random generation component of the second page, display the randomly generated text in the text input component of the second page, the randomly generated text is used to characterize the randomly generated observation object; in response to the second trigger operation on the second page, determine the randomly generated text as the target text.

[0141] According to one or more embodiments of the present disclosure, the perspective special effects content has at least one of the following target features: target camera movement features, target lens angles, and target painting style features; wherein the target camera movement features are used to characterize the lens movement rules of the video screen of the perspective special effects content; the target lens angle characterizes the lens angle of the video screen of the perspective special effects content; the target painting style features characterize the picture style of the video screen of the perspective special effects content; the target features are determined based on the target state or target observation object corresponding to the target perspective.

[0142] According to one or more embodiments of the present disclosure, the generation module is specifically used to: obtain a second prompt word corresponding to the target perspective, the second prompt word is used to instruct the content generation model to generate a video based on the observation perspective of the target observation object; input the second prompt word and the image media into the content generation model to generate the special effects video.

[0143] According to one or more embodiments of the present disclosure, the second prompt word includes a first participle, and at least one of a second participle and a third participle, wherein the first participle is used to characterize the target observation object, the second participle is used to characterize the height and / or pitch angle of the observation point of the target observation object, and the third participle is used to characterize the movement law of the observation point of the target observation object and / or the movement law of the observation angle.

[0144] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, comprising: at least one processor and a memory;

[0145] The memory stores computer-executable instructions;

[0146] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the content generation method described in the first aspect and various possible designs of the first aspect.

[0147] In a fourth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the content generation method described in the first aspect and various possible designs of the first aspect is implemented.

[0148] In a fifth aspect, according to one or more embodiments of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the content generation method described in the first aspect and various possible designs of the first aspect.

[0149] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0150] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0151] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A content generation method, characterized in that: include: In response to a user operation, determining a target viewing angle, wherein the target viewing angle is used to characterize an observation viewing angle in a target state; Acquire image media, and call a content generation model to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to show the visual effect of observing the image media based on the target perspective.

2. The method according to claim 1, characterized in that: The user operation includes a selection operation, and the method further includes: Displaying a first page, wherein the first page displays special effect components corresponding to at least two observation perspectives; The step of determining the target viewing angle in response to the user operation includes: In response to a selection operation on a target special effect component in the first page, an observation angle corresponding to the target special effect component is determined as the target angle.

3. The method according to claim 2, characterized in that The selection operation includes a first selection operation and a second selection operation, and in response to the selection operation on the target special effect component in the first page, determining the observation angle corresponding to the target special effect component as the target angle, includes: In response to a second selection operation on a target special effect component, a special effect content page corresponding to the target special effect component is displayed, the special effect content page displays at least two special effect videos generated based on the observation angle corresponding to the target special effect component, and a confirmation component is provided in the special effect content page; In response to a first selection operation on the confirmation component, the observation angle corresponding to the target special effect component is determined as the target angle.

4. The method according to claim 2, characterized in that: A preview area is provided in the special effect component, and the method further includes: In the preview area of ​​each special effect component in the first page, a recommended special effect video corresponding to the special effect component is displayed; The recommended special effect video is a video determined by sorting the special effect videos according to the video attributes of the special effect videos generated based on the observation angle corresponding to the special effect component; The video attributes include video generation time and / or video access popularity.

5. The method according to claim 1, characterized in that The target viewing angle includes the viewing angle of the target observation object, and the user operation includes an input operation; the method further includes: Displaying a second page, wherein the second page is provided with a text input component; The step of determining the target viewing angle in response to the user operation includes: In response to an input operation on a text input component in the second page, generating a target text, wherein the target text is used to determine the target observation object; According to the target text, a target perspective is determined.

6. The method according to claim 5, characterized in that Based on the target text, determine the target perspective, including: generating a first prompt word according to the semantics of the target text, wherein the first prompt word is used to characterize the perspective feature of the observation perspective; Processing the first prompt word through a pre-trained model to generate an observation object name, where the observation object name is used to indicate an observation object having a viewing angle feature of the observation viewing angle indicated by the first prompt word; According to the name of the observed object, a target viewing angle is determined.

7. The method according to claim 5, characterized in that The input operation includes a first trigger operation and a second trigger operation, a random generation component is configured in the second page, and the generating of the target text in response to the input operation on the text input component in the second page includes: In response to a first trigger operation on the random generation component of the second page, displaying randomly generated text in the text input component of the second page, wherein the randomly generated text is used to represent the randomly generated observation object; In response to a second trigger operation on the second page, the randomly generated text is determined as a target text.

8. The method according to claim 1, characterized in that: The perspective special effect content has at least one of the following target characteristics: Target camera movement characteristics, target camera angles, and target painting style characteristics; The target camera movement feature is used to characterize the camera movement law of the video screen of the perspective special effect content; The target lens angle represents the lens angle of the video picture of the perspective special effect content; The target style feature represents the style of the video image of the perspective special effect content; The target feature is determined based on the target state or target observation object corresponding to the target viewing angle.

9. The method according to claim 1, characterized in that: Calling a content generation model to process the image media based on the target perspective to generate perspective special effect content includes: Acquire a second prompt word corresponding to the target viewing angle, where the second prompt word is used to instruct the content generation model to generate a video based on the viewing angle of the target observation object; The second prompt word and the image media are input into the content generation model to generate the special effect video.

10. The method according to claim 9, characterized in that The second prompt word includes a first participle, and at least one of a second participle and a third participle, wherein the first participle is used to characterize the target observation object, the second participle is used to characterize the height and / or pitch angle of the observation point of the target observation object, and the third participle is used to characterize the movement law of the observation point and / or the movement law of the observation angle of the target observation object.

11. A content generating device, characterized in that: include: An interaction module, configured to determine a target viewing angle in response to a user operation, wherein the target viewing angle is used to characterize an observation viewing angle in a target state; A generation module is used to obtain image media and call a content generation model to process the image media based on the target perspective to generate perspective special effects content, wherein the perspective special effects content has a special effects video screen, and the special effects video screen is used to display the visual effect of observing the image media based on the target perspective.

12. An electronic device, characterized in that: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the content generation method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the content generation method according to any one of claims 1 to 10 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the content generating method according to any one of claims 1 to 10 is implemented.

Images