Method, apparatus, device and storage medium for generating video

Abstract

Embodiments of the present disclosure relate to a method, device, equipment and storage medium for generating a video. The method proposed herein comprises: in response to receiving a video creation request in an interactive interface, obtaining at least one item of media content; in a first interface, presenting creation information generated based on the at least one item of media content, the creation information comprising scheme description content associated with at least one video creation scheme; and in a second interface, providing at least one item of video content generated based on the at least one video creation scheme. In this way, the embodiments of the present disclosure can improve the efficiency of generating video content.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatus, devices, and computer-readable storage media for generating video. Background Technology

[0002] With the development of computer technology, people can share or access media content through internet platforms. Media editing tools have also gradually become important tools in people's lives; for example, people can use media editing tools to edit or generate video content and share it through media platforms. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for generating a video is provided. The method includes: in response to receiving a video creation request in an interactive interface, acquiring at least one piece of media content; presenting creation information generated based on the at least one piece of media content in a first interface, the creation information including scheme description content associated with at least one video creation scheme; and providing at least one piece of video content generated based on at least one video creation scheme in a second interface.

[0004] In a second aspect of this disclosure, an apparatus for generating video is provided. The apparatus includes: a material acquisition module, an information presentation module, and a first video viewing module. The material acquisition module is configured to acquire at least one piece of media content in response to receiving a video creation request in an interactive interface; the information presentation module is configured to present creation information generated based on at least one piece of media content in a first interface, the creation information including a scheme description associated with at least one video creation scheme; and the first video viewing module is configured to provide at least one piece of video content generated based on at least one video creation scheme in a second interface.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0008] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram is shown of an example environment in which embodiments of the present disclosure may be implemented;

[0011] Figures 2A to 2G Example interfaces according to some embodiments of this disclosure are shown;

[0012] Figure 3 A schematic diagram illustrating an example implementation process for generating video according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A flowchart illustrating an example process for generating video according to some embodiments of this disclosure is shown;

[0014] Figure 5 A schematic structural block diagram of an example apparatus for generating video according to some embodiments of the present disclosure is shown; and

[0015] Figure 6 A block diagram of an electronic device capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0018] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0019] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0020] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0021] As mentioned above, media editing tools are gradually becoming important tools in people's lives, allowing them to edit or generate video content. With the increasingly widespread application of generative models, various generative models are now embedded in some media editing tools in order to improve media editing efficiency.

[0022] With the current technology, the number of tools associated with generative models in media editing applications is increasing, and the entry points are becoming more scattered. This makes it easy to confuse some editing tools or entry points, making it difficult to find tools and entry points, and the maintenance costs of tools are also gradually increasing.

[0023] In addition, different editing tools in related media editing applications have different model effects, making it difficult to create cross-type videos. As a result, users with multiple video creation needs need to repeatedly switch between different editing tools, which is not only cumbersome but also inefficient.

[0024] Embodiments of this disclosure propose a scheme for generating videos. The scheme includes: in response to receiving a video creation request in an interactive interface, acquiring at least one piece of media content; in a first interface, presenting creation information generated based on the at least one piece of media content, the creation information including scheme description content associated with at least one video creation scheme; and in a second interface, providing at least one piece of video content generated based on at least one video creation scheme.

[0025] In this way, according to the embodiments provided in this disclosure, at least one video creation scheme for at least one type of media content can be quickly generated using a model, thereby ensuring the relevance and relevance between the video creation scheme and the media content; and accordingly, the corresponding video creation tools can be invoked to quickly generate at least one type of video content based on the video creation scheme generated by the model, thereby improving the efficiency of video content generation and video quality.

[0026] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0027] Example Environment

[0028] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. For example... Figure 1 As shown, example environment 100 may include electronic device 110.

[0029] In this example environment 100, electronic device 110 may run an application 120 that supports video generation. Application 120 may be any suitable type of application for generating video, examples of which may include, but are not limited to, media editing applications, video generation applications, or other suitable applications. User 140 may interact with application 120 via electronic device 110 and / or its attached devices.

[0030] exist Figure 1 In environment 100, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting video generation.

[0031] In some embodiments, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0032] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for the video generation application 120 in electronic device 110.

[0033] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and electronic device 110 can achieve signaling interaction through the communication connection between them.

[0034] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0035] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.

[0036] Example Interaction

[0037] Figures 2A to 2G Example interfaces 200A to 200G according to some embodiments of the present disclosure are shown. Interfaces 200A to 200G may, for example, be provided by... Figure 1 The electronic device 110 shown is provided.

[0038] In some embodiments, such as Figure 2A As shown, the electronic device 110 can present an interactive interface 200A. As an example, the interactive interface 200A can be the homepage of a media editing application, such as an editing interface, or it can be an interface that presents content including media content, text content, etc., or it can be an interface that enables interaction such as virtual social interaction, media playback, or video creation.

[0039] refer to Figure 2A As shown, the exemplary interactive interface 200A presented by the electronic device 110 is the editing interface of a media editing application, and a generation entry 210 is provided in the interactive interface 200A.

[0040] In some embodiments, the electronic device 110 may determine that a video creation request has been received upon being triggered by the generation entry 210. Furthermore, the electronic device 110 may present a material acquisition interface based on the video creation request, for example... Figure 2B The interface 200B shown can also present other interactive interfaces such as a media generation interface. As an example, the electronic device 110 can present a generation entry point in the media content playback interface, so that users can quickly create videos based on creative ideas obtained during the browsing of media content, thereby improving video generation efficiency.

[0041] In some embodiments, in response to the triggering of the generation entry 210, the electronic device 110 may verify the user's login information before presenting the material acquisition interface.

[0042] In some embodiments, during or after presenting the material acquisition interface, the electronic device 110 may first present a preset sample video for the user to preview. For example, the sample video may be a demonstration video showcasing a sample video generation process performed based on the generation entry point 210.

[0043] by Figure 2B Taking interface 200B as an example, electronic device 110 presents multiple candidate media content (or media materials) 201 on interface 200B. As an example, the multiple candidate media content 201 presented on interface 200B can be media content stored in electronic device 110, or media content stored in server 130 or other cloud environments, and is not limited here.

[0044] In some embodiments, the electronic device 110 may present at least one level of filter tags in the interface 200B. As an example, the electronic device 110 may present a first-level tag, which may be a source tag, such as local / cloud / online media library, etc.; then, based on the selection of any item in the first-level media tag, the electronic device 110 may further present a second-level tag, which may be a type tag, such as all / video / image / live, etc., so that users can quickly find the media content they need.

[0045] In some embodiments, the electronic device 110 may present multiple candidate media content 201 by presenting a cover image. The electronic device 110 may present at least one piece of information about the candidate media content, such as its content image and duration, in the cover image.

[0046] As an example, when the cover image of candidate media content is triggered, the electronic device 110 can display a preview interface of the candidate media content. For instance, if the candidate media content is video footage, the electronic device 110 can play the video footage within the preview interface. As another example, if the candidate media content is image footage, the electronic device 110 can display a scaled-down version of the image footage at a preset specification within the preview interface, allowing the user to view more image details.

[0047] In some embodiments, the electronic device 110 may also display a selection identifier 201-1 at an associated position on the cover of the candidate media content (e.g., the upper right corner, lower right corner, upper left corner, or center). As an example, the selection identifier 201-1 may indicate whether the corresponding candidate media content has been selected. For instance, in response to receiving the first or an odd number of triggers to the selection identifier 201-1, the electronic device 110 determines that the candidate media content corresponding to the selection identifier is selected and can configure the selection identifier to a selected state, for example, by displaying a "√" element or a number element, where the number element indicates that the candidate media content is the Xth selected media content. As another example, in response to the selection identifier 201-1 not being triggered or being triggered an even number of times, the electronic device 110 can determine that the candidate media content corresponding to the selection identifier is not selected and can then configure the selection identifier to an unselected state, for example, by displaying an initial state.

[0048] In some embodiments, the electronic device 110 may also be configured with preset material selection conditions, such as material quantity conditions, material duration conditions, and material type conditions. As an example, the material quantity condition may include selecting up to 30 or 50 materials (or media content); the material duration condition may include the minimum duration of a single material, the maximum duration of a single material, and the minimum and maximum total duration of the selected materials; the material type may include allowed or disallowed material types, such as still images, videos, moving images, and audio, which are not limited here.

[0049] In some embodiments, the electronic device 110, in response to the selection of at least one media content (e.g., media content 201a, 201b, 201c) from a plurality of candidate media content 201, presents a media panel 220. In the media panel 220, the electronic device 110 presents the identifier elements of the selected media content (e.g., Figure 2B Identifier elements 221a, 221b and 221c in the selected media content, such as the cover image of the selected media content.

[0050] As an example, the electronic device 110 can also deselect the media content corresponding to the identifier element based on the triggering of the identifier element presented in the media panel 220.

[0051] In some embodiments, the electronic device 110 may also display material prompts 222 in the material panel 220, such as "Selecting XX materials will produce better results".

[0052] In some embodiments, the electronic device 110 may also present media processing controls 223 in the media panel 220. As an example, the media processing controls 223 may be presented as "Next," "Process Media," or "Generate Video," etc.

[0053] In some embodiments, in response to the triggering of the media processing control 223, the electronic device 110 can generate a corresponding video creation request based on media content (e.g., media content 201a, 201b, 201c) selected from at least one media content 201.

[0054] In some embodiments, after receiving a video creation request, the electronic device 110 can send the media content selected in the material acquisition interface to a preset model, and use the preset model to identify and analyze the media content to obtain at least one video creation scheme for at least one selected media content. As an example, the preset model can be a pre-trained content understanding model.

[0055] In some embodiments, the electronic device 110 can send all the selected media content to the preset model, or it can perform frame extraction processing on the selected media content according to preset rules to obtain multiple material frames, and then send the multiple material frames to the preset model for recognition and analysis.

[0056] In some embodiments, the preset model performs image recognition and analysis on the received media content or multiple material frames to obtain the image description information of the media content, as well as material association information such as the number of segments and duration of the media content, and can further obtain editing information such as editing schemes for the media content.

[0057] In some embodiments, the electronic device 110 can present a media analysis interface based on the triggering of the media processing control 223, for example... Figure 2C The interface 200C shown presents creative information generated by a preset model based on the selected media content. As an example, this creative information may include at least one of the following: material analysis progress information, at least one material description generated based on the media content, and a scheme description associated with at least one video creation scheme. The scheme description may include theme information and / or editing information associated with the video creation scheme.

[0058] refer to Figure 2C As shown, in the media analysis interface 200C, the electronic device 110 can dynamically display the processing progress information 231 of the preset model on the media content. As an example, the electronic device 110 can dynamically display "Media analysis progress XX%", "Media processing in progress...XX%", or "Analyzing the final product concept XX%", etc.

[0059] In some embodiments, the electronic device 110 may also present, in the interface 200C, a scheme description content 232 of at least one video creation scheme generated by a preset model based on selected media content in the form of streaming output (e.g., word-for-word output). As an example, the scheme description content 232 may include at least one of the following descriptive information of at least one video creation scheme: theme description information, event description information, video editing information, etc. For example, the electronic device 110 may present "Based on the material of 'XXXXX,' different styles of editing schemes in XX were designed: Theme 1, Event Description Information 1, Video Editing Scheme 1; Theme 2, Event Description Information 2, Video Editing Scheme 2," etc.

[0060] In some embodiments, the electronic device 110 may present the above-described content 232 in any form, such as a table, a list, or a segmented format, without limitation.

[0061] Continue to refer to Figure 2CAs shown, in the material analysis interface 200C, the electronic device 110 can also provide input controls 233.

[0062] As an example, the electronic device 110 can receive user input information via input control 233, which can be used as supplementary information or modification suggestions for the scheme description content 232, and the received input information is provided to the preset model. Then, the preset model regenerates at least one video creation scheme based on the input information, and further calls the corresponding video creation tool to generate at least one corresponding video content.

[0063] In practical applications, if users are not satisfied with the solution description presented in the material analysis interface 200C or have other supplementary ideas, they can input them through the input control 233, which will be received by the electronic device 110 and provided to the preset model.

[0064] Comprehensive reference Figure 2C and Figure 2D As shown, in response to a triggering of the input control 233, the electronic device 110 can present an information input box 233-1 and an input panel 233-2. As an example, the electronic device 110 can receive input information 233a via the input panel 233-2 and display it in the information input box 233-1.

[0065] The electronic device 110 can also display an information processing control 233b in the information input box 233-1. Based on the triggering of the information processing control 233b, the electronic device 110 provides the received input information 233a to the preset model to update the video creation scheme for the selected media content.

[0066] In some embodiments, the electronic device 110 may present the input control 233 at the beginning of the presentation of the material analysis interface 200C, or it may present the input control 233 in response to the information presented in the material analysis interface 200C meeting the preset conditions. No limitation is made here.

[0067] As an example, the electronic device 110 may present the input control 233 when the processing progress indicated by the processing progress information 231 reaches a preset progress (e.g., 50%, 60%, or 100%), when the scheme description content 232 is started to be presented, after the scheme description content of at least one video creation scheme has been presented, or after the scheme description content 232 has been presented.

[0068] Continue to refer to Figure 2C As shown, in the media analysis interface 200C, the electronic device 110 can also display a first generation control 240. As an example, based on the triggering of the first generation control 240, the electronic device 110 can invoke video creation tools to generate at least one piece of video content based on the selected media content.

[0069] In some embodiments, if a complete description of a video creation scheme associated with any video creation scheme has not yet been presented in the media analysis interface 200C when the first generation control 240 is triggered, the electronic device 110 may determine at least one video template based on the selected media content and call the video creation tool corresponding to the at least one video template to generate at least one video content.

[0070] In some embodiments, if a description of a scheme associated with at least one video creation scheme has been presented in the material analysis interface 200C when the first generation control 240 is triggered, the electronic device 110 can call at least the video creation tool corresponding to the presented video creation scheme to generate at least one video content.

[0071] In some embodiments, if the media analysis interface 200C has already presented a scheme description associated with at least one video creation scheme when the first generation control 240 is triggered, the electronic device 110 can also determine at least one video template based on the selected media content and call the video creation tool corresponding to the at least one video template to generate at least one video content.

[0072] In some embodiments, the electronic device 110, triggered by the first generation control 240, can display a video viewing interface, for example... Figure 2E The interface shown is 200E.

[0073] Reference Figure 2E As shown, the electronic device 110 can provide at least one set of video content 250 generated by a video authoring tool based on selected media content in the video viewing interface 200E. As an example, the at least one set of video content 250 may include a first set of video content generated by the video authoring tool based on at least one video authoring scheme generated by a preset model, or it may include a second set of video content generated by the video authoring tool based on at least one video template and the selected media content. The at least one video template is determined based on the selected media content.

[0074] In some embodiments, the electronic device 110 can be configured to generate a first number (e.g., 10 or 8) of video content by calling a video creation tool in one go. As an example, the electronic device 110 can also be configured such that the number of video content generated by a video creation scheme based on a first model is less than or equal to a second number, wherein the first number is greater than or equal to the second number. For the video content corresponding to the difference between the first and second numbers, the electronic device 110 can call the video creation tool to generate it based on a second video template.

[0075] Taking a first quantity of 10 as an example, the electronic device 110 can call the video creation tool to generate 5 or fewer videos based on the video creation scheme generated by the first model, such as 4, and call the video creation tool to generate 6 video contents based on the video template; if the first generation control 240 is triggered before the first model generates the video creation scheme, the electronic device 110 can call the video creation tool to generate 10 video contents based on the video template.

[0076] In some embodiments, once the electronic device 110 determines that a video content of one or more has been generated, it can display the video content in the video viewing interface 200E.

[0077] In some embodiments, the electronic device 110 may display a preview entry 251 corresponding to at least one piece of video content 250 in the video viewing interface 200E. As an example, the electronic device 110 may display the cover image of the video content and the title text of the video content in the preview entry 251. The cover image of the video content may be the first frame image or any intermediate video frame image.

[0078] In some embodiments, the title text of the video content may be generated by a second model based on at least one of the following: at least one piece of media content; text information associated with the video creation tool; video creation scheme, etc. For example, material event information corresponding to at least one piece of media content, narration text or video theme generated by the video creation tool, creation theme associated with the video creation scheme generated by a preset model based on at least one piece of media content, etc.

[0079] In some embodiments, in response to the triggering of a preview entry for any video content, the electronic device 110 may display at least one video frame of the video content in the playback area 255 of the video viewing interface 200E.

[0080] like Figure 2E As shown, in response to the triggering of a preview entry for any video content, the electronic device 110 can also present a video editing entry 260 for that video content at a location associated with the preview entry, such as a location that covers the preview entry. Through the editing entry 260, the electronic device 110 can receive editing requests for the video content and present an editing interface for that video content.

[0081] In some embodiments, in response to the triggering of the editing entry 260 corresponding to the target video content, the electronic device 110 may present an editing interface for the target video content, for example... Figure 2F The interface shown is 200F.

[0082] refer to Figure 2FAs shown, in the editing interface 200F, the electronic device 110 can present a set of editing controls 265. As an example, a set of editing controls 265 may include screen editing controls for screen content, text editing controls for text content such as subtitles and / or copywriting, sound editing controls for audio content such as background music or voice, and may also include control entries for other editing controls such as effects, templates, stickers, etc.

[0083] Accordingly, the electronic device 110 can receive editing information for at least one of the following aspects of the target video content via a set of editing controls 265: image content, text content, audio content, etc. The specific editing information and the editing process for that information can be found in related technical solutions and will not be elaborated upon here.

[0084] Return to reference Figure 2E As shown, in the video viewing interface 200E, the electronic device 110 can also present a second generation control 270. As an example, the second generation control 270 can be an update control for at least one piece of video content 250 that has been presented. For example, the second generation control 270 can be configured to present "Update Video" or "Regenerate," etc.

[0085] In some embodiments, in response to the second generation control 270 being triggered, the electronic device 110 re-invokes the video authoring tool to update at least one piece of presented video content 250.

[0086] As an example, in response to the second generation control 270 being triggered, the electronic device 110 can switch the video frame presented in the preview area 255 to a preset image or progress information.

[0087] refer to Figure 2G As shown, in the video viewing interface 200G, the electronic device 110 can also display a third generation control 280. As an example, the third generation control 280 can be configured to generate and display a preset number of video contents.

[0088] In some embodiments, in response to the triggering of the third generation control 280, the electronic device 110 determines at least one video template based on the media content selected in the material acquisition interface, and calls the corresponding video creation tool based on the at least one video template to generate at least one new video content based on the selected media content and the at least one video template, and presents it after the at least one video content 250.

[0089] Example process

[0090] Figure 3A schematic diagram of an example implementation process 300 for generating video according to some embodiments of the present disclosure is shown. Process 300 can be implemented at electronic device 110. Reference is made below. Figure 1 To describe process 300.

[0091] refer to Figure 3 As shown, the electronic device 110 acquires at least one media content 301 based on the user's selection operation; then it performs frame extraction processing on the at least one media content 301 and sends it to the content understanding model 310 to obtain screen description information 311, duration and number of segments information 312 and screen summary information 313 for the at least one media content 301.

[0092] In some embodiments, the screen description information 311 may include at least one event description text corresponding to at least one media content 301. The number of event description texts may be greater than or equal to the number of media content 301. For example, if the electronic device 110 acquires three media content items 301, the screen description information 311 output by the content understanding model 310 may include event description texts corresponding to at least three events. One of the media content items may correspond to one or more event description texts.

[0093] The duration and number of segments information 312 includes the duration information of each material of at least one media content 301, the total duration of the material, and the number of material segments.

[0094] The screen summary information 313 may include a summary description of all screen content of at least one media content 301.

[0095] In some embodiments, the electronic device 110 can present duration and segment number information 312 and screen summary information 313 on an interactive interface (e.g., a material analysis interface) so that users can understand and view them.

[0096] In some embodiments, the electronic device 110 may provide screen description information 311 to the generative model 320 to generate at least one video creation scheme for at least one piece of media content 301. As an example, the video creation scheme may include a final product scheme 321 and a COT (Chain of Thought) process document 322.

[0097] In some embodiments, the finalization scheme 321 may include n finalization paths and n finalization information corresponding to each of the n finalization paths, where n is an integer greater than or equal to 1. The finalization path may indicate the video editing tool corresponding to each finalization method, such as editing tools for at least one aspect of media content, including shot composition, highlights, narration / text, playback speed, and background music. The finalization information may indicate tool call information for the video editing tools corresponding to each of the aforementioned finalization paths; for example, it may include search information or prompts associated with the aforementioned video editing tools.

[0098] In some embodiments, the COT process document 322 may include descriptive information such as the final theme of the media content, the final reasoning process, and the expected editing process. For example, for media content 1, which is suitable for the theme XX, it can be edited using the XXX editing tool.

[0099] As an example, electronic device 110 can present the COT process document 322 on an interactive interface (such as a material analysis interface) so that users can understand and access it.

[0100] In some embodiments, to make the output information of the generative model 320 more accurate and better adapted to the media content 301, the electronic device 110 may provide auxiliary decision-making information 314 and output format information 315 in addition to providing image description information 311 to the generative model 320. The auxiliary decision-making information 314 may include auxiliary information such as scheme description information and editing merit descriptions for each final cut path; the output format information 315 may include the output format requirements corresponding to the final cut scheme 321 and the COT process document 322, such as at least one output requirement information such as text format and text word count.

[0101] In some embodiments, a user can view the COT process document 322 via an interactive interface. If the user is not satisfied with the finalized solution presented in the COT process document 322, they can input supplementary information 316 into the electronic device 110. For example, the user can use the input control 233 in the interface 200C to input supplementary information 316 into the electronic device 110. The electronic device 110 then provides the received supplementary information 316 to the generative model 320 to update the finalized solution 321.

[0102] After obtaining the final film scheme 321 based on the output of the generative model 320, the electronic device 110 can determine and call the video creation tool 330 corresponding to each final film path based on the final film scheme 321 to generate at least one video content.

[0103] In some embodiments, the video creation tool 330 includes a template matching tool 331. As an example, the template matching tool 331 can determine at least one video template that matches at least one piece of media content 301, and generate corresponding video content accordingly. Accordingly, the tool invocation information corresponding to the template matching tool 331 may include a first search term associated with the template matching tool 331. For example, template theme tags, special effects tags in the template, etc.

[0104] In some embodiments, the video creation tool 330 includes a clip editing tool 332. As an example, the clip editing tool 332 can perform at least one editing operation on at least one piece of media content, such as shot segmentation, highlight extraction, scene reordering, and speed adjustment. Correspondingly, the tool invocation information for the clip editing tool 332 may include first prompt information associated with the clip editing tool 332, such as the number of highlight clips and the duration of the highlight clips.

[0105] In some embodiments, the video authoring tool 330 includes an audio generation tool 333. As an example, the audio generation tool 333 can generate corresponding audio content based on the screen description information 311 or preset text information, and add it to the video content.

[0106] In some embodiments, the tool invocation information corresponding to the audio generation tool 333 includes a second prompt message associated with the audio generation tool 333, such as audio duration and audio timbre.

[0107] In some embodiments, the video creation tool 330 includes a music matching tool 334. As an example, the audio matching tool 334 may include at least one of the following: a music recommendation tool, a music generation tool, a music trimming tool, a music beat matching tool, etc.

[0108] In some embodiments, the electronic device 110 may determine at least one piece of music content that matches at least one piece of media content 301 based on the music matching tool 334, and perform adaptive editing of the at least one piece of music content with at least one piece of media content 301 to obtain corresponding video content.

[0109] Correspondingly, the tool call information for the music matching tool 335 includes a second search term associated with the music matching tool. For example, music title, music style, music author, etc.

[0110] In some embodiments, the video authoring tool 330 includes a text generation tool 335. As an example, the electronic device 110 may use the text generation tool 335 to generate text that matches at least one piece of media content 301.

[0111] As an example, the electronic device 110 can combine the text generation tool 335 with the audio generation tool 333 to generate corresponding audio content from the text generated by the text generation tool 335, and perform adaptive editing with at least one piece of media content 301 to obtain corresponding video content.

[0112] As an example, the tool invocation information corresponding to the text generation tool 335 includes third-party prompts associated with the text generation tool 335. These may include text tags, text themes, and text styles.

[0113] In some embodiments, the video creation tool 330 may also include other auxiliary tools such as an effects matching tool 336 and a text matching tool 337. The effects matching tool 336 can identify at least one effects that match at least one piece of media content 301 and add it to the media content 301. The text matching tool 337 can search for at least one preset text that matches the media content 301 from a preset text data set. It can also be combined with the audio generation tool 333 to generate corresponding audio content from the identified at least one preset text, and then perform adaptive editing with the media content 301 to generate corresponding video content.

[0114] Continue to refer to Figure 3 As shown, the electronic device 110 can generate n video content items by calling the video creation tool 330, and then sort the generated n video content items according to the preset sorting strategy 340 to obtain the final result 302 corresponding to the n final pieces.

[0115] Figure 4 A flowchart of an example process 400 for generating video according to some embodiments of the present disclosure is shown. Process 400 can be implemented at electronic device 110. Reference is made below. Figure 1 To describe process 400.

[0116] like Figure 4 As shown in box 410, electronic device 110, in response to receiving a video creation request in the interactive interface, acquires at least one piece of media content.

[0117] As an example, the interactive interface can be referenced. Figure 2A The editing interface 200A shown indicates that the electronic device 110 can receive a video creation request based on the triggering of the generation entry 210, and at least one piece of media content can be referenced. Figure 2B The media content shown is 201a, 201b, and 201c.

[0118] In frame 420, electronic device 110 presents creation information generated based on at least one media content in a first interface, the creation information including scheme description content associated with at least one video creation scheme.

[0119] As an example, the first interface can be referenced. Figure 2C The interface shown is 200C or Figure 2D The interface shown is 200D. You can refer to the creation information or scheme description content. Figure 2C and Figure 2D The video creation scheme described in Scheme Description 232 can be referenced from "Theme 1, XXXXXXXX", "Theme 2, XXXXXXXX", and "Theme 3, XXXXXXXX".

[0120] In frame 430, electronic device 110 provides at least one video content generated based on at least one video creation scheme in a second interface.

[0121] As an example, the second interface can be referenced. Figure 2E The interface shown is 200E and Figure 2G The interface shown is 200G, and at least one video content can be referenced, with at least one video content of 250.

[0122] In this way, the present disclosure embodiments analyze the acquired media content, obtain a video creation scheme associated with the media content, and generate video content accordingly. This can effectively ensure the relevance and effectiveness between the creation scheme and the media content, thereby ensuring the quality of video content generation and improving the efficiency of video content generation.

[0123] In some embodiments, in a first interface, creative information generated based on at least one media content is presented, including: in the first interface, presenting a first portion of the creative information, the first portion indicating material description content generated based on at least one media content; and in the first interface, presenting a second portion of the creative information, the second portion indicating scheme description content generated based on the material description content.

[0124] In this way, the embodiments of this disclosure can present the material description content generated based on at least one media content and the solution description content corresponding to the video creation solution on the first interface, so that users can understand and view the corresponding material description information and solution description content in a timely manner, making it easier for users to understand the video generation solution and improving the interaction quality and user experience.

[0125] In some embodiments, the scheme description content indicates at least one of the following: thematic information associated with the video creation scheme; and editing information associated with the video creation scheme.

[0126] In this way, the embodiments of this disclosure can clearly and concisely present the subject information and editing information associated with the creative scheme, making it easy for users to understand and consult, and effectively improving interaction efficiency, interaction quality and user experience.

[0127] In some embodiments, the first interface includes a generation control, and the second interface provides at least one video content generated based on at least one video creation scheme, including: in response to the generation control being triggered, presenting the second interface, which provides at least one video content generated based on at least one video creation scheme.

[0128] As an example, you can refer to the following for generating controls. Figure 2C The first generation control 240 is shown.

[0129] In this way, the embodiments of this disclosure can effectively ensure the user's confirmation of the information presented in the first interface based on the triggering of the generated controls in the first interface, and then present the second interface and the corresponding video content. This can effectively ensure the presentation effect of the information presented in the first interface and the user's viewing experience, and ensure the accuracy and effectiveness of the presented video content, avoid unnecessary repeated generation or editing operations, and improve video generation efficiency.

[0130] In some embodiments, the first interface includes an input control, and process 400 further includes: the electronic device 110 acquiring input information via the input control; and regenerating a video creation scheme based on the input information for generating corresponding video content.

[0131] As an example, the input control can be referenced. Figure 2C The input control 233 shown can be used as a reference for input information. Figure 2D The input information shown is 233a.

[0132] In this way, the embodiments of this disclosure can regenerate the video creation scheme based on the input information, which can effectively ensure the effectiveness of the video creation scheme, thereby ensuring the effectiveness of the generated video content, ensuring the quality of video generation, and improving the efficiency of video generation.

[0133] In some embodiments, at least one video content corresponds to a first set of video content, and process 400 further includes: electronic device 110 providing a second set of video content generated based on a set of video templates and at least one media content in a second interface, wherein the set of video templates is determined based on at least one media content.

[0134] In this way, the embodiments of this disclosure can determine a video template that matches the media content and generate video content corresponding to the media content, ensuring the compatibility between the video template and the media content, thereby ensuring the effectiveness and quality of the generated video content, and improving the efficiency of video generation and the diversity and richness of the generated video content.

[0135] In some embodiments, process 400 further includes: electronic device 110 presenting a preview entry corresponding to at least one video content in a second interface, the preview entry presenting title text associated with at least one video content.

[0136] In this way, the present embodiment can quickly view the title text of video content through the preview entry, improving the presentation effect and viewing efficiency of video content and enhancing the user interaction experience.

[0137] In some embodiments, the title text is generated by a second model based on at least one piece of information: at least one piece of media content; editorial information associated with at least one piece of media content; and at least one video creation scheme.

[0138] In this way, the embodiments of this disclosure can fully guarantee the relevance between the title text and the media content, thereby ensuring the effectiveness of the title text.

[0139] In some embodiments, process 400 further includes: in response to receiving a generation request before creation information is generated, electronic device 110 triggers a halt to the generation of creation information and provides video content generated based on a video template, the video template being determined based on at least one type of media content.

[0140] In this way, the embodiments of this disclosure can quickly determine the video template corresponding to the media content and generate video content accordingly, effectively ensuring the efficiency of video content generation and the compatibility between the video template and the media content, thereby ensuring the video quality and effectiveness of the generated video content.

[0141] In some embodiments, process 400 further includes: electronic device 110 receiving an editing request for target video content in at least one video content; and in response to the editing request, presenting an editing interface for the target video content.

[0142] As an example, electronic device 110 can be via... Figure 2E The editing entry 260 shown receives the corresponding editing request. The editing interface can be found by referring to [the documentation / reference]. Figure 2F The interface shown is 200F.

[0143] In this way, the embodiments of this disclosure can further edit the generated video content to ensure the video quality of the generated video content.

[0144] In some embodiments, at least one piece of video content is generated based on the following process: providing a model with at least one piece of media content and tool description information of a set of candidate video creation tools; using the model to determine a video creation tool that matches the video creation scheme from the set of candidate video creation tools; and generating tool invocation information associated with the video creation tool by the model, so that the video creation tool can generate video content corresponding to the video creation scheme based on the tool invocation information.

[0145] In some implementations, providing the model with at least one piece of media content and tool description information for a set of candidate video creation tools includes: the electronic device 110 providing at least one piece of media content to a first sub-model of the model, generating material description information corresponding to the at least one piece of media content; and then providing the material description information and tool description information for a set of candidate video creation tools to a second sub-model of the model, so as to determine the video creation tool that matches the video creation scheme from the set of candidate video creation tools.

[0146] As an example, the first sub-model can be referenced. Figure 3 The content comprehension model 310 shown can be referenced in its second sub-model. Figure 3 Generative model 320 in the middle.

[0147] In some implementations, providing the model with at least one piece of media content and tool description information for a set of candidate video creation tools includes: the electronic device 110 providing at least one piece of media content to the first model and generating material description information corresponding to the at least one piece of media content; and then providing the material description information and tool description information for a set of candidate video creation tools to the second model, so as to determine the video creation tool that matches the video creation scheme from the set of candidate video creation tools.

[0148] As an example, the first model can be referenced. Figure 3 The content comprehension model 310 shown is used as a reference for the second model, which can be referred to as generative model 320.

[0149] As an example, at least one piece of media content can refer to media content 301, the material description information can refer to the image description information 311 corresponding to media content 301, and the tool description information of a set of candidate video creation tools can refer to... Figure 3 The auxiliary decision-making information 314 and the tool research information can be referenced from the final film plan 321 or the n final film information in the final film plan 321. The video content can be referenced from... Figure 3 There are n segments in the array.

[0150] In this way, the embodiments of this disclosure can use the model to quickly determine the video creation tool that matches the video creation scheme based on the media content, and call it to quickly generate video content. This can effectively ensure the accuracy of calling the video creation tool, thereby ensuring the matching of the generated video content with the video creation scheme, and ensuring the efficiency and quality of video generation.

[0151] In some embodiments, the video creation tool includes a template matching tool, and the tool invocation information includes a first search term associated with the template matching tool; and / or, the video creation tool includes a clip editing tool, and the tool invocation information includes a first prompt associated with the clip editing tool; and / or, the video creation tool includes an audio generation tool, and the tool invocation information includes a second prompt associated with the audio generation tool; and / or, the video creation tool includes a text generation tool, and the tool invocation information includes a third prompt associated with the text generation tool; and / or, the video creation tool includes a music matching tool, and the tool invocation information includes a second search term associated with the music matching tool.

[0152] In this way, the embodiments of this disclosure can provide a wealth of video creation tools and tool calling information, and can accurately and quickly call the corresponding video creation tools based on the tool calling information, thereby ensuring the matching of the generated video content with the video creation scheme, and ensuring video generation efficiency and video quality.

[0153] Example devices and equipment

[0154] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 5 A schematic structural block diagram of an example device 500 for generating video according to certain embodiments of the present disclosure is shown. Device 500 may be implemented as or included in electronic device 110. Various modules / components in device 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0155] like Figure 5 As shown, the device 500 includes: a material acquisition module 510, an information presentation module 520, and a first video viewing module 530. The material acquisition module 510 is configured to acquire at least one piece of media content in response to receiving a video generation request in an interactive interface; the information presentation module 520 is configured to present, in a first interface, creative information generated based on at least one piece of media content, the creative information including a scheme description associated with at least one video creation scheme; and the first video viewing module 530 is configured to provide, in a second interface, at least one piece of video content generated based on at least one video creation scheme.

[0156] In some embodiments, in a first interface, creative information generated based on at least one media content is presented, including: in the first interface, presenting a first portion of the creative information, the first portion indicating material description content generated based on at least one media content; and in the first interface, presenting a second portion of the creative information, the second portion indicating scheme description content generated based on the material description content.

[0157] In some embodiments, the scheme description content indicates at least one of the following: thematic information associated with the video creation scheme; and editing information associated with the video creation scheme.

[0158] In some embodiments, the first interface includes a generation control, and the second interface provides at least one video content generated based on at least one video creation scheme, including: in response to the generation control being triggered, presenting the second interface, which provides at least one video content generated based on at least one video creation scheme.

[0159] In some embodiments, the first interface includes an input control, and the device 500 further includes a module that performs the following processes: acquiring input information via the input control; and regenerating a video creation scheme based on the input information for generating corresponding video content.

[0160] In some embodiments, at least one video content corresponds to a first set of video content, and the device 500 further includes a second video viewing module configured to provide, in a second interface, a second set of video content generated based on a set of video templates and at least one media content, wherein the set of video templates is determined based on at least one media content.

[0161] In some embodiments, the device 500 further includes an entry presentation module configured to present a preview entry corresponding to at least one video content in a second interface, the preview entry presenting title text associated with at least one video content.

[0162] In some embodiments, the title text is generated by a second model based on at least one piece of information: at least one piece of media content; editorial information associated with at least one piece of media content; and at least one video creation scheme.

[0163] In some embodiments, the device 500 further includes a stop creation module configured to, in response to receiving a generation request before creation information is generated, trigger a halt to the generation of creation information and provide video content generated based on a video template, the video template being determined based on at least one piece of media content.

[0164] In some embodiments, the device 500 further includes a video editing module configured to: receive an editing request for target video content in at least one video content; and, in response to the editing request, present an editing interface for the target video content.

[0165] In some embodiments, at least one piece of video content is generated based on the following process: providing a model with at least one piece of media content and tool description information of a set of candidate video creation tools; using the model to determine a video creation tool that matches the video creation scheme from the set of candidate video creation tools; and generating tool invocation information associated with the video creation tool by the model, so that the video creation tool can generate video content corresponding to the video creation scheme based on the tool invocation information.

[0166] In some embodiments, the video creation tool includes a template matching tool, and the tool invocation information includes a first search term associated with the template matching tool; and / or, the video creation tool includes a clip editing tool, and the tool invocation information includes a first prompt associated with the clip editing tool; and / or, the video creation tool includes an audio generation tool, and the tool invocation information includes a second prompt associated with the audio generation tool; and / or, the video creation tool includes a text generation tool, and the tool invocation information includes a third prompt associated with the text generation tool; and / or, the video creation tool includes a music matching tool, and the tool invocation information includes a second search term associated with the music matching tool.

[0167] In the apparatus 500 provided in the embodiments of this disclosure, the specific processing procedures of each module and the technical effects they bring can be referred to the relevant description of the example process 400 above, and will not be repeated here.

[0168] like Figure 6 As shown, electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, at least one processor 610 or processing unit, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processor 610 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600.

[0169] Electronic device 600 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 630 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 600.

[0170] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 6 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0171] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0172] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 600, or with any device that enables electronic device 600 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0173] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0174] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0175] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0176] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0177] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0178] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating video, comprising: In response to receiving a video creation request in the interactive interface, acquire at least one piece of media content; In the first interface, creative information generated based on the at least one media content is presented, the creative information including scheme description content associated with at least one video creation scheme; as well as The second interface provides at least one video content generated based on the at least one video creation scheme.

2. The method according to claim 1, wherein, The creation information generated based on the at least one media content, presented in the first interface, includes: In the first interface, a first portion of the creation information is presented, the first portion indicating material description content generated based on the at least one media content; and In the first interface, a second part of the creation information is presented, which indicates the scheme description content generated based on the material description content.

3. The method according to claim 1, wherein, The description of the scheme indicates at least one of the following: Thematic information related to the video creation plan; Editing information associated with the video creation plan.

4. The method according to claim 1, wherein, The first interface includes generation controls, and the second interface provides at least one piece of video content generated based on the at least one video creation scheme, including: In response to the generation control being triggered, the second interface is presented, which provides the at least one video content generated based on the at least one video creation scheme.

5. The method according to claim 1, wherein, The first interface includes input controls, and the method further includes: Input information is obtained via the input control; and Based on the input information, a video creation scheme is regenerated to generate the corresponding video content.

6. The method according to claim 1, wherein, The at least one piece of video content corresponds to the first group of video content, and the method further includes: In the second interface, a second set of video content is provided, which is generated based on a set of video templates and the at least one piece of media content, wherein the set of video templates is determined based on the at least one piece of media content.

7. The method according to claim 1, further comprising: In the second interface, a preview entry corresponding to the at least one video content is presented, and the preview entry presents title text associated with the at least one video content.

8. The method according to claim 7, wherein, The title text is generated by the second model based on at least one of the following pieces of information: At least one of the media contents; Editing information associated with at least one of the media contents; The at least one video creation scheme.

9. The method according to claim 1, further comprising: In response to receiving a generation request before the creation information is generated, the generation of the creation information is stopped and video content generated based on a video template is provided, the video template being determined based on the at least one piece of media content.

10. The method according to claim 1, further comprising: Receive an editing request for target video content in the at least one video content; as well as In response to the editing request, an editing interface for the target video content is presented.

11. The method according to claim 1, wherein, The at least one piece of video content is generated based on the following process: Provide the model with tool description information for at least one piece of media content and a set of candidate video creation tools; Using the model, determine the video creation tool that matches the video creation scheme from the set of candidate video creation tools; as well as The model generates tool call information associated with the video creation tool, so that the video creation tool can generate video content corresponding to the video creation scheme based on the tool call information.

12. The method according to claim 11, wherein: The video creation tool includes a template matching tool, and the tool invocation information includes a first search term associated with the template matching tool; and / or The video creation tool includes a clip editing tool, and the tool invocation information includes a first prompt message associated with the clip editing tool; and / or The video creation tool includes an audio generation tool, and the tool invocation information includes a second prompt message associated with the audio generation tool; and / or The video creation tool includes a text generation tool, and the tool invocation information includes third prompt information associated with the text generation tool; and / or The video creation tool includes a music matching tool, and the tool call information includes a second search term associated with the music matching tool.

13. An apparatus for generating video, comprising: The media acquisition module is configured to acquire at least one piece of media content in response to receiving a video creation request in the interactive interface; The information presentation module is configured to present creation information generated based on the at least one media content in a first interface, the creation information including scheme description content associated with at least one video creation scheme; as well as The first video viewing module is configured to provide at least one video content generated based on the at least one video creation scheme in the second interface.

14. An electronic device comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 12 when executed by the at least one processor.

15. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 12.

16. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 12.

Images